Compare commits

...

430 Commits

Author SHA1 Message Date
anderewrey 251eba1392 feat(workflows): add brownfield epic scoping to detect file churn (#1823)
Add design completeness gate, file overlap check, and validation
to prevent unnecessary file churn when epics target the same component.
2026-04-26 17:30:42 -05:00
Brian 350688df67
fix(installer): resolve url-source custom modules from custom-modules cache (#2323)
* fix(installer): resolve url-source custom modules from custom-modules cache

resolveInstalledModuleYaml previously only searched ~/.bmad/cache/external-modules/,
so modules installed via --custom-source <git-url> (cached at
~/.bmad/cache/custom-modules/<host>/<owner>/<repo>/) could not be located on
re-install runs. This caused warnings during npx bmad-method install:

  [warn] collectAgentsFromModuleYaml: could not locate module.yaml for '<name>'
  [warn] writeCentralConfig: could not locate module.yaml for '<name>'

Adds a fallback that walks the custom-modules cache via _findCacheRepoRoots
(identifying repo roots by .bmad-source.json or .claude-plugin/, not
marketplace.json, so direct-mode modules are also covered), reuses the same
searchRoot candidate-path logic, and matches by the discovered yaml's code
or name field.

Works without needing _resolutionCache to be populated, which fixes the
re-install scenario where no --custom-source flag is passed.

Closes #2312

* fix(installer): enumerate all module.yamls when walking custom-modules cache

A url-source custom-modules repo can host multiple plugins in discovery
mode (e.g. skills/module-a/module.yaml and skills/module-b/module.yaml).
The previous walk used searchRoot which returned only the first match,
so asking for module-b would surface module-a's yaml, fail the code/name
check, and skip the repo entirely — never inspecting module-b.

Splits the candidate-path traversal into searchRootAll (returns every
module.yaml in priority order) and a thin searchRoot wrapper for the
existing single-module fallbacks. The custom-modules walk now iterates
every yaml per repo and matches each against code or name.
2026-04-26 15:53:36 -05:00
Curtis Ide be85e5b4a0
fix(installer): support local custom-source modules in resolveInstalledModuleYaml and TOML key (#2316)
- resolveInstalledModuleYaml: fall back to CustomModuleManager._resolutionCache for local
  custom-source modules (external cache path doesn't exist for these); refactor candidate-path
  search into shared searchRoot() helper; add *-setup/assets/module.yaml BMB standard path
- manifest-generator: use module code field (not display name) as TOML section key [modules.X]

Co-authored-by: cidemaxio <cidemaxio@users.noreply.github.com>
2026-04-26 12:55:56 -05:00
Brian 04cfde1454
fix(installer): mirror launch channel as default for external modules (#2321)
* fix(installer): mirror launch channel as default for external modules

When the user runs `npx bmad-method@next install`, the installer itself
runs from a prerelease, but the interactive channel gate previously hardcoded
"(all stable)" — defaulting tea/community modules to stable while bmad-method
itself was on next. The bleeding-edge launch did not flow through.

Detect the installer's own version via semver.prerelease() and default the
gate (and per-module picker) to match — "all next" for prerelease launches,
"all stable" for stable. Users keep full control: hit "n" to customize per
module, or pass explicit --channel / --pin / --next flags to override.

* fix(installer): seed channelOptions before module picker, not gate

CodeRabbit caught a label/install mismatch in the previous approach: the
module picker resolves version labels via decideChannelForModule, which runs
before _interactiveChannelGate. With channelOptions.global still null at
picker time, labels rendered from stable tags — then the gate flipped global
to 'next' and externals installed from main HEAD. Net effect on @next launches:
"tea (v1.6.0)" in the picker, but install pulled HEAD.

Move the launch detection up into promptInstall, immediately after
parseChannelOptions. Seeding channelOptions.global = 'next' before the picker
makes labels resolve from main HEAD (matching the install) and lets the
existing gate's haveFlagIntent check skip cleanly — the @next user already
declared their intent by typing it. Per-module customization remains available
via --pin / --next / --channel flags, same as for any pre-set global.
2026-04-26 10:54:38 -05:00
Brian 7baa30c567
fix(publish): advance @next dist-tag after stable release (#2320)
* fix(publish): advance @next dist-tag after stable release

When a stable release publishes via workflow_dispatch, @latest can leapfrog
the existing @next prerelease (e.g. latest=6.5.0 while next=6.4.1-next.0),
turning `npx bmad-method@next install` into a silent downgrade until the
next qualifying push to main republishes a fresh -next.0.

- publish.yaml: after stable publish, repoint @next at the just-published
  stable version. The existing derive-prerelease step picks max(latest, next)
  as its base, so subsequent push-driven prereleases bump from there.
- bmad-cli.js: checkForUpdate was querying the @beta dist-tag (which this
  package does not use). Replace string-matching with semver.prerelease()
  and query @next for prerelease users.

* fix(publish): harden next-tag advance step and broaden path filter

- continue-on-error on the dist-tag advance: failure leaves @next stale
  until the next push-driven prerelease, which is recoverable; failing the
  job after a successful publish + git tag + GH release is not.
- Status echo so release-log triage can confirm the advance ran.
- Add removals.txt to the push-trigger path filter. Installer-affecting
  changes outside src/** (like the post-6.5.0 removals.txt fix) should
  still trigger a fresh -next.0 publish.
2026-04-26 10:30:41 -05:00
Brian 88b9a1c842
fix(installer): remove pre-v6.2.0 wrapper skills on update (closes #2309) (#2315)
Adds 32 entries to removals.txt covering the module-prefixed wrapper
skill names used pre-v6.2.0 (bmad-bmm-* and bmad-agent-bmm-*). Users
upgrading from v6.0.x / v6.1.x had these installed in their IDE skill
directories, but the v6.2.0 architecture switch dropped the module
prefix and the cleanup never knew the old names. Stale wrappers stayed
behind alongside the new self-contained skills, causing duplicates and
broken-file errors when invoked (referenced files no longer exist).

The removals.txt entries get added to the cleanup removalSet on every
install/update, so the next install run for an upgrading user removes
the stale wrappers automatically.
2026-04-25 22:08:44 -05:00
github-actions[bot] 69cbeb4d07 chore(release): v6.5.0 [skip ci] 2026-04-26 02:25:31 +00:00
Brian 1d35acfd84
docs: add v6.5.0 changelog entry (#2314) 2026-04-25 21:24:43 -05:00
Brian 01cc32540b
feat(installer): expand to 42 platforms with shared target_dir coordination (#2313)
* refactor(installer): replace legacy_targets auto-cleanup with upgrade warnings

Removes the legacy_targets YAML field and its install-time auto-migration
of pre-v6.1.0 directories (.claude/commands, .opencode/agents, etc.). On
install, surface a warning instead: read manifest version and scan 24
known legacy paths, then print rm -rf commands the user can run themselves.
Also deletes orphan tools/platform-codes.yaml (never loaded by any code)
and fixes a stale URL in the cs translation.

* feat(installer): consolidate to .agents/skills and add global_target_dir for all platforms

Updates platform-codes.yaml against verified primary docs for all 24 supported
platforms. 14 platforms (auggie, codex, crush, cursor, gemini, github-copilot,
kilo, kimi-code, opencode, pi, roo, rovo-dev, windsurf) move their project
target_dir to the cross-tool .agents/skills/ standard. Junie moves from the
broken .agents/skills/ to its own .junie/skills/ per JetBrains docs.

Adds global_target_dir to every platform: 11 share ~/.agents/skills/, Crush
uses XDG ~/.config/agents/skills/, Codex global stays ~/.codex/skills/, the
rest are tool-specific. Ona and Trae omit global (no documented home path).

Note: installer logic does not yet dedupe writes for platforms sharing a
target_dir — users installing multiple .agents/skills/ tools together will
overwrite the same files (harmless on install, but uninstalling one clears
the dir for the others). Coordination logic is the next step.

* feat(installer): add 18 new platforms, dedup shared target_dir, ownership-aware cleanup

Adds 18 platforms from the verified Vercel list (adal, amp, bob, command-code,
cortex, droid, firebender, goose, kode, mistral-vibe, mux, neovate, openclaw,
openhands, pochi, replit, warp, zencoder). Marks codex and github-copilot as
preferred alongside claude-code and cursor.

Coordination for platforms sharing a target_dir:

- IdeManager.setupBatch dedups skill writes when multiple selected platforms
  point at the same target_dir (e.g. .agents/skills/). The first platform
  writes, peers skip the redundant wipe-and-rewrite. Result reports the same
  count and target dir for every member so the install summary is consistent.

- IdeManager.cleanupByList accepts remainingIdes; when removing one platform
  from a shared dir while another co-installed platform still owns it, the
  target_dir wipe is skipped. Platform-specific hooks (copilot markers, kilo
  modes, rovodev prompts) still run.

- _setupIdes uses setupBatch; _removeDeselectedIdes passes remainingIdes so
  partial reconfigure preserves shared skills.

Skill ownership now uses skill-manifest.csv canonicalIds, not the bmad- prefix.
This unblocks custom modules that ship skills with non-bmad names (e.g.
fred-cool-skill). Affected sites:

- _config-driven.detect: reads canonicalIds from the project's bmadDir
- _config-driven.findAncestorConflict: reads canonicalIds from the ancestor's
  own bmadDir, falling back to the prefix only when no manifest exists
- legacy-warnings.findStaleLegacyDirs: same canonicalId-based detection

Migration warnings: LEGACY_SKILL_PATHS adds 12 skill dirs that moved to the
.agents/skills/ standard (cursor, gemini, github-copilot, kimi, opencode, pi,
roo, rovodev, windsurf, plus their globals). Users with stale skills in those
locations get a one-line warning with the rm command per dir.

New shared helper tools/installer/ide/shared/installed-skills.js exposes
getInstalledCanonicalIds(bmadDir) and isBmadOwnedEntry(entry, canonicalIds).

Tests: 9 new assertions across two suites covering dedup, partial uninstall
preservation, and custom-module skill detection. All 286 tests pass.

* fix(installer): setupBatch must not claim a shared target_dir on failure

If the first platform's setup throws or returns success: false, the dedup map
previously still recorded the claim with skillCount: 0, causing every peer
sharing the target_dir to skip its install — leaving the dir empty/broken
behind a cascade of misleading "shares with X" rows.

Now the claim is only recorded when the install succeeded and wrote skills.
On failure, the next peer becomes the new first writer and recovers.

Adds Suite 40b regression test that monkey-patches cursor.setup to throw
and verifies gemini still populates the shared dir.

* fix(installer): address PR #2313 review findings

Three issues raised by augmentcode and coderabbit bot reviewers:

1. _removeDeselectedIdes silently swallowed cleanup failures after the
   refactor to cleanupByList. The old per-IDE try/catch logged a warning;
   the new path discarded the result array. Now logs a warning per failed
   ide so failures stay visible.

2. The legacy-dir cleanup hint printed `rm -rf "<path>"/bmad*` which both
   matched bmad-os-* utility skills the user should keep AND missed the
   custom-module skills (e.g. fred-cool-skill) that the new canonical-id
   detection now finds. Findings now carry the exact entry names from the
   scan, and the warning prints one precise rm line per entry.

3. warnPreNativeSkillsLegacy did unguarded fs reads at install start. A
   permission/IO error would have aborted the whole install. Wrapped the
   call site in try/catch so legacy-scan failures only emit a warning.
2026-04-25 21:14:00 -05:00
github-actions[bot] 1197122001 chore(release): v6.4.0 [skip ci] 2026-04-25 03:34:02 +00:00
Brian 314fe69d14
docs: add v6.4.0 changelog entry (#2310) 2026-04-24 22:31:01 -05:00
Yahya Bin Naveed 9ff9d6f8f3
feat: add Kimi Code CLI support (#2302)
Adds kimi-code to both platform-codes.yaml files so Kimi Code CLI
is available as an install target via the config-driven installer.
Skills are installed to .kimi/skills/, which is the project-level
skills directory per the official Kimi Code CLI documentation.

Closes #1630

Co-authored-by: Brian <bmadcode@gmail.com>
2026-04-24 18:22:09 -05:00
Pablo Ontiveros c29b72ecc0
fix(create-story): read UPDATE files before generating dev notes (#2274)
When a story modifies existing files, create-story must read those
files before generating dev notes. Without this, dev agents improvise
design decisions without knowing the current state of the code, leading
to regressions caught only at review time.

Adds a step at the end of Step 3 (Architecture analysis) that reads
every file marked UPDATE in the architecture directory structure and
documents its current state, what the story changes, and what must
be preserved.

Fixes #2273

Co-authored-by: Brian Madison <bmadcode@gmail.com>
2026-04-24 18:21:10 -05:00
Jérôme Revillard e7a213ed07
feat: uniform customize.toml support across all BMM workflows (#2308)
* feat: extend customize.toml to all 6 developer-execution workflows (#2303)

Add uniform customization support to dev-story, code-review,
sprint-planning, sprint-status, quick-dev, and checkpoint-preview,
matching the same 4 extension points (activation_steps_prepend,
activation_steps_append, persistent_facts, on_complete) already
available on 17 BMM workflows from PR #2287.

- Create customize.toml for each workflow
- Add 6-step activation block to SKILL.md (merge workflow.md
  content in, delete workflow.md per PR #2287 pattern)
- Wire on_complete at terminal steps (inline <action> for XML
  workflows, ## On Complete section for step-file workflows)
- Fix pre-existing step number reference in dev-story (Step 6 → 9)

* fix: correct goto step="6" → step="9" in dev-story

The XML goto at line 203 still pointed to step 6 ("Author
comprehensive tests") instead of step 9 ("Story completion and mark
for review"), which is the actual completion gate. This was the
same class of pre-existing bug fixed in the text (M-1) but
missed in the XML action.

---------

Co-authored-by: Brian <bmadcode@gmail.com>
2026-04-24 17:45:25 -05:00
Murat K Ozcan 0533976753
fix: installer live version for external modules (#2307)
* resolved merge conflict

* fix: addressed PR comments

* fix: use git tags for installer module versions
2026-04-24 13:13:56 -05:00
Brian 3d824d4c0f
feat(installer): channel-based version resolution + interactive channel management (#2305)
* feat(installer): channel-based version resolution for external modules

Adds stable/next/pinned channel resolution so external/community modules
install at released git tags by default instead of tracking main HEAD.
Manifest now records channel, resolved version, and SHA per module for
reproducible installs.

CLI flags: --channel, --all-stable, --all-next, --next=CODE (repeatable),
--pin CODE=TAG (repeatable). Precedence: pin > next > channel > registry
default > stable. --yes accepts patch/minor upgrades but refuses majors.

Interactive "Ready to install (all stable)?" gate with a per-module
picker (stable/next/pin) when declined. Re-install prompts classify tag
diffs as patch/minor/major with semver-class-dependent defaults.
Legacy version:null manifests get a one-time migration prompt.

Custom modules gain an optional @<ref> URL suffix for pinning (https,
ssh, /tree/<ref>/subdir forms supported; local paths rejected).
Community modules honor --next/--pin overrides with a curator-bypass
warning; default path still enforces the approved SHA.

Quick-update now reads the manifest's recorded channel per module so
pinned installs don't silently roll forward.

* feat(installer): interactive channel switch, upgrade refusal, unified docs

Builds on the channel-resolution foundation. The installer now lets users
flip a module between stable, next, and pinned after install — either
interactively via a "Review channel assignments?" gate, or by flag. Quick
and modify re-installs classify stable upgrades; under non-interactive
flows, patches and minors apply automatically but majors are refused with
a pointer to --pin.

Fallback behavior for GitHub rate-limit / network failures is now cache-
aware: re-installs reuse the recorded ref silently; fresh installs abort
with actionable guidance (set GITHUB_TOKEN or use --next/--pin). Bundled
modules (core, bmm) warn when targeted by --pin or --next so users aren't
left wondering why the flag had no effect.

Install summary labels no longer mangle "main" into "vmain"; next-channel
entries render as "main @ <short-sha>" instead. Bundled modules are now
correctly skipped from all channel prompts and tag-API lookups.

Docs consolidated into a single how-to. install-bmad.md now covers the
interactive flow, the channel model (stable/next/pinned plus the npm
dist-tag axis for core/bmm), the re-install upgrade prompts, the full
flag reference, copy-paste recipes, and troubleshooting. The old
non-interactive-installation.md is reduced to a redirect stub.

* fix(installer): review fixes + unit tests for channel resolution

- ui.js: import parseGitHubRepo; fixes ReferenceError in the
  interactive channel picker's stable-tag pre-resolve path.
- community-manager: pinned modules now fetch+checkout the pin tag
  on cache refresh instead of resetting to origin/HEAD (was silently
  drifting to main on re-install).
- channel-plan: parseChannelOptions returns acceptBypass so --yes
  auto-confirms the curator-bypass prompt; headless --next/--pin
  installs of community modules no longer hang.
- community-manager: simplify recordedVersion (dead ternary branch).
- custom-module-manager: drop "or sha" from the @<ref> comment
  (git clone --branch rejects raw SHAs); update-path fetches
  origin <ref> so /tree/<branch>/ URLs work too.
- install-bmad.md: rename "Headless / CI installs" to "Headless CI
  installs" so the stub's #headless-ci-installs anchor resolves.
- test/test-installer-channels.js: 83 unit tests for channel-plan
  and channel-resolver pure modules; wired into npm test as
  test:channels.

* fix(installer): address CodeRabbit review findings

- ui.js: skip stable-channel upgrade classification when the user has
  already declared intent via --pin/--next=/--channel or the review
  gate. Prevents the decline / major-refused / fetch-error branches
  from silently overwriting an explicit pin with prev.version.
- external-manager.js: short-circuit cloneExternalModule when the
  requested plan matches an existing in-process resolution and the
  cache is valid. Avoids redundant resolveChannel() + git fetch on
  every same-plan lookup in a single install.
- installer.js: fall back to CommunityModuleManager.getResolution()
  when no external resolution exists, so community module result
  rows carry newChannel/newSha instead of null under --next/--pin.
- installer.js: don't label a module as "no change" when its version
  string is 'main'/'HEAD' — the SHA may have moved and preVersions
  doesn't track the prior SHA. Show "(refreshed)" instead.
- official-modules.js: match versionInfo.version to the manifest's
  cloneRef || (hasGitClone ? 'main' : version) expression so summary
  lines report the cloned ref for git-backed custom installs.
- install-bmad.md: clarify that sha is only written for git-backed
  modules and that rerunning the same --modules on another machine
  does not reproduce stable-channel installs — convert recorded tags
  into explicit --pin flags for cross-machine reproducibility.
2026-04-24 08:20:30 -05:00
Murat K Ozcan 2395b0e2ed
fix: bmad tea instal version (#2298)
* fix: bmad tea instal version

* fix: addressed review comments
2026-04-22 11:03:20 -05:00
Brian 914c4edd6b
fix(installer): resolve external-module agents from cache during manifest write (#2295)
External official modules (bmb, cis, gds, tea, wds) are cloned to
~/.bmad/cache/external-modules/<name>/ and never copied into src/modules/,
so collectAgentsFromModuleYaml silently skipped them and their agents
never reached config.toml. Swap the hardcoded src/modules lookup for a
resolveInstalledModuleYaml() helper that also searches the external cache
(handling src/, skills/, nested, and root layouts) and warns instead of
silently skipping when a module.yaml can't be found.
2026-04-21 22:51:04 -05:00
miendinh 16c9976d7e
docs(vi-vn): sync and update Vietnamese documentation (#2291)
Co-authored-by: miendinh <miendinh@users.noreply.github.com>
2026-04-21 21:31:53 -05:00
Brian 87292cd86a
feat(skills): wire on_complete into terminal steps; add full customize.toml comments (#2290)
All 16 bare workflow customize.toml files now have the same thorough comment
block as the well-documented ones, with skill-specific on_complete descriptions
that name the exact terminal step and exit condition.

on_complete is now executed at the true end of each workflow's terminal step
rather than lazily referenced in SKILL.md:

- Linear workflows: ## On Complete block appended to the final step file
  (create-prd step-12, create-ux-design step-14, create-architecture step-08,
  generate-project-context step-03, check-implementation-readiness step-06,
  epics-and-stories step-04, all three research step-06 files, prfaq verdict,
  document-project both sub-workflow instruction files)
- Multi-path workflows: on_complete inline on each true exit path only
  (edit-prd fires on [S] Summary and [X] Exit, not on [V] Validate or [E] Edit;
  validate-prd fires on [X] Exit only, not on [R], [E], or [F])
- Inline XML workflows: <action> tag at the close of the final step
  (correct-course step-6, create-story step-6, retrospective step-12,
  qa-generate-e2e-tests appended to SKILL.md)
2026-04-20 22:53:23 -05:00
Brian b63086f22e
feat(core-skills): add bmad-customize — guided authoring for _bmad/custom overrides (#2289)
* feat(core-skills): add bmad-customize for authoring _bmad/custom overrides

A conversational guide skill that helps users author or update TOML overrides
in _bmad/custom/ for customizable BMad agents and workflows. Covers per-skill
agent and workflow surfaces; central config is out of scope for v1.

- SKILL.md: six-step flow (intent, discover, route, compose, team-vs-user,
  show-confirm-write-verify) with baked-in agent-vs-workflow routing heuristic
  and a template-swap subroutine
- scripts/list_customizable_skills.py: stdlib-only scanner that enumerates
  customizable skills across standard IDE install paths, reports surface type
  and override status, PEP 723, 10 unit tests
- Reuses _bmad/scripts/resolve_customization.py for post-write verification
- Registered in core-skills/module-help.csv with menu code BC

* refactor(bmad-customize): apply QA pass (top 3 recommendations)

Applies the three highest-payoff themes from the quality analysis:

- Labeling + completion contracts: rename ## Purpose to ## Overview,
  add domain framing (what customization means in BMad, typical user
  arrival shapes), add an explicit Completion block with testable
  conditions for "skill run is done"
- Hostile-environment robustness: add On-Activation preflight that
  classifies no-BMad / BMad-without-resolver / full-install states,
  instruct Step 2 to surface scanner errors[] and scanned_roots on
  empty results, add resolver-missing fallback to Step 6.4, add a
  re-enter-Step-4 recovery loop when verify shows the override didn't
  take effect
- Returning-user and iteration experience: add "Audit / iterate"
  intent class in Step 1, lead discovery with already-overridden
  skills for that intent, read existing overrides in Step 3 before
  composing, frame Step 4 as additive-on-top rather than fresh
  authoring, give Cross-cutting intent an explicit Step 3 branch
  that walks agent-vs-workflow with the user

Resolves 12 of 18 observations from the quality report. Lint clean
(scan-path-standards and scan-scripts both 0 findings). Unit tests
still 10/10.

* refactor(bmad-customize): derive skills root from install location

Previously the scanner hardcoded a list of IDE skill directories
(.claude/skills, .cursor/skills, .cline/skills, .continue/skills) and
scanned them relative to the project root. That was wrong: skills can
be installed either project-local or user-global, the IDE determines
the convention, and the set of valid locations is open-ended.

The scanner now derives its primary skills root from __file__ — the
running skill's own install directory is the authoritative location
for finding siblings. --skills-root overrides the default; --extra-root
(repeatable) adds additional locations for the rare mixed-install case.

Changes:
- list_customizable_skills.py: remove SKILL_ROOTS constant, add
  default_skills_root() derived from __file__, rename scan_project
  to scan_skills(skills_roots, project_root), add --skills-root and
  --extra-root flags, de-dupe skills when the same name appears in
  multiple roots (first wins)
- SKILL.md: update Step 2 to describe the scanner's derive-from-install
  behavior and when to use --extra-root; drop the hardcoded IDE path
  list from Notes
- tests: refactor setUp to place skills under a generic skills root
  (not .claude/skills), add 3 new tests for multiple-roots merge,
  duplicate-name precedence, and missing-root error reporting

* docs(customization): point users at bmad-customize as the guided path

Surface the new bmad-customize skill across the three customization
docs so users know they don't need to hand-author TOML to benefit
from the surface:

- customize-bmad.md: prominent tip at the top introducing the skill
  as the guided authoring helper; updated the "Need to see what's
  customizable?" troubleshooting tip to recommend the skill first
- expand-bmad-for-your-org.md: tip under prereqs noting every recipe
  can be applied via the skill, with the recipes remaining the
  reference for what to override
- named-agents.md: short paragraph in the customization section and a
  link entry under the references list

Hand-authoring still works the same way; the skill is additive.
Central-config overrides are flagged as the current exception.

* docs(bmad-customize): steer users at bmad-builder instead of 'forking'

* fix(bmad-customize): reword description to pass file-ref validator

* refactor(bmad-customize): tighten description and expand module-help entry

- SKILL.md description: drop the catch-all 'or asks how to change the
  behavior of a specific BMad skill' trigger clause that would fire in
  casual discussion; keep the four explicit phrase triggers.
- module-help.csv: rewrite the description so bmad-help has real
  routing material — names the concrete capabilities (persistent
  facts, template swaps, activation hooks, menus), the scope routing,
  and the value prop (no TOML hand-authoring). Matches the 'Use
  when...' pattern other Core entries use.

* fix(module-help): quote bmad-customize description field that contains commas

* fix(bmad-customize): address PR #2289 review findings

- SKILL.md preflight: load root config from _bmad/config.toml and
  config.user.toml (not .yaml) — the installer emits TOML; the YAML
  references would have made the skill silently miss real user config
- SKILL.md resolver fallback (Step 6.4): read all three merge layers
  when present (base / team / user) and describe the merge in
  base → team → user order; the prior wording could describe the wrong
  effective merge when the user wrote .user.toml on top of an existing
  team .toml
- SKILL.md: replace bare 'docs/how-to/customize-bmad.md' references
  (3 locations) with the public docs URL so users installing the skill
  aren't pointed at a path they don't have locally
- list_customizable_skills.py: catch UnicodeDecodeError in
  read_frontmatter_description so a non-UTF-8 SKILL.md can't abort
  the whole scan
- list_customizable_skills.py: clarify exit-code contract in the
  module docstring — errors[] is non-fatal by design, exit 2 is
  reserved for invocation errors
- customize-bmad.md: tighten the tip to scope bmad-customize to the
  per-skill surface; central-config is out of scope v1
- expand-bmad-for-your-org.md: same scoping — Recipes 1-4 can be
  applied by the skill; Recipe 5 (central config) stays hand-authored

* fix(bmad-customize): markdownlint MD034 and validate-file-refs

- Wrap the three docs.bmad-method.org references as
  [text](url) markdown links instead of bare URLs (MD034)
- Drop the {project-root}/ prefix on line 41's config.toml
  references. validate-file-refs strips the template prefix and
  tries to resolve 'config.toml' as 'src/config.toml'; sibling
  skills (party-mode, retrospective, advanced-elicitation) all
  reference '_bmad/config.toml' bare and pass CI — match that
  pattern. The '(root level under {project-root}, installer-owned)'
  parenthetical preserves the disambiguation.

* refactor(bmad-customize): cut token-wasting prose from SKILL.md

Down from 175 lines to 110. Removed:
- 'What customization means in BMad' architecture backgrounder — the
  LLM reads the live customize.toml in Step 3; doesn't need the lore
- 'Desired Outcomes' section — retrospective narration of what the
  6 steps already instruct
- 'Role' section — fluff; the flow itself defines the role
- 'Notes' section — sparse-override rule already in Step 4, IDE-path
  note is commentary, docs link duplicates the out-of-scope section
- 'The scanner derives its skills directory from...' and 'returns JSON
  with...' — commentary the LLM doesn't need; it runs the script and
  sees the output
- 'that file IS the schema' and similar editorial asides throughout
- Explanatory clauses like 'silently drifts on every release' and
  'trust the user's domain knowledge'

Kept everything that's load-bearing: preflight conditionals, intent
classification, routing heuristic, merge semantics, template-swap
subroutine, team-vs-user defaults, verify fallback and recovery loop,
completion conditions, out-of-scope list.
2026-04-20 22:14:54 -05:00
Brian ffdd9bc69e
feat(skills): add TOML workflow customization to 17 bmm-skills (#2287)
* feat(skills): add TOML workflow customization to 17 bmm-skills

Flattens each skill's workflow.md into SKILL.md and adds a customize.toml
surface with a 6-step activation block (resolve_customization, prepend,
persistent_facts, config, greet, append). Core-skills and developer
execution skills (dev-story, code-review, sprint-planning, sprint-status,
quick-dev, checkpoint-preview) are intentionally excluded.

Customized: document-project, prfaq, domain/market/technical-research,
create-prd, create-ux-design, edit-prd, validate-prd,
check-implementation-readiness, create-architecture,
create-epics-and-stories, generate-project-context, correct-course,
create-story, qa-generate-e2e-tests, retrospective.

* fix(skills): address PR review findings on workflow customization

- bmad-create-story: drop stale {project_context} variable reference
  from step 2 note; content is already loaded via persistent_facts
- research skills (market/domain/technical): derive research_topic_slug
  before writing output filename to prevent path injection and invalid
  filesystem characters
- bmad-correct-course: reconcile step 1 verify list and HALT with the
  "Missing documents" rule — Architecture and UI/UX are optional, HALT
  only fires when PRD or Epics are missing
- fix grammar in Micro-file Design bullets across 5 migrated skills
  (self contained → self-contained, adhere too 1 file → adhere to one
  file at a time)
- docs/how-to/customize-bmad.md: document workflow activation order
  and frame the baseline fields as a stable initial pass with targeted
  per-workflow customization points coming later
2026-04-20 20:10:22 -05:00
Brian 1251458173
feat(agents): set team to software-development on BMM agents (#2286)
* feat(agents): set team to software-development on BMM agents

All six BMM agents (analyst, tech-writer, PM, UX designer, architect,
dev) now explicitly declare `team: software-development` in the
module.yaml roster instead of falling back to the module-code default
of `bmm`.

This matches the BMad-wide team convention where agents across modules
that collaborate on software delivery share one named team. Tea's Murat
joins the same team via a parallel PR in bmad-method-test-architecture-
enterprise so party-mode, help catalog, and retrospective skills can
route the full software-delivery roster as a single unit.

* test: update team assertions for explicit software-development
2026-04-20 00:11:16 -05:00
Brian 4405b817a9
refactor(skills): remove bmad-skill-manifest yaml; introduce central config.toml (#2285)
* refactor: remove bmad-skill-manifest yaml; introduce four-layer central config.toml

- Agent essence moves from per-skill bmad-skill-manifest.yaml files
  into each module.yaml's `agents:` block (code, name, title, icon,
  description). Per-agent customize.toml remains the deep-behavior
  source of truth.
- Installer emits four TOML files:
    _bmad/config.toml              team install answers + agent roster
    _bmad/config.user.toml         user install answers
    _bmad/custom/config.toml       team overrides stub
    _bmad/custom/config.user.toml  personal overrides stub
  Prompts declare scope: user to route answers to config.user.toml.
- resolve_config.py merges four layers: base-team -> base-user ->
  custom-team -> custom-user.
- Three consumer skills (party-mode, advanced-elicitation,
  retrospective) switched from agent-manifest.csv to the resolver.
- installer.js mergeModuleHelpCatalogs now takes the in-memory
  agent list from ManifestGenerator -- no CSV roundtrip.
- Deleted: 6 bmad-skill-manifest.yaml files, agent-manifest.csv
  emission, collectAgents/getAgentsFromDirRecursive,
  paths.agentManifest().

* fix(installer): strip core-key pollution from [modules.*]; soften config headers

- writeCentralConfig now always strips core-module keys from every
  [modules.<code>] bucket, even when the module's schema is not
  available in src/ (external / marketplace modules like cis, bmb).
  Core values belong in [core] only; workflows read them directly.
- When the module's own schema IS available (built-in modules),
  also drop any key it does not declare as a prompt — same
  spread-pollution filter as before, now layered on top.
- Section-aware headers on both _bmad/config.toml and
  _bmad/config.user.toml: [core] / [modules.*] values are
  editable (installer reads them as defaults on next install);
  [agents.*] is regenerated from module.yaml and will be wiped —
  overrides for agents go in _bmad/custom/config*.toml instead.

* docs: cover central config.toml + Diataxis prose pass across three files

Document the new four-file central configuration surface (_bmad/config.toml,
config.user.toml, and custom/ overrides) alongside the existing per-skill
customize.toml. Make editing rules, scope partitioning, and when-to-use-which
guidance explicit.

- customize-bmad.md: new "Central Configuration" section with editing rules,
  three worked examples (rebrand, fictional agent, module settings override),
  and a "when to use which surface" table. Converted five h4 headers to
  bold paragraph intros per style guide.
- expand-bmad-for-your-org.md: two-layer mental model extended to three;
  new Recipe 5 with three variants (rebrand, custom crew, pinned team
  settings); reinforcement table extended.
- named-agents.md: noted the dual customization surface — per-skill shapes
  behavior, central config shapes roster identity.

Diataxis prose pass applied across all three files: banned vocabulary
check, em-dash cap, hypophora / metanoia / amplificatio / stakes-inflation
cleanup, rhythm and burstiness fixes. Structural conformance verified;
markdownlint and prettier clean.

* test+docs: add central config unit tests; fix stale recipe count

- test: two new suites (35 + 36) covering writeCentralConfig and
  ensureCustomConfigStubs. Verifies scope partitioning (user_name
  lands only in config.user.toml), core-key pollution stripping
  from [modules.*], unknown-schema fallthrough (external modules
  survive without schema), agent roster baked into config.toml
  [agents.*] only, stub-preservation on re-install. 44 new
  assertions.
- docs: fixed four stale "four recipes" references to say "five"
  after Recipe 5 (Customize the Agent Roster) was added. Touches
  frontmatter, opening paragraph, Combining Recipes paragraph,
  and the named-agents cross-link blurb.

* fix: address PR review feedback on central config

- resolve_config.py argparse: three-layer → four-layer description
- SKILL/workflow/explanation docs: document all four layers including
  _bmad/config.user.toml (was missing from merge-stack descriptions)
- customize-bmad.md + installer headers: drop the false "direct edits to
  config.toml persist" claim; installer reads from per-module config.yaml,
  not central TOML, so direct edits get clobbered. Route users to
  _bmad/custom/config.toml for durable overrides
- writeCentralConfig: warn loudly when a module.yaml can't be parsed
  (previously silent — user-scoped keys could mis-file into team config)
- writeCentralConfig: preserve [agents.*] blocks for modules that didn't
  contribute fresh agents this run (e.g. quickUpdate skipping modules
  whose source is unavailable) so the roster doesn't silently shrink
- add extractAgentBlocks helper + Test Suite 37 covering preservation

Addresses comments from augmentcode and coderabbitai on PR #2285.
2026-04-19 23:11:44 -05:00
Brian 0dbfae675b
feat(skills): TOML-based agent and workflow customization (#2284)
* feat(skills): TOML-based agent customization with stdlib Python resolver

Re-applies PR #2282's three-layer customization model (skill defaults →
team → user) but swaps YAML for TOML and uv for stdlib tomllib. Users
no longer need uv, pip, or a virtualenv — plain python3 (3.11+) is
sufficient, since tomllib shipped in the standard library.

## Schema changes vs PR #2282

- Flat agent schema: fields live directly under [agent], no nested
  metadata/persona sub-tables. Easier to author, less indentation.
- Non-configurable identity: name and title are declared in
  customize.toml as source-of-truth metadata (for future skill-manifest
  generation) but SKILL.md ignores overrides there — identity is
  hardcoded to preserve brand recognition.
- role redefined: now describes what the skill does for the user
  within its module phase, not a restatement of the title.
- persistent_facts replaces the activation-time file-context load AND
  the old memories concept. Entries can be literal sentences or
  file: prefixed paths/globs; avoids collision with the upcoming
  runtime memory sidecar.
- activation_steps_prepend / activation_steps_append harmonized across
  agents and workflows (replaces agent-specific critical_actions).
- [workflow] namespace mirrors [agent] for workflow customization.
  Same four structural rules, same field vocabulary.

## Resolver (src/scripts/resolve_customization.py)

Four purely structural merge rules, zero field-name hardcoding:

  - Scalars: override wins
  - Tables: deep merge
  - Arrays of tables where every item has `code` or `id`: merge by
    that key (matching keys replace, new keys append)
  - Any other array: append

No removal mechanism — overrides cannot delete base items. Fork the
skill or override by code with a no-op value to suppress defaults.

## Agents ported (6)

All six BMad agents now ship customize.toml + rewritten SKILL.md:
analyst (Mary), tech-writer (Paige), pm (John), ux-designer (Sally),
architect (Winston), dev (Amelia). Each uses the same 8-step
activation template: resolve → execute prepend → adopt persona →
load persistent facts → load config → greet (with {agent.icon}) →
execute append → dispatch or present menu.

Step 8 supports fast-path invocation: "hey Mary, let's brainstorm"
dispatches the matching menu item directly after greeting, skipping
the menu render when intent is clear. Chat, clarifying questions,
and bmad-help remain available when nothing on the menu fits.

## Installer + tooling

- _bmad/scripts/ provisioned on install (copies src/scripts/)
- _bmad/custom/ seeded with .gitignore for *.user.toml on fresh install
- Non-module-dir filter extended to skip _memory, memory, docs,
  scripts, and custom when scanning for modules
- Dead _config/agents/ directory no longer created
- metadata.capabilities removed from agent-manifest.csv and schema
- eslint config extended to cover src/scripts/**
- validate-file-refs.js knows about custom/ as install-only

## Deferred for follow-up

- bmad-product-brief workflow port (the pilot that demonstrates
  [workflow] + on_complete)
- Translated docs (cs/fr/vi-vn/zh-cn) — regenerate from English

* feat(skills): port bmad-product-brief to TOML workflow customization

Completes the customization surface rollout by giving the product-brief
workflow the same override model as the six BMad agents, under the
[workflow] namespace instead of [agent].

## customize.toml

Mirrors the agent shape under [workflow] with:
- activation_steps_prepend / activation_steps_append (harmonized across
  agents and workflows — same field names, same append semantics)
- persistent_facts with the file: convention, seeded with
  file:{project-root}/**/project-context.md
- on_complete scalar (renamed from PR #2282's skill_end for clarity —
  reads cleaner as "what runs when the workflow completes")

## SKILL.md

7-step workflow activation:
  1. Resolve workflow block
  2. Execute prepend steps
  3. Load persistent facts (file: or literal)
  4. Load config
  5. Greet if not already
  6. Execute append steps
  7. Stage 1 — Understand Intent

python3 + stdlib tomllib invocation; no uv required.

## Prompt file changes

- Path normalization: ../agents/ → agents/, ../resources/ → resources/,
  bare foo.md → prompts/foo.md. All references now resolve from the
  skill root (matches the convention documented in SKILL.md).
- Paths: meta-line added to each of the 4 prompt files that reference
  other files, reinforcing "bare paths resolve from skill root" so the
  LLM doesn't lose the convention when operating two hops into a
  prompt chain.
- finalize.md terminal stage now calls the resolver for
  workflow.on_complete — non-empty values run as the final step.

## Validation

- Resolver output verified: 4 workflow fields returned cleanly.
- validate-file-refs.js: 254 files scanned, 139 refs checked, 0 broken.
- test:refs: passing.

* docs(skills): enterprise customization recipes + workflow template variable

Three independent improvements bundled because they share the same
surface (workflow/agent customization) and landed from the same design
discussion:

## Fallback sentence disambiguated (7 SKILL.md files)

The "if the script fails" fallback used to say `{project-root}/_bmad/
custom/{skill-name}.toml` for the team override and then just `{skill-
name}.user.toml` for the user override, leaving the user file's
location implicit. LLMs could reasonably guess skill root or project
root instead. Replaced with an unambiguous numbered list that spells
out the full path for every file in the merge chain.

## Product-brief: stage promotion + brief_template variable

- Promoted `## Stage 1: Understand Intent` from a nested step inside
  "On Activation" to a top-level section. The previous "Step 7: Stage
  1 — Understand Intent → Proceed to Stage 1 below" was mechanical
  numbering pretending to be a step. Activation now ends cleanly at
  Step 6; Stage 1 is a peer section.
- Added `brief_template` as a workflow-level scalar customization
  defaulting to `resources/brief-template.md`. Stage 4 reads
  `{workflow.brief_template}` instead of the hardcoded path, so orgs
  can point at their own template under `{project-root}/...` without
  forking the skill.

## New doc: docs/how-to/extend-bmad-for-your-org.md

Four worked recipes that together cover most enterprise scenarios:

1. Shape an agent across every workflow it dispatches (dev agent +
   Context7 MCP + Linear search — the highest-leverage pattern)
2. Enforce org conventions inside a specific workflow (product-brief
   + compliance-field persistent_facts)
3. Publish completed outputs to external systems (product-brief +
   Confluence + Jira via MCP, gated on user confirmation for Jira)
4. Swap in your own output template (product-brief + brief_template
   variable swap)

Opens with the two-layer mental model (agent spans workflows,
workflow is local) so readers pick the right granularity before
reading any recipe. Closes with a "Combining Recipes" section
showing all four composed. Cross-linked from customize-bmad.md.

## Validation

- Resolver: workflow.brief_template returns the default cleanly.
- validate-file-refs.js: 254 files scanned, 146 refs checked
  (+7 from this commit), 0 broken.

* docs(skills): encourage CLAUDE.md/AGENTS.md reinforcement of critical rules

Added a "Reinforce Global Rules in Your IDE's Session File" section to
extend-bmad-for-your-org.md. BMad customizations only load when a
skill activates, but IDE session files (CLAUDE.md, AGENTS.md, cursor
rules, copilot-instructions) load every turn — worth restating the
most critical rules there too so they survive ad-hoc chat outside a
BMad skill.

Includes a one-line example reinforcing the Recipe 1 Context7 rule,
plus a scope table that clarifies what each layer is for:
  - IDE session file: universal, every session, keep succinct
  - Agent customization: persona-specific, every dispatched workflow
  - Workflow customization: one workflow run

Emphasizes brevity — noise in the session file crowds out signal.

* docs(skills): add Named Agents explanation doc

New docs/explanation/named-agents.md walking through the three-legged
stool (skills + named agents + customization) with the "Hey Mary,
let's brainstorm" activation flow as the narrative thread.

Covers:
- Why named agents vs menu-driven or prompt-driven alternatives
- The 8-step activation flow and what each step contributes
- How customization scales the model beyond a single developer
- Cross-links to the how-to docs for implementation details

Sits alongside brainstorming.md, quick-dev.md, party-mode.md in the
explanation folder — feature narratives for users who want to
understand why BMad is designed the way it is, not just how to use it.

* docs(skills): clarify that keyed-merge requires a single identifier key per array

Review feedback (PR #2284) flagged that the merge-rules wording was
ambiguous: "every item has a `code` or `id` field" could reasonably
be read as "each item individually has at least one of the two",
allowing arrays to mix `code` and `id` across items.

The resolver has always required all items share the *same* identifier
key (all `code`, or all `id`). Mixed arrays fall through to append —
intentional, because mixing identifier keys within one array is a
schema smell and any guess about which key should merge creates a
worse trap than the append-fallback.

Clarified in three places:
- Merge-rules table in customize-bmad.md: "every item shares the
  **same** identifier field"
- `code`/`id` convention paragraph: "pick **one** convention ... and
  stick with it across the whole array"
- Resolver docstring and `_detect_keyed_merge_field` docstring:
  explicit note that mixed arrays fall through with rationale

No behavior change.

* docs(skills): address CodeRabbit review — fallback rules, OS claim, headless greeting

Three fixes from PR #2284 review feedback:

## 1. Fallback merge wording (7 SKILL.md files)

Every SKILL.md told the LLM to merge the three customization files
"in priority order (later wins)" when the resolver fails. That reads
as shallow last-write-wins — but the resolver does structural merge
(scalars override, tables deep-merge, code/id-keyed arrays merge by
key, other arrays append). Following the old wording manually would
have silently stripped base `principles`, `persistent_facts`, and
`menu` items whenever a team override was present.

Expanded the fallback sentence to restate the four structural rules
explicitly, matching the resolver's behavior.

Applied to all 6 agents + bmad-product-brief workflow.

## 2. Python 3.11 / OS shipping claim (customize-bmad.md)

The docs claimed "macOS 13+, Ubuntu 22.04+, Debian 12+, Fedora 37+
all ship 3.11 or newer." Inaccurate — Ubuntu 22.04 defaults `python3`
to 3.10.6 (3.11 is a separate package), and macOS doesn't really
ship Python by default anymore.

Replaced with honest guidance: check `python3 --version` and note
that macOS without Homebrew and Ubuntu 22.04 default to 3.10 or
earlier.

## 3. Autonomous mode greeting gate (bmad-product-brief)

Product-brief's activation-mode detection documents autonomous mode
as "produce complete brief without interaction" — but Step 5 greeted
unconditionally, adding conversational output before the headless
artifact. Gated the greeting on `{mode}` != `autonomous`.

## Dismissed (replied on thread)

- `.gitignore` migration from *.user.yaml to *.user.toml: YAML
  installer code was in reverted #2282, never released. No users
  affected. Same rationale as Augment's earlier thread.

Validated: 254 files, 146 refs, 0 broken. test:refs 7/7,
test:install 242/242.

* docs: rename Extend to Expand throughout customization docs
2026-04-19 19:30:29 -05:00
Brian e550df2474
Revert "feat(skills): YAML-based agent customization with Python resolver (#2282)" (#2283)
This reverts commit bd1c0053d5.
2026-04-19 11:09:21 -05:00
Brian bd1c0053d5
feat(skills): YAML-based agent customization with Python resolver (#2282)
Three-layer customization (skill defaults → team → user) for BMad agents    
  and any skill that opts in. Users edit `_bmad/custom/{skill-name}.yaml`
  (team, committed) or `{skill-name}.user.yaml` (personal, gitignored);       
  customizations survive updates.                                             
                                                                              
  Resolver is a Python script using PEP 723 inline metadata, invoked via      
  `uv run` so deps auto-install into a cached isolated env on first call.     
  This aligns with Anthropic's Agent Skills spec and BMB conventions, and     
  keeps the dependency declared (scannable by pip-audit/Dependabot) rather    
  than vendored.                                                              
                                                                              
  ## Design choices                                                           
                                                                              
  - **Agent identity is hardcoded** in SKILL.md (name, title, Overview prose) 
    so skills can be invoked reliably by role *or* default name. Brand
    recognition is preserved; customization shapes behavior, not identity.    
  - **Luminary-anchored personas** (e.g. "Channels Martin Fowler's            
    pragmatism and Werner Vogels's cloud-scale realism") deliver ~55%
    token savings per agent while preserving distinctive voice beats.         
  - **Universal per-field merge rules** with v6.1-compatible agent            
    semantics: metadata shallow-merge, persona replace, critical_actions      
    and memories append, menu merge-by-code, all else deep-merge.             
  - **Workflow customization** shares the same surface — `bmad-product-brief`
    pilots `activation_steps_prepend`, `activation_steps_append`, and         
    `skill_end` hooks that any workflow-style skill can adopt.                
                                                                              
  ## Infrastructure                                                           
                                                                              
  - `_bmad/scripts/` houses shared Python scripts (resolver + future).        
  - `_bmad/custom/` is provisioned empty with a seeded `.gitignore` for
    `*.user.yaml` on fresh installs.                                          
  - Installer filters ensure `scripts/`, `custom/`, and sidecar-generated   
    `memory/` directories are never treated as modules.                       
  - Dead v6.1 code cleaned up: `_config/agents/` no longer created,         
    `metadata.capabilities` removed from schema and CSV manifest.
2026-04-18 23:13:31 -05:00
Alex Verkhovsky d09363b1b2
feat(installer): use GitHub API as primary fetch with raw CDN fallback (#2248)
* feat(installer): use GitHub API as primary fetch with raw CDN fallback

Corporate proxies commonly block raw.githubusercontent.com while allowing
api.github.com. Add fetchGitHubFile() to RegistryClient that tries the
GitHub Contents API first, falling back to the raw CDN transparently.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(installer): cap redirect depth and preserve dual-fallback errors

Add maxRedirects parameter to fetch() and _fetchWithHeaders() to prevent
unbounded redirect recursion. Wrap CDN fallback in try/catch and throw
AggregateError with both API and CDN errors for better diagnostics.
Extract marketplace repo coordinates into named constants in
external-manager.

* chore(installer): drop unused fetchJson and fetchGitHubJson

Neither method has any callers. Also drop the corresponding test.

* refactor(test): fold registry tests into test-installation-components

No reason for RegistryClient tests to be a separate runner — the same
file already tests the registry consumers in Suite 33. Drop test:registry
from package.json scripts and quality gate.

* fix(installer): include URL, API message, and rate-limit info in HTTP errors

Non-2xx responses previously yielded bare `HTTP 403`. Now surface the
request URL, GitHub's JSON error message (or body snippet), X-RateLimit-Reset
when quota is exhausted, and Retry-After. Turns a mystery 403 into
'rate limit exhausted; resets at 2026-04-15T18:00:00Z' — the difference
between 'try GITHUB_TOKEN' and a wild goose chase.

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-18 08:53:23 -07:00
Brian 6b964acd56
Merge pull request #2254 from lrliang/docs/zh-cn-missing-translations
docs(zh-cn): add missing Chinese translations
2026-04-13 18:13:06 -05:00
Brian 723bca4e38
Merge branch 'main' into docs/zh-cn-missing-translations 2026-04-13 18:12:56 -05:00
Brian 262fa882ef
Merge pull request #2257 from bmad-code-org/issue-fixes
fix(installer): add missing fs-native exports
2026-04-13 18:06:56 -05:00
Brian Madison 0f958cf713 fix(installer): add missing sync and async methods to fs-native wrapper
Closes #2256
2026-04-13 09:59:41 -05:00
Brian b336cd0987
Merge pull request #2255 from bmad-code-org/fix-skill-scanner-recursion
fix(installer): stop skill scanner from recursing into discovered skills
2026-04-13 01:13:06 -05:00
Brian Madison 9ffb5b80ab fix(installer): stop skill scanner from recursing into discovered skills
Skills don't nest. Once the manifest generator finds a valid SKILL.md
in a directory, it should not recurse into that skill's subdirectories
looking for more skills. Template files (like bmb's setup-skill-template)
inside a skill's assets/ would be incorrectly scanned and produce
spurious errors.
2026-04-13 01:11:28 -05:00
梁山河 8ee35aaea3
Merge branch 'main' into docs/zh-cn-missing-translations 2026-04-13 13:55:50 +08:00
Brian 5456b26ab7
Merge pull request #2253 from bmad-code-org/fix-fs-extra-graceful-fs
fix(installer): replace fs-extra with native node:fs to prevent file loss
2026-04-13 00:55:09 -05:00
Brian Madison c6c8301ea1 fix(installer): add move() and overwrite support to fs-native
Add missing move() with cross-device fallback (rename → copy+rm on
EXDEV), needed by OfficialModules.createModuleDirectories for directory
migrations during upgrades.

Honor overwrite/errorOnExist options in copy() to match fs-extra
behavior for callers that pass these flags.
2026-04-13 00:52:41 -05:00
Brian Madison a6d075bd0b fix(installer): replace fs-extra with native node:fs to prevent file loss
fs-extra routes all operations through graceful-fs, which globally
monkey-patches node:fs with a deferred retry queue. During multi-module
installs (~500+ file ops), retried unlink operations from one module's
remove phase can fire after the next module's copy phase has written
files, silently deleting them non-deterministically.

Replace fs-extra with a thin fs-native.js wrapper over node:fs/promises
and node:fs. All 21 consumers now use native APIs with no global
monkey-patching, eliminating the retry-queue race condition entirely.

Closes #1779
2026-04-13 00:44:28 -05:00
Brian 82632a4872
Merge pull request #1927 from sunilp/fix/prd-scoping-permission-model
fix(prd): require user confirmation before de-scoping requirements or inventing phases
2026-04-13 00:21:58 -05:00
Brian 5f848c27c8
Merge branch 'main' into fix/prd-scoping-permission-model 2026-04-13 00:21:44 -05:00
Brian d401afd3f3
Merge pull request #2252 from bmad-code-org/fix-workflow-diagram-bob
docs: remove Bob from workflow map diagrams
2026-04-12 23:13:57 -05:00
Brian b4d6a92e65
Merge branch 'main' into fix-workflow-diagram-bob 2026-04-12 23:13:47 -05:00
Brian Madison 246270bef2 docs: remove Bob from workflow map diagrams
Bob (Scrum Master) was consolidated into Amelia (Developer) in v6.3.0
(#2186) but still appeared in the workflow map diagrams for
sprint-planning, create-story, and retrospective. Updated both English
and French versions to show Amelia and removed the unused Bob CSS class.

Closes #2249
2026-04-12 23:12:32 -05:00
Brian 79a6876a65
Merge pull request #2251 from bmad-code-org/fix-installer-builtin-modules
fix(installer): source built-in modules locally instead of from registry
2026-04-12 23:01:42 -05:00
Brian Madison 83f374c254 fix(installer): source built-in modules locally instead of from registry
Core and BMM modules live in this repo (src/core-skills, src/bmm-skills)
but the installer UI sourced them from the remote registry. When the
registry was unreachable (VPN, proxy, firewall), the fallback YAML only
had the 4 external modules, so core and bmm disappeared from the install
list entirely.

Now _selectOfficialModules and getDefaultModules always read built-in
modules from the local source via OfficialModules.listAvailable(), then
append external modules from the registry. Network failures only affect
external modules.

Closes #2239
2026-04-12 22:41:40 -05:00
leon 10c194c2a6 docs(zh-cn): add missing Chinese translations for 3 documents
Translate the remaining untranslated English docs to Chinese:
- explanation/analysis-phase.md
- explanation/checkpoint-preview.md
- how-to/install-custom-modules.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-13 10:35:23 +08:00
Alex Verkhovsky ea99b7ece5
chore(installer): remove 1,683 lines of dead code (#2247)
* chore(installer): remove dead code across installer modules

Delete 3 entirely dead files (agent-command-generator, bmad-artifacts,
module-injections) and remove ~50 unused exports from manifest.js,
cli-utils.js, prompts.js, path-utils.js, official-modules.js,
external-manager.js, custom-module-manager.js, and registry-client.js.
Removes corresponding dead tests.

* fix(installer): restore currentProjectDir writes for placeholder expansion

The previous commit removed the three assignments to
OfficialModules.currentProjectDir as dead code, but buildQuestion()
still reads the property to resolve {directory_name} placeholders in
module config defaults during interactive collection. Without the
writes, any module default containing {directory_name} would surface
the literal placeholder to users.
2026-04-10 20:24:50 -07:00
Alex Verkhovsky eabcd03f65
chore(installer): remove dead template and agent-command pipeline (#2244)
The legacy agent-command-generator, bmad-artifacts helpers, and all 26
IDE template files (combined/ and split/) are unreachable dead code.
The installer now uses verbatim SKILL.md directory copying -- no template
rendering occurs. The files own TODO comments confirm retirement.
2026-04-10 10:06:57 -07:00
Alex Verkhovsky 17da5ca8ca
feat(quick-dev): sync sprint-status.yaml on epic-story implementation (#2234)
* feat(quick-dev): sync sprint-status.yaml on epic-story implementation

When quick-dev infers the intent is an epic story, resolve the full
sprint-status key during step-01's previous-story-continuity sub-step,
then sync sprint-status.yaml at the two workflow boundaries code-review
already owns the trailing half of:

- step-03 start: flip the story to in-progress and lift the parent
  epic out of backlog if needed.
- step-05 end: flip the story to review. Code-review keeps ownership
  of review -> done.

Resolution uses exact numeric-segment equality on the {epic}-{story}
prefix (never string-prefix match), so 1-1 no longer collides with
1-10. Both sync blocks are idempotent so step-04 loopbacks do not
clobber human edits or bump last_updated without cause. Skips silently
when sprint-status.yaml is missing or the intent is not an epic story.

* feat(quick-dev): add sprint-status sync to one-shot route

Epic stories do get implemented via one-shot in practice. Add the same
in-progress / review sync pair that step-03 and step-05 already have,
with identical idempotency guards and skip-on-missing behavior.

* refactor(quick-dev): extract sprint-status sync into shared file

Replace inline sync blocks in step-03, step-05, and step-oneshot with
one-line callouts to sync-sprint-status.md. The shared file owns all
edge-case handling (idempotency, epic lift, missing file/key) and is
parameterized by {target_status}. Any future route picks it up with a
single Follow line.

* fix(quick-dev): resolve story_key on early-exit resume paths

Extract story-key resolution into a shared subsection referenced by
all early-exit paths and INSTRUCTIONS, ensuring sprint-status sync
works for resumed epic stories.

* refactor(quick-dev): tighten story-key resolution prompt

Remove mechanical details the LLM can infer; keep only the
collision-prevention constraint.
2026-04-10 10:03:53 -07:00
JakubStejskalCZ a0705af9be
docs(cs): groom analysis-phase.md translation (#2242)
* docs(cs): groom analysis-phase.md translation

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs(cs): fix AI term and ideation phrasing in analysis-phase.md

Replace "UI" with "AI" (DeepL mistranslation of the AI acronym as
user interface) and rephrase "techniky idealizace" to "techniky
generování nápadů" so the meaning matches the English source.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-10 06:23:00 -07:00
Alex Verkhovsky f5030c7084
feat(review): enforce model parity for all review subagents (#2236)
Prevent review subagents from being downgraded to cheaper models.
Rare findings from the Acceptance Auditor tend to be high-severity,
and research shows smaller models have worse recall on rare-event
detection.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-10 05:53:54 -07:00
Alex Verkhovsky daa7137623
fix(docs): normalize Czech typographic quotes in analysis-phase.md (#2241)
Close pairs with U+201C instead of straight U+0022.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 23:12:35 -07:00
Alex Verkhovsky 14fc7b2517
docs(cs): add missing analysis-phase.md translation (#2240)
The PRFAQ link added in #2238 points to ../explanation/analysis-phase.md
which exists in en, vi-vn, and fr but was missing from the Czech
translation, breaking both CI doc checks.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 23:07:48 -07:00
Alex Verkhovsky edfb405e27
fix(docs): update stale Analyst triggers and add PRFAQ link (#2238)
Analyst (Mary) triggers were listed as BP, RS, CB, WB, DP but the
actual agent source defines BP, MR, DR, TR, CB, WB, DP. Update all
locale agents.md files. Also add PRFAQ Working Backwards hyperlink
to commands.md in en, cs, and vi-vn.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 22:18:08 -07:00
Alex Verkhovsky 202c842826
fix(code-review): remove dead Batch-apply option from patch menu (#2225)
The Batch-apply option (added in 9c3e2804) was instructed to "skip
any finding that requires judgment" — but step-03-triage already
guarantees patch findings are unambiguous (the decision-needed
bucket exists precisely to absorb ambiguous ones). The option had
no distinct work to do that option 1 did not already cover, and
its label suggested a meaningful difference that did not exist.

- Delete option 0 and the >3 findings conditional
- Rename "Fix them automatically" -> "Apply every patch", with
  explicit scope (patches only; defer/decision-needed untouched)
- Rename "Walk through each" -> "Walk through each patch" for the
  same scope clarity
- Unify <Z> placeholder with the existing <P> patch count
- Strip stale (or "0" for batch) notes from HALT lines
2026-04-09 21:02:07 -07:00
Emmanuel Atsé 128b252c32
docs(fr): sync translations with upstream and fix sidebar ordering (#2231)
* docs(fr): fix noun gender typo

* docs(fr): translation of new bmad-prfaq skill

Translation of commit abfc56b

* docs(fr): remove agents.md superfluous frontmatter description details

* docs(fr): restore Amelia as dev agent

Reference commit 1aa0903

* docs(fr): translate checkpoint preview explanation

Reference commit 7ef45d4

* docs(fr): harmonize removal of QA agent

Reference commit 48c2324

* docs(fr): harmonize removal of SM Agent

Reference commit 003c979

* docs(fr): translate get-answers-about-bmad rewrite

Reference commit aa48f83

* docs(fr): restore agent invocation in getting started

Matching English reference

* docs(fr): fix sidebar order numbering

* docs(fr): fix typo
2026-04-09 20:58:43 -07:00
miendinh b018c7ad7c
docs(vi-vn): sync translations and add missing checkpoint-preview page (#2222)
Co-authored-by: miendinh <miendinh@users.noreply.github.com>
2026-04-09 20:49:18 -07:00
github-actions[bot] 7f7690dbfd chore(release): v6.3.0 [skip ci] 2026-04-10 01:00:56 +00:00
Brian a92f5d626b
Merge pull request #2235 from bmad-code-org/changelog
docs: v6.3.0 changelog
2026-04-09 20:00:04 -05:00
Brian Madison 1d5a3caec5 docs: draft v6.3.0 changelog 2026-04-09 19:59:18 -05:00
Brian 97d32405d0
feat(installer): universal source support for custom module installs (#2233)
* feat(installer): add plugin resolution strategies for custom URL installs

When installing from a custom GitHub URL, the installer now analyzes
marketplace.json plugin structures to determine how to locate module
registration files (module.yaml, module-help.csv). Five strategies
are tried in cascade:

1. Root module files at the common parent of listed skills
2. A -setup skill with registration files in its assets/
3. Single standalone skill with registration files in assets/
4. Multiple standalone skills, each with their own registration files
5. Fallback: synthesize registration from marketplace.json metadata
   and SKILL.md frontmatter

Also changes the custom URL flow from confirm-all to multiselect,
letting users pick which plugins to install. Already-installed modules
are pre-checked for update; new modules are unchecked for opt-in.

New file: tools/installer/modules/plugin-resolver.js
Modified: custom-module-manager.js, official-modules.js, ui.js

* fix(installer): address PR review findings for plugin resolver

- Guard against path traversal in plugin-resolver.js: skill paths from
  unverified marketplace.json are now constrained to the repo root using
  path.resolve() + startsWith check
- Skip npm install during browsing phase: cloneRepo() accepts
  skipInstall option, used in ui.js before user confirms selection,
  preventing arbitrary lifecycle script execution from untrusted repos
- Add createModuleDirectories() call to installFromResolution() so
  modules with declarative directory config are fully set up
- Fix ESLint: use replaceAll instead of replace with global regex

* fix(installer): pass version and repoUrl to manifest for custom plugins

installFromResolution was passing empty strings for version and repoUrl,
which the manifest stores as null. Now threads the repo URL from ui.js
through resolvePlugin into each ResolvedModule, and passes the plugin
version and URL to the manifest correctly.

* fix(installer): manifest-generator overwrites custom module version/repoUrl

ManifestGenerator rebuilds the entire manifest via getModuleVersionInfo
for every module. For custom modules, this returned null for version and
repoUrl because it only checked _readMarketplaceVersion (which searches
for marketplace.json on disk) and hardcoded repoUrl to null. Now checks
the resolution cache first to get the correct version and repo URL.

* fix(installer): resolve custom modules from disk cache on quick update

When the resolution cache is empty (fresh CLI process, e.g. quick
update), findModuleSourceByCode only matched plugin.name against the
module code. This failed for modules like "sam" and "dw" where the
code comes from module.yaml inside a setup/standalone skill, not from
the plugin name in marketplace.json.

Now runs the PluginResolver on cached repos when the direct name match
fails, finding the correct module source and re-populating the cache
for the install pipeline.

* feat(installer): universal source support for custom modules

Replace GitHub-only custom module installation with support for any Git
host (GitHub, GitLab, Bitbucket, self-hosted) and local file paths.

- Add parseSource() universal input parser (local paths, SSH, HTTPS with
  deep path/subdir extraction for GitHub, GitLab, Gitea)
- Add resolveSource() coordinator: parse -> clone if URL -> detect
  discovery vs direct mode (marketplace.json present or not)
- Clone-first approach eliminates host-specific raw URL fetching
- 3-level cache structure (host/owner/repo) with .bmad-source.json
  metadata for URL reconstruction
- Local paths install directly without caching; localPath persisted in
  manifest for quick-update source lookup
- Direct mode scans target directory for SKILL.md when no marketplace.json
- Fix version display bug where walk-up found parent repo marketplace.json
  and reported wrong version for custom modules

* fix(installer): harden readMarketplaceJsonFromDisk and hoist require

- Add try/catch to readMarketplaceJsonFromDisk so malformed JSON returns
  null instead of throwing an unhandled parse error
- Hoist CustomModuleManager require outside the per-module loop in
  _installOfficialModules

* fix(installer): restore validateGitHubUrl strictness and fix prettier

- Restore original GitHub-only regex in deprecated validateGitHubUrl
  wrapper so existing tests pass (rejects non-GitHub URLs, trailing
  slashes)
- Run prettier to fix formatting in custom-module-manager.js

* feat(installer): add --custom-source CLI flag for non-interactive installs

Allows installing custom modules from Git URLs or local paths directly
from the command line without interactive prompts:

  npx bmad-method install --custom-source /path/to/module
  npx bmad-method install --custom-source https://gitlab.com/org/repo
  npx bmad-method install --custom-source /path/one,https://host/org/repo

Works alongside --modules and --yes flags. All discovered modules from
each source are auto-selected.

* docs: add custom and community module installation guide

New how-to page covering community module browsing, custom sources (any
Git host, local paths), discovery vs direct mode, local development
workflow, and the --custom-source CLI flag. Clarifies that
.claude-plugin/ is a cross-tool convention, not Claude-specific.

Also updates non-interactive installation docs with the new flag and
examples, bumps sidebar ordering, and fixes --custom-source to install
only core + custom modules when --modules is not specified.
2026-04-09 18:44:40 -05:00
Alex Verkhovsky 3ba51e1bac
feat(quick-dev): add epic context compilation to step-01 (#2218)
* feat(quick-dev): add epic context compilation to step-01

Fork step-01 context loading: epic stories get a sub-agent that
compiles planning docs into a cached epic-{N}-context.md, while
freeform intents keep the lightweight directory-listing path.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(quick-dev): tighten epic context loading per PR review

- Validate cached epic-<N>-context.md is non-empty and starts with the
  expected header before loading; treat invalid cache as missing.
- Replace inline {N} placeholders with <N> so the skill validator does
  not flag them as unresolved workflow variables.
- Replace ambiguous "fall back to path B" with an explicit instruction
  to scan/load planning artifacts using path B's procedure, with a note
  not to re-evaluate path B's gating clause.

Addresses CodeRabbit and Augment review comments on PR #2218.

* refactor(quick-dev): tighten compile-epic-context prompt

- Restructure with Task/Steps opening and Exact Output Format section.
- Switch Stories template to bullet form for clarity.
- Add "no hallucination" and explicit "omit empty sections except Goal
  and Stories" rules.
- Use <N> instead of {N} in the filename for consistency with step-01.

* refactor(quick-dev): restructure epic-story context loading

Reshape path A of step-01 into five explicit numbered steps and add an
inline-compilation fallback for runtimes that cannot spawn sub-agents
(Copilot, Codex, local Ollama, older Claude).

- Pull cache validity, compilation, verification, and continuity into
  separate numbered steps instead of nested paragraphs.
- Define "valid cached context" upfront: non-empty and starts with
  `# Epic <N> Context:`.
- Add inline-compilation fallback: runtimes without sub-agent support
  read compile-epic-context.md and follow it directly.
- Make previous-story continuity run regardless of which context source
  succeeded (cache hit, fresh compilation, or path-B raw fallback).

* fix(quick-dev): address review findings on epic context compilation

- Add freshness check to cached epic-N-context.md (invalidate when any
  planning artifact is newer)
- Remove the silent fall-back-to-raw-planning-docs path on compile
  failure; HALT and report instead
- Add explicit "ambiguous → freeform" tiebreakers for both the path A
  header and the epic-number identification step
- Drop "verbatim" from compile-epic-context.md format header to resolve
  the verbatim-vs-omit-empty contradiction

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 18:29:17 -07:00
Brian 59b07c33e2
feat(bmad-help): llms.txt support for general questions (#2230)
* feat(bmad-help): add _meta rows and llms.txt support for general questions

Register llms.txt URLs in module-help.csv via _meta rows so bmad-help
can fetch module documentation when users ask questions that don't map
to a specific skill.

* refactor(bmad-help): streamline llms.txt docs into existing skill sections
2026-04-08 09:53:27 -05:00
Alex Verkhovsky f9925eb180
feat(quick-dev): improve checkpoint 1 UX (#2217)
* feat(quick-dev): improve checkpoint 1 UX with clickable link, external editing note, and change detection

Display spec file path as clickable CWD-relative link alongside the
summary. Inform users they can open the spec in another session with
any tool before approving. On approval, re-read the spec from disk
and acknowledge any external edits before proceeding.

* fix(quick-dev): tighten checkpoint 1 [A] flow wording

- Remove stray 'and options' from the editing-note intro so the note's
  position relative to the [A]/[E] menu is unambiguous.
- Restructure the [A] bullet into explicit missing/exists branches so
  the missing-file HALT cannot fall through to status updates and
  recreate a deleted spec.

Addresses augmentcode review comments on PR #2217.

* docs(quick-dev): rewrite checkpoint 1 editing-note

- Drop boilerplate opener about the spec being a regular file.
- Enumerate concrete options: editor, in-session Q&A, or bmad-advanced-elicitation / bmad-party-mode / bmad-code-review skills.
- Flag that skills should ideally run in another session to avoid context bloat.
- Change "add this note" to "display this note" for precision.
2026-04-08 07:27:06 -07:00
Brian b744408783
feat(installer): community module browser and custom URL support (#2229)
* feat(installer): add community module browser and custom URL support

Three-tier module selection: official, community (category drill-down
with featured/search), and custom GitHub URL.

- Add RegistryClient shared fetch utility
- Add CommunityModuleManager with SHA-pinned cloning (refuses install
  if approved SHA cannot be reached; uses HEAD when no SHA set)
- Add CustomModuleManager for arbitrary GitHub repo installation
- Extend findModuleSource chain with community and custom fallthrough
- Extend manifest to detect community and custom source types
- Add Config.customModulesMeta for custom module metadata

* fix: resolve review findings for community/custom module support

- Remove redundant CommunityModuleManager instantiation in UI display
- Remove dead customModulesMeta field from Config (never populated)
- Add 35 unit tests for CustomModuleManager and CommunityModuleManager
  pure functions: URL validation, normalization, search, featured, categories

* fix: preserve installed community/custom modules in modify flow

When a user does "Modify Installation" and declines to browse community
modules, previously installed community/custom modules are now auto-kept.
If the user does browse, their selections are trusted (they can deselect).

Also fix stale docs: class doc for SHA pinning, JSDoc return type.

* fix: include community and custom modules in quick update

Quick update now checks community registry and custom cache so installed
community/custom modules are updated instead of skipped.

* fix: use defaults for new config fields during quick update

When quick update encounters new config fields (e.g., from a newly
supported community module), use schema defaults silently instead of
prompting the user. Quick update should be non-interactive.

* test: add unit tests for SHA pinning, category filtering, and URL edge cases

Cover SHA normalization (set vs null/trusted), listByCategory,
getModuleByCode, and URL validation edge cases (HTTP, trailing slash,
SSH without .git). Total: 243 tests.
2026-04-08 00:50:04 -05:00
Brian 5e038a8ce4
feat(installer): remote registry + remove custom content (#2228)
* refactor(installer): remove custom content installation feature

Remove the entire local filesystem custom content feature from the
installer to make way for marketplace-based plugin installation.

Deleted: custom-handler.js, custom-module-cache.js, custom-modules.js
Removed: --custom-content CLI flag, interactive custom content prompts,
custom module caching, manifest tracking, missing-source resolution,
and related test suites. Updated docs across all translations.

* fix: address review findings from Augment

Fix admonition syntax (remove accidental space in :::note) across 4
translated docs files, and update stale JSDoc on listAvailable().

* feat(installer): fetch module list from marketplace registry

Switch module list source of truth from bundled
external-official-modules.yaml to the remote marketplace registry
(registry/official.yaml) fetched via raw.githubusercontent.com.

- Rewrite ExternalModuleManager to fetch from GitHub with local fallback
- Simplify selectAllModules/getDefaultModules to use registry as single source
- Registry order controls display order; built_in flag prevents cloning
- Rename fallback file to registry-fallback.yaml in modules/
- Only show legacy migration message when legacy dirs actually exist
2026-04-07 22:45:01 -05:00
Brian 5dbfb588ee
refactor(installer): remove custom content installation feature (#2227)
* refactor(installer): remove custom content installation feature

Remove the entire local filesystem custom content feature from the
installer to make way for marketplace-based plugin installation.

Deleted: custom-handler.js, custom-module-cache.js, custom-modules.js
Removed: --custom-content CLI flag, interactive custom content prompts,
custom module caching, manifest tracking, missing-source resolution,
and related test suites. Updated docs across all translations.

* fix: address review findings from Augment

Fix admonition syntax (remove accidental space in :::note) across 4
translated docs files, and update stale JSDoc on listAvailable().
2026-04-07 21:41:03 -05:00
Alex Verkhovsky 9ca0316674
refactor(quick-dev): eliminate spec-wip.md singleton (#2214)
* refactor(quick-dev): eliminate spec-wip.md singleton

Write directly to spec-{slug}.md with status: draft instead of using
a shared spec-wip.md file. Use draft status for resume detection in
step-01. Removes wipFile variable from all step frontmatter and
workflow initialization.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(quick-dev): address PR review findings

- step-02: preserve Intent block on draft resume instead of regenerating from template (F1)
- step-01: resume existing draft on slug collision rather than creating -2 duplicate (F3)
- step-01: recognize `done` status and ingest as context instead of silently re-implementing (F4)
- step-oneshot: remove unused spec_file frontmatter declaration (F6)

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 10:14:24 -07:00
Alex Verkhovsky 6cecab2626
chore(install): stop copying skill prompts to _bmad by default (#2182)
* chore(install): stop copying skill prompts to _bmad by default

Flip install_to_bmad default from true to false so skill directories
are cleaned from _bmad/ after IDE install. Skills are self-contained
in their IDE directories (.claude/skills/, etc.) and no longer need
duplicate copies in _bmad/.

Two skills (bmad-create-prd, bmad-validate-prd) opt back in via
explicit manifests because bmad-edit-prd cross-references their data
files. Also fixes broken bmm-skills/ path references and corrects
the file-ref validator module-to-source mapping.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(install): make edit-prd self-contained and remove install_to_bmad

Give bmad-edit-prd its own copy of prd-purpose.md and replace the
cross-skill validation workflow reference with a skill invocation, so
all three PRD skills are fully self-contained. With no remaining
consumers, remove the install_to_bmad flag from manifests, CSV output,
the post-install cleanup loop, and the dedicated test file.

* feat(install): clean up skill directories from _bmad after IDE install

Skills are self-contained in IDE directories, so _bmad/ only needs
module-level files (config.yaml, _config/). After all IDE setups
complete, remove skill directories from _bmad/ via skill-manifest.csv.
Also cleans up skill dirs left by older installer versions.

* test(install): drop stale install_to_bmad column from suite 27 CSV row

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 10:02:59 -07:00
Brian c46502f640
feat(installer): overhaul branding, versioning, and skill cleanup (#2223)
* feat(installer): overhaul branding, versioning, and skill cleanup

Logo and branding:
- Responsive logo: full "BMAD METHOD" at >=95 cols, "BMAD" for narrower terminals
- Color scheme updated from yellow to blue (matching bmadcode.com brand)
- Added copyright notice and tagline in white for contrast
- Removed version number from logo (individual module versions shown in summary)
- Added ™ to both wide and narrow logo variants

Installer start message:
- Replaced outdated V6 launch announcement with clean welcome
- Consolidated redundant module/platform messaging into single intro
- Tightened open source manifesto (same spirit, fewer words)
- Merged speaking/media into support section with contact email
- Added full social links: Website, Discord, YouTube, X, Facebook
- Replaced docs.bmad-method.org and changelog links with bmadcode.com hub

Install summary improvements:
- Module names now show full display names from module.yaml (not abbreviations)
- All module versions sourced from .claude-plugin/marketplace.json exclusively
- Summary shows version transitions: "v6.2.2 -> v6.3.0", "v6.3.0, no change",
  or "v6.3.0, installed" for fresh installs
- Switched summary from clack note() to box() for full-brightness text
- Removed dim/gray styling that was hard to read on dark terminals
- Links styled with color.blue instead of color.dim
- Get started section leads with actionable steps (launch agent, run bmad-help)
- Removed redundant social links (already shown in start message)

Version source unification:
- All module versions now come from .claude-plugin/marketplace.json only
- Removed package.json as version source for core/bmm modules
- Updated manifest.js getModuleVersionInfo() to use marketplace.json
- Updated installer.js _getMarketplaceVersion() helper
- Updated ui.js getMarketplaceVersion() for module selection display
- Quick Update menu no longer shows misleading version (was using package.json)
- Module selection list now shows versions next to each module name

Skill cleanup overhaul:
- Replaced blunt-force bmad-* prefix deletion with surgical removal system
- Added removals.txt support: optional per-project file listing skills to remove
- Created initial removals.txt with all skills removed since v6.2.0
- Install/update: captures previously installed skill IDs from skill-manifest.csv
  before manifest regeneration, then removes those + removals.txt entries
- Uninstall: removes all installed skills via skill-manifest.csv + removals.txt
- Deselecting modules now correctly removes their skills from IDE directories
- User-created bmad-* skills in IDE directories are no longer destroyed
- Legacy directory cleanup retains prefix matching (those dirs are abandoned)

Bug fixes:
- Fixed duplicate "CORE module already up to date" during quick update
- Fixed version display showing package.json version instead of actual module version
- Updated test fixture for bmad-os-* preservation test to use skill-manifest.csv

* fix(installer): address Augment review findings

- Fix plugins[0] fragility: extract highest version across all plugins
  in marketplace.json instead of assuming first entry (ui.js, installer.js,
  manifest.js)
- Fix _readMarketplaceVersion ignoring moduleSourcePath: custom modules
  can now source their own marketplace.json by walking up from source path
- Hard-exclude bmad-os-* utility skills in both surgical and legacy cleanup
  modes, preventing accidental deletion if tracked in manifests
- Distinguish missing file vs parse error in skill-manifest.csv reading:
  warn on corrupt CSV instead of silently skipping cleanup

* fix(installer): resolve module source before reading marketplace version

Move _readMarketplaceVersion call after source type resolution so custom
modules use their own source path instead of falling back to the external
module cache, which could match a different module with the same code.
2026-04-07 02:31:36 -05:00
Brian 47991536c5
docs: add Python 3.10+ and uv as prerequisites (#2221) 2026-04-06 00:30:00 -05:00
Alex Verkhovsky 595746335c
fix(docs): wrap bare email in angle brackets for markdownlint MD034 (#2219) 2026-04-05 13:14:03 -07:00
Brian 28aa522753
Update community and support links in README (#2215) 2026-04-05 00:52:39 -05:00
Alex Verkhovsky aefabc74b0
feat(quick-dev): add previous story continuity to context loading (#2201)
When quick-dev infers the intent is an epic story, it now scans for
completed specs from the same epic and loads the most recent one to
extract Code Map, Design Notes, Spec Change Log, and task list as
continuity context for planning.
2026-04-04 20:49:55 -07:00
Alex Verkhovsky aa48f83a65
docs: rewrite get-answers-about-bmad for flow and accuracy (#2213)
Restructure from two glued-together documents into a single
escalation flow (bmad-help → source → community). Remove
references to deprecated _bmad folder and closed Discord channels.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-04 20:44:43 -07:00
JakubStejskalCZ ac18b195e9
docs(cs): add Czech (Čeština) documentation translation (#2134)
* docs(cs): add Czech (Čeština) documentation translation

Add complete Czech translation of all 29 documentation files mirroring
the English source structure. Register cs-CZ locale in Starlight config
with sidebar label translations.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(cs): repair corrupted characters and table formatting in Czech docs

Fix UTF-8 encoding artifacts in customize-bmad.md and upgrade-to-v6.md,
align markdown table formatting, and correct Czech grammar in
project-context.md heading.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(cs): address CodeRabbit review feedback

- Normalize 64 Czech quotation marks to proper „…" pairs across 14 files
- Fix corrupted UTF-8 box-drawing character in upgrade-to-v6.md
- Use relative roadmap link (./roadmap) in index.md for locale consistency
- Fix typo: Podníková → Podniková in modules.md

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(cs): sync Czech translation with upstream agent consolidation and PRFAQ addition

Agents: remove Barry/Quinn/Bob (merged into Developer), add WB trigger and PRFAQ to Analyst.
Tutorials/commands/workflow-map: fix SM→DEV references, add PRFAQ workflow entries.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-04-04 20:42:54 -07:00
Alex Verkhovsky 1050415351
refactor(code-review): harmonize step-01 intent cascade (#2206)
* refactor(code-review): harmonize step-01 intent cascade with quick-dev and checkpoint-preview

Replace keyword-matching entry point with 5-tier priority cascade:
explicit argument → recent conversation → sprint tracking → git state → ask.
Diff-mode keyword detection preserved as sub-check within tier 1.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(code-review): address review findings in step-01 intent cascade

- Set {spec_file} immediately in Tier 1 when spec provided
- Add staged/uncommitted handlers to instruction 3 dispatch table
- Replace undefined {branch}/{sha} placeholders with angle brackets
- Fix {story_key} vs {{story-id}} placeholder mismatch
- Correct "wants reviewed" grammar to "wants to be reviewed"

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-04 20:07:15 -07:00
Brian 783601b576
fix: move BMB announcement to custom Banner component (#2210)
Starlight banner config doesn't render with custom Header. Added
announcement row to Banner.astro and removed unused config.
2026-04-04 16:10:37 -05:00
Brian 975aea6e74
docs: add BMad Builder announcement banner to docs site (#2209) 2026-04-04 16:02:26 -05:00
Alex Verkhovsky f98083ba75
docs: add contribution guardrails for unsolicited PRs (#2207)
Add Discord-first callout banner and AI-generated code curation policy.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-04 12:13:06 -05:00
Brian 3a24d8ffc9
docs: add BMad Ecosystem cross-links to sidebar (#2204) 2026-04-04 00:34:00 -05:00
Brian 15f49b8bd4
docs: add BMad Ecosystem cross-links to sidebar (#2203) 2026-04-04 00:27:47 -05:00
Alex Verkhovsky d51e2159e5
fix(quick-dev): specify {project-root}/ anchor for context: list paths (#2200)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-03 11:42:31 -07:00
Alex Verkhovsky e9a6bfa95c
feat(quick-dev): add planning artifact awareness for context-informed specs (#2185)
Teach quick-dev step-01 what BMAD phase 1-3 planning artifacts are (PRD,
architecture, UX, epics, product brief) so it can selectively load relevant
docs instead of guessing from code alone. Remove hard cap of 3 on spec
context field, replacing with judgment guidance. Instruct step-03 to
explicitly pass context files to the implementation sub-agent.
2026-04-03 09:24:48 -07:00
Alex Verkhovsky 0edcd0571f
fix(docs): correct translation fidelity issues in Vietnamese docs (#2192)
Sync Vietnamese translations with current English source:
- Update agent table to consolidated Developer agent architecture
- Fix bmad-dev -> bmad-agent-dev skill ID references
- Replace Quinn/QA agent framing with built-in QA workflow
- Fix SM agent -> Developer agent in getting-started
- Fix broken platform-codes.yaml URL
- Add missing Validation Commands section to style guide
- Fix malformed table row in style guide
- Remove unsourced content additions in project-context
- Fix roadmap section heading and index link format
- Fix accountability softening in party-mode dialogue
2026-04-02 20:46:44 -07:00
miendinh 072de34450
docs(vi-vn): add Vietnamese translation for BMAD documentation (#2110)
* docs(vi-VN): add Vietnamese translation for BMAD documentation

* feat(i18n): add Vietnamese website locale

* docs(vi-VN): refine translated documentation

* docs(vi-VN): sync terminology with latest upstream docs

* fix(docs): normalize Vietnamese locale path casing

* docs(vi): update non-interactive installation translation

* docs(vi): translate analysis phase explanation

* docs(vi): sync updated reference and tutorial pages

---------

Co-authored-by: miendinh <miendinh@users.noreply.github.com>
2026-04-02 20:44:13 -07:00
Alex Verkhovsky 003c979dbc
chore: remove SM agent (Bob) and migrate to Developer agent (#2186)
* chore: remove SM agent (Bob) and migrate capabilities to Developer agent

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(docs): correct agent naming and grammar from review triage

Standardize Developer agent references to bmad-agent-dev (matching
installed skill directory name) and fix possessive apostrophe in
implementation-readiness workflow.

* fix(skills): replace dev team references with Developer agent

No longer a multi-agent development team — just one Developer agent.
Remove residual Scrum Master search patterns from retrospective.

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 12:25:24 -07:00
Alex Verkhovsky 48c2324b28
chore: remove QA agent (Quinn) and migrate capability to Developer agent (#2179)
Delete the Quinn (bmad-agent-qa) agent wrapper and add QA test-generation
capability to Amelia (bmad-agent-dev). Update agent tables, testing docs
(EN/ZH-CN/FR), marketplace.json, party-mode, and checklist references.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 07:13:35 -07:00
Alex Verkhovsky 07d72394fd
fix(checkpoint): add explicit HALT before decision menu in wrapup step (#2184)
Skill validator (STEP-04) flagged the decision menu in step-05 as
missing an explicit halt instruction between presenting the menu and
acting on the user's choice, risking LLM auto-advance.
2026-04-01 22:52:46 -06:00
Alex Verkhovsky 7ef45d472c
docs(checkpoint): add explainer page and workflow diagram (#2183)
* docs(checkpoint): add explainer page and workflow diagram

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs(checkpoint): replace excalidraw source with exported PNG diagram

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 22:20:48 -06:00
Alex Verkhovsky 2ea917ef5c
fix(checkpoint): address review findings from adversarial triage (#2180)
Clarify review_mode state transition intent in generate-trail, label
step-02 walkthrough branches as normal vs fallback, replace circular
communication style rule with config variable refs, swap confirm gate
for [inferred] flag, and clarify stats data source as full diff.
2026-04-01 10:43:08 -07:00
Alex Verkhovsky 1b776f565b
feat: add bmad-checkpoint-preview skill (#2145)
* feat: add bmad-checkpoint skill for guided human change review

Copies the av-human-review experiment skill into BMAD-METHOD as
bmad-checkpoint, following established multi-step skill conventions
(SKILL.md → workflow.md → step chain). Registered in module-help.csv
under 4-implementation phase.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: rename bmad-checkpoint to bmad-checkpoint-preview

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(checkpoint): inline workflow into SKILL.md and add global step rules

Remove separate workflow.md — its content now lives directly in SKILL.md
with merged frontmatter. Replace scattered standing rules with a structured
Global Step Rules section (path:line format, front-load output, comm style).

* refactor(checkpoint): reference global step rules from SKILL.md in step-01

* refactor(checkpoint): deduplicate step rules against global step rules

Steps 2–4 now reference Global Step Rules in SKILL.md instead of
restating path:line format, front-load, and silence rules locally.
Step-specific rules (concern-based org, design judgment, risk
awareness, experiential testing) are preserved.

* fix(checkpoint): move main_config out of SKILL.md frontmatter

SKILL.md frontmatter should only contain name and description.
Hardcode the config path inline in the INITIALIZATION section.

* docs(checkpoint): update skill description and trigger phrases

Rewrite description to reflect the skills purpose as an LLM-assisted
human-in-the-loop review. Add checkpoint trigger, drop stale triggers.

* fix(checkpoint): align trail format with global step rules and add token budget

Use CWD-relative path:line in fallback trail (not markdown links),
cap full-file reads at ~50k tokens, remove over-prompted empty-tree SHA.

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

* refactor(checkpoint): rewrite FIND THE CHANGE as numbered priority cascade

Replace the ad-hoc change-finding logic with a clean 1-5 cascade
modeled after quick-dev Intent Check: explicit argument, recent
conversation, sprint tracking, current git state, ask. Extract
spec/commit pairing into a separate ENRICH step that runs after
any cascade level resolves. Add planning_artifacts to SKILL.md
initialization.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(checkpoint): clarify review_mode and terse-commit instructions in step-01

Replace opaque Review Mode table with explicit set-variable instructions.
Scope terse commit message handling to bare-commit mode only.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(checkpoint): make review_mode a numbered cascade, not independent bullets

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(checkpoint): simplify change_type from table to one-liner

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(checkpoint): make link-to-source conditional on source existing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(checkpoint): make surface area stats best-effort with baseline cascade

Replace rigid with-spec/bare-commit split with a 4-level fallback:
baseline_commit, merge-base, HEAD~1, skip. Omit metrics that
cannot be computed rather than failing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(checkpoint): extract fallback trail generation into generate-trail.md

Reduce step-01 bloat by moving the conditional trail generation
sub-routine into its own file, loaded only when review mode is
not full-trail.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(checkpoint): add early-exit routing and wrap-up step

Replace undefined "I've seen enough" exits with proper early-exit
handling across steps 02-04. Extract wrap-up logic into dedicated
step-05-wrapup.md. Fix step-02 menu text that incorrectly promised
"code review" when step-03 does risk surfacing.

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 10:12:14 -07:00
Alex Verkhovsky 1aa0903e79
chore(agents): remove Barry quick-flow-solo-dev agent (#2177)
Delete the Barry agent persona and migrate its QD (quick-dev)
capability to the Amelia dev agent. Update EN, ZH, and FR docs,
marketplace JSON, and workflow diagrams.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 08:46:14 -07:00
Brian 2c5436f672
style: update docs theme to match bmadcode.com Ghost blog (#2176)
Replace purple/electric blue accent with Ghost blog design tokens:
- Background #0a0a0a, surface #1a1a1a, borders #262626
- Accent blue #3b82f6, text #fafafa/#a1a1a1/#666666
- Inter body, Space Grotesk headings, JetBrains Mono code
- Remove logo images, use text title
2026-04-01 01:12:40 -05:00
Taras Romaniv 1f99eb0496
fix: preserve local custom module sources during quick update (#2172)
* fix: preserve local custom module sources during quick update

Keep customModules in the generated main manifest so local custom
module source paths survive update runs. Load those preserved source
paths during stock quick update before falling back to the custom
cache directory.

This fixes the case where BMAD would drop customModules, lose the
original source path for a local module, and then skip the module or
try to re-cache from _bmad/_config/custom/<module>, which could fail
with ENOENT after the cache directory was removed.

Also adds an installation component regression test to verify
customModules and sourcePath are preserved in manifest generation.

Fixes #1582

* fix: ensure consistent formatting

* refactor: extract quick update custom source assembly

Move quick-update custom module source collection out of Installer and into
CustomModules as assembleQuickUpdateSources(). This keeps discoverPaths() focused on consuming prepared install inputs while
making the quick-update source assembly step explicit and easier to evolve.

Also:
- preserve customModules metadata in manifest regeneration for installed modules
- drop stale customModules entries when modules are no longer installed
- cover manifest preservation and manifest-backed quick-update sources in tests
2026-03-30 17:49:05 -07:00
Emmanuel Atsé 2302d9cdc5
docs(fr): translate output folder path resolution section (#2140)
Syncs French translation with commit 1040c3c (fix: correctly resolve
output_folder paths outside project root #2132).

Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-29 14:01:09 -07:00
Alex Verkhovsky 3980e57885
feat(quick-dev): one-shot route generates spec trace file (#2121)
* feat(quick-dev): generate spec trace file for one-shot route

One-shot changes now leave a lightweight spec file with frontmatter,
intent summary, and suggested review order — eliminating numbering
gaps when quick-dev is used as the primary dev loop.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(quick-dev): reference spec template instead of inlining structure

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(quick-dev): deduplicate slug derivation and clarify title variable

Extract shared slug derivation logic above the route fork in step-01 so
both one-shot and plan-code-review routes use a single instruction block.
Add explicit title variable assignment in step-oneshot before it is
referenced in the Generate Spec Trace section.

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 13:55:09 -07:00
PinkyD 4b1026b252
fix(party-mode): clarify solo mode and improve response presentation (#2164)
* clear up contradiction and config mispath

* fix(party-mode): clarify solo mode behavior and improve response presentation rules

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 11:25:56 -05:00
PinkyD ce9c66490a
refactor(party-mode): consolidate into single SKILL.md with real subagents (#2160)
Replace the multi-file workflow architecture (workflow.md + 3 step files)
with a self-contained SKILL.md that spawns each agent as an independent
subagent via the Agent tool. This produces genuinely diverse perspectives
instead of one LLM roleplaying multiple characters. Adds --model and
--solo flags for flexibility.
2026-03-29 01:22:34 -05:00
Brian 7dd49a452f
refactor: remove bmad-init skill, standardize config loading (#2159)
* refactor: remove bmad-init skill and standardize config loading across all skills

Remove the bmad-init core skill entirely — all agents and workflow skills now
load config directly from their module's config.yaml instead of delegating to
bmad-init as an intermediary. This eliminates the Python script dependency and
simplifies the activation path for every skill.

Changes across all skill types:

- Agents (9 skills): Replace "Load config via bmad-init skill" block with
  direct config loading from `{project-root}/_bmad/bmm/config.yaml`, resolving
  user_name, communication_language, document_output_language,
  planning_artifacts, and project_knowledge

- Workflow skills (12 skills): Standardize INITIALIZATION/Configuration Loading
  sections to a consistent Activation format matching the agent pattern

- bmad-prfaq: Align activation to standard config pattern, convert scripted
  dialogue to outcome-focused instructions (no direct quotes)

- bmad-product-brief: Remove External Skills section referencing bmad-init

- bmad-party-mode: Standardize initialization to Activation format

- bmad-advanced-elicitation: Inline agent_party path instead of config var

- bmad-distillator: Remove unused argument-hint frontmatter

- Delete legacy create-prd/ directory (superseded by bmad-create-prd)

- Delete bmad-init skill entirely: SKILL.md, bmad_init.py, core-module.yaml,
  and test suite

* fix: remove remaining bmad-init references from marketplace.json and distillate examples

Clean up missed references: remove bmad-init from marketplace.json skills
list, replace bmad-init examples in distillate-format-reference.md with
bmad-help/bmad-setup to keep examples valid without referencing a removed skill.

* fix: update broken file references in bmad-edit-prd after create-prd deletion

Point prdPurpose refs from deleted create-prd/data/ to bmad-create-prd/data/
and validationWorkflow ref from create-prd/steps-v/ to bmad-validate-prd/steps-v/.
2026-03-28 20:35:11 -05:00
Alex Verkhovsky 04513e5953
feat(installer): restore KiloCoder support and installer (#2151)
Kilo Code now supports Agent Skills. Remove the suspended flag,
restore it in the IDE picker, and replace the suspended test suite
with a full native-skills installation test.

- Remove suspended message from platform-codes.yaml
- Rewrite test suite 22: config, IDE picker, install, skill output,
  legacy cleanup, and reinstall assertions
- Update migration checklist to reflect active status

Co-authored-by: Junie <junie@jetbrains.com>
Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-28 20:24:29 -05:00
Brian aae6ddb8c9
fix: remove ancestor_conflict_check from all platforms (#2158)
The ancestor directory walk was based on the false premise that IDEs
like Claude Code inherit skills from parent directories — they do not.
The check blocked legitimate installations when unrelated BMAD skills
existed anywhere up the directory tree.
2026-03-28 18:45:55 -05:00
Brian abfc56bd2c
feat: add bmad-prfaq skill as alternative analysis path (#2157)
* feat: add bmad-prfaq skill as alternative to product brief

Add Working Backwards PRFAQ challenge skill for stress-testing product
concepts through Amazon's PRFAQ methodology. Includes press release
drafting, customer FAQ, internal FAQ, and verdict stages with subagent
support for artifact scanning and web research.

- New bmad-prfaq skill with 5-stage interactive gauntlet and headless mode
- Subagents for artifact analysis and web research (graceful degradation)
- Research-grounded output directive for current market/competitive data
- Always produces distillate for downstream PRD consumption
- Fix manifest array syntax in both prfaq and product-brief manifests
- Drop number prefixes from reference files
- Update docs: getting-started, workflow-map, agents, skills reference
- Add analysis-phase explainer doc with comparison table and decision guide
- Update workflow-map-diagram.html with prfaq card
- Add -H and -A args to CSV for both skills
- Add unist-util-visit as devDependency (was imported but undeclared)

* fix: harden bmad-prfaq for compaction resilience and context efficiency

Add coaching persona re-anchors to all stage prompts so the behavioral
directive survives context compaction. Add do-not-read guards at resume
detection, headless mode, and input gathering to prevent parent agent
context bloat. Add Stage 1 coaching notes capture. Adapt template and
press release stage for non-commercial concept types. Cap subagent
response token budgets.

* fix: add config.user.yaml to file-ref validator allowlist

Also update PRFAQ config path to use correct _config/bmm/ prefix.
2026-03-28 17:16:41 -05:00
Alex Verkhovsky fa909a8916
feat: add Junie platform support (#2142)
* feat: add Junie platform support with .agents/skills target

Co-authored-by: Junie <junie@jetbrains.com>

* fix: disable ancestor_conflict_check for Junie platform

Junie does not traverse ancestor directories looking for skills,
so ancestor_conflict_check should be false.

Co-authored-by: Junie <junie@jetbrains.com>

---------

Co-authored-by: Junie <junie@jetbrains.com>
2026-03-27 23:55:57 -06:00
Brian e0ea6a0500
fix: support skills/ folder as module source location (#2149)
The installer now finds module.yaml in both skills/ and src/ directories,
including one level deep in subfolders. Updates bmb module-definition to
skills/module.yaml to match its actual structure.
2026-03-28 00:33:10 -05:00
Brian c91db0db4b
fix: revert bmb module-definition path to src/module.yaml (#2146)
bmad-builder reverted its skills/ directory back to src/ for installer
compatibility (bmad-code-org/bmad-builder#40). Update the external
modules manifest to match.
2026-03-27 08:46:18 -06:00
Alex Verkhovsky 513f440a23
refactor(installer): restructure installer with clean separation of concerns (#2129)
* refactor(installer): restructure installer with clean separation of concerns

Move tools/cli/ to tools/installer/ with major structural cleanup:

- InstallPaths async factory for path resolution and directory creation
- Config value object (frozen) replaces mutable config bag
- ExistingInstall value object replaces stateful Detector class
- OfficialModules + CustomModules + ExternalModuleManager replace monolithic ModuleManager
- install() is prompt-free; all user interaction in ui.js
- Update state returned explicitly instead of mutating customConfig
- Delete dead code: dependency-resolver, _base-ide, IdeConfigManager,
  platform-codes helpers, npx wrapper, xml-utils
- Flatten directory structure: custom/handler → custom-handler,
  tools/cli/ → tools/installer/, lib/ directories removed
- Update all path references in package.json, tests, CI, and docs

* fix(installer): guard ExistingInstall.version and surface module.yaml errors

Guard ExistingInstall.version access with .installed check in
uninstall.js, ui.js, and installer.js to prevent throwing on
empty/partial _bmad dirs. Surface invalid module.yaml parse errors
as warnings instead of silently returning empty results.
2026-03-27 06:50:07 -06:00
sdev 36f9df69bf fix: address CodeRabbit review feedback for PRD scoping step
step-08-scoping.md:
- Neutral title replacing hard-coded "MVP & Future Features"
- Task statement no longer mandates phase-based prioritization
- Confirmation gate now covers artifact creation, not just de-scoping
- Phased delivery uses user-defined phase labels/count instead of fixed 3
- "wants phased" phrasing replaced with "requests/chooses"
- Development sequence question branches by release mode
- Menu text conditional on delivery mode (no "phased roadmap" for single-release)
- Handoff to step-09 now persists releaseMode in frontmatter
- New failure mode for unapproved phase artifact creation

step-11-polish.md:
- Preservation rule now includes consent-critical evidence from step 8
2026-03-27 18:13:18 +05:30
sdev 4655bb1482 fix(prd): require explicit user confirmation before de-scoping requirements or inventing phases 2026-03-27 18:13:17 +05:30
Akhilesh Tyagi 1040c3c306
fix: correctly resolve output_folder paths outside project root (#2132)
* fix(bmad-init): correctly resolve output_folder paths outside project root

  When output_folder was set to an absolute path (e.g. /Users/me/outputs),
  the {project-root}/{value} result template stored it as
  {project-root}//absolute/path. resolve_project_root_placeholder then did
  a naive string replace, producing /project//absolute/path — a broken path
  that workflows could not resolve.

  For relative paths outside the root (e.g. ../../sibling), the same naive
  replace left un-normalized paths like /project/../../sibling in the
  resolved config, which some tools mishandled.

  Fix resolve_project_root_placeholder to strip the {project-root} token,
  detect whether the remainder is absolute (returning it directly) or
  relative (joining with project root and normalizing via os.path.normpath).

  Fix apply_result_template to skip the template entirely when raw_value is
  already an absolute path, and to normalize the result for relative-but-
  outside paths. This covers the bmad-init SKILL write path, which bakes
  the resolved path directly into config.yaml.

  Add 7 tests covering all three path cases (absolute, relative-with-
  traversal, normal in-project) for both functions.

* Address review comments

---------

Co-authored-by: Akhilesh Tyagi <akhilesh.t@nextiva.com>
Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-26 21:46:14 -05:00
Brian ed9dea9058
refactor: consolidate plugin.json metadata into marketplace.json (#2137)
Merge license, homepage, repository, keywords, and author from
plugin.json into marketplace.json and remove the redundant file.
The npx skills installer only reads marketplace.json for skill
discovery — plugin.json contributed no functional value.
2026-03-26 19:48:04 -05:00
Brian 3d8a89c7e1
feat: add .claude-plugin marketplace and plugin metadata (#2136) 2026-03-26 19:12:32 -05:00
github-actions[bot] 819d373e2e chore(release): v6.2.2 [skip ci] 2026-03-26 02:44:35 +00:00
Brian a5640c890d
chore: add v6.2.2 changelog and use CHANGELOG.md for GH release notes (#2127)
Update publish workflow to extract release notes from CHANGELOG.md
instead of using --generate-notes, with fallback if no entry found.
2026-03-25 21:43:25 -05:00
Brian 6dd0a97c1f
fix: update bmb module-definition path for skills/ restructure (#2126)
bmad-builder moved skills from src/skills/ to skills/ at repo root
for Claude Code plugin and Vercel Skills CLI compatibility.
2026-03-25 21:25:33 -05:00
Brian cfe40fccd5
refactor: modernize module-help CSV format and rewrite bmad-help as outcome-based skill (#2120)
New CSV format: module,skill,display-name,menu-code,description,action,args,phase,after,before,required,output-location,outputs

- Replace sequence numbers with after/before dependency graph
- Drop command, workflow-file, agent, options columns
- Add action column for multi-action skills (tech-writer, create-story)
- Add args column for CLI shortcut hints
- Make description optional (only when adding flow/routing context beyond frontmatter)
- Expand module names for clarity
- Rewrite bmad-help SKILL.md from procedural 8-step execution to outcome-based design
- Fix eslint config to ignore gitignored lock files (pnpm-lock.yaml, bun.lock)
2026-03-24 23:46:48 -05:00
梁山河 090bfea9b2
docs(zh-cn): close explanation gap relinks (#2102)
我补齐 explanation 目录在本轮审校中确认的中文缺口,统一关键命令名为当前 `bmad-*` 形式,并修正 Party Mode 示例里的半翻角色标签。此前这些页面缺少回连到中文目标的入口且术语混用旧名,导致查阅路径容易断层;现在每页都补了中文回链并对齐命名,降低理解和跳转成本。

Feishu: https://feishu.cn/wiki/TODO
Made-with: Cursor

Co-authored-by: leon <leon.liang@hairobotics.com>
2026-03-24 04:07:07 -06:00
github-actions[bot] fce9d6c0c8 chore(release): v6.2.1 [skip ci] 2026-03-24 06:25:54 +00:00
Brian 3acd1a7912
Merge pull request #2116 from bmad-code-org/release
docs: add v6.2.1 changelog
2026-03-24 01:21:43 -05:00
Brian 8cac7f9210
Merge branch 'main' into release 2026-03-24 01:21:05 -05:00
Brian Madison 0cdfd7564f docs: add v6.2.1 changelog 2026-03-24 01:18:08 -05:00
梁山河 c350e5b9d8
docs(zh-cn): refresh reference and roadmap docs (#2101)
我统一修订中文模块与测试参考、路线图和文档风格指南,确保模块边界、测试能力、术语和跳转在中文站点内一致。此前这些页面存在命名过时、语气不统一和提示块语法不稳定的问题;现在我改为当前 skills/workflow 语义,并明确英文外部资源边界与 `:::` 提示块规范,以降低查阅和贡献时的歧义成本。

Feishu: https://feishu.cn/wiki/TODO
Made-with: Cursor

Co-authored-by: leon <leon.liang@hairobotics.com>
2026-03-23 23:33:43 -06:00
梁山河 0d7d7dae04
docs(zh-cn-reference): refresh workflow and skill references (#2100)
我统一修订中文 reference 中 workflow-map、commands、agents、core-tools 四页,改正过时命名与调用方式,并将术语切换到当前 skills 体系。此前这些页面混用了旧版前缀和命令语义,容易让用户在查阅阶段误用流程;现在页面结构与英文源和现行实现保持一致,同时优先串联中文路径以提升检索效率。

Feishu: https://feishu.cn/wiki/TODO
Made-with: Cursor

Co-authored-by: leon <leon.liang@hairobotics.com>
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-23 23:31:16 -06:00
Brian a04635efe0
fix: agent-manifest.csv empty after install — type mismatch + scan path bug (#2115)
Two bugs combined to produce an empty agent-manifest.csv:

1. collectAgents() only scanned {module}/agents/ directories, but agents
   live at various paths (bmm/1-analysis/bmad-agent-analyst/,
   cis/skills/bmad-cis-agent-*, etc.). Now walks the full module tree.

2. All 9 BMM agent manifests declared type: skill instead of type: agent.
   The manifest generator requires type: agent to include a directory in
   agent-manifest.csv. CIS, GDS, TEA, and WDS already had the correct type.

Changes:
- Fix 9 BMM bmad-skill-manifest.yaml files: type: skill → type: agent
- Replace collectAgents/getAgentsFromDir with full-tree recursive scan
- Module field from manifest file always takes precedence over directory
- Remove dead skillManifest load (legacy .md agent support removed)
- Add TODO in bmad-artifacts.js documenting legacy agent pipeline as dead code
- Add 10 regression tests covering BMM, CIS, and GDS directory layouts
2026-03-24 00:18:29 -05:00
梁山河 94831cbb1e
docs(zh-cn): refine Epic3 story 3.3 and 3.4 explanations (#2099)
* docs(zh-cn-explanation): refine epic3 stories 3.3-3.4

我重写头脑风暴、高级启发与 Party Mode 的中文说明,明确三者在适用场景、价值和边界上的差异,避免字面对译带来的误用。
我同步收敛 Quick Dev 与对抗性评审文案,强调各自定位与配合关系,并补齐中文优先链路和当前 workflow 命名。

feishu: https://feishu.cn/wiki/TODO
Made-with: Cursor

* docs(zh-cn-explanation): 统一提示块围栏语法

我将五篇 explanation 文档里的四冒号提示块语法统一为三冒号,确保与当前文档渲染规则一致。
此前这些文档混用不同围栏写法,容易在审阅和渲染中引入不必要差异;现在统一后可减少维护噪音。

feishu: https://feishu.cn/wiki/TODO
Made-with: Cursor

---------

Co-authored-by: leon <leon.liang@hairobotics.com>
2026-03-23 22:04:09 -06:00
梁山河 8b0754106d
docs(zh-cn): refine Epic3 story 3.1 and 3.2 explanations (#2098)
* docs(zh-cn-explanation): refine epic3 stories 3.1-3.2

我统一 solutioning、project context 与 established projects 的中文术语和叙述边界,避免 explanation 页面混入 how-to 语气导致误判。
我补齐中文优先跳转并更新关键 workflow 命名,使多智能体协作与既有项目 FAQ 的说明更可执行。

feishu: https://feishu.cn/wiki/TODO
Made-with: Cursor

* docs(zh-cn-explanation): normalize admonition syntax

我将 3 篇中文 explanation 文档中的提示块语法统一为仓库约定的 `:::...:::` 形式。
此前使用 `::::...::::` 会导致与现有文档规范不一致;现在统一后可减少渲染歧义与后续维护成本。

Feishu: <https://www.feishu.cn/>
Made-with: Cursor

---------

Co-authored-by: leon <leon.liang@hairobotics.com>
2026-03-23 20:03:54 -06:00
梁山河 90d9d880b6
docs(zh-cn): refine story 2.5 and 2.6 how-to guides (#2097)
* docs(zh-cn-how-to): refine stories 2.5 and 2.6 docs

我澄清中文自定义与文档分片指南,保留命令、路径和配置键名的技术准确性,降低高级操作误解。
我同步修正 v4 到 v6 升级步骤中的旧新路径与工作流命名,帮助迁移时按当前约定执行。

feishu: https://feishu.cn/wiki/TODO
Made-with: Cursor

* docs(zh-cn-how-to): clarify shard output precedence

我在“你将获得”中补充完整文档与分片文档并存时的读取优先级说明。
此前“可保留”表述容易让用户误以为分片会自动生效;现在明确并存不建议且默认优先读取完整文档。

Feishu: <https://www.feishu.cn/>
Made-with: Cursor

---------

Co-authored-by: leon <leon.liang@hairobotics.com>
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-23 19:20:03 -06:00
lif 0c245474c4
fix: use execFileSync to preserve spaces in CLI arguments (#2088)
Replace execSync with execFileSync in npx wrapper so that
argument values containing spaces (e.g. --user-name "CI Bot")
are passed as discrete array elements instead of being split
by the shell.

Fixes #2066

Signed-off-by: majiayu000 <1835304752@qq.com>
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-23 18:28:32 -06:00
Murat K Ozcan 303e7ae290
fix: issue 55 config paths (#2113)
* fix: issue 55 config paths

* Fix: ci test failure
2026-03-23 15:55:19 -05:00
Alex Verkhovsky 48152507e2
fix(quick-dev): remove redundant H1 title from spec template (#2111)
The frontmatter `title` field is the single source of truth.
The duplicate `# {title}` H1 heading was redundant and has been removed.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-23 01:51:53 -06:00
Alex Verkhovsky b3cf338118
refactor(quick-dev): rename tech-spec prefix to spec (#2109)
* refactor(quick-dev): rename tech-spec prefix to spec

* docs: update tech-spec references to spec
2026-03-23 00:09:05 -06:00
Alex Verkhovsky fc2b253ab5
fix(quick-dev): preserve tracking identifiers in spec slug derivation (#2108)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 23:40:44 -06:00
Alex Verkhovsky ac5cb9de5c
refactor(quick-dev): replace unconditional artifact scan with intent cascade (#2105)
Short-circuit evaluation in step-01: explicit argument → conversation
context → full artifact scan. Stops prompting as soon as intent is
unambiguous. All existing scan behaviors preserved in tier 3.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 22:40:04 -06:00
Alex Verkhovsky 980d2904f4
fix(quick-dev): add self-check gate for task completion tracking (#2104)
Adds a Self-Check subsection at the end of step-03 that forces the
implementing agent to verify all tasks are complete and mark checkboxes
before handing off to the review step.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 16:46:54 -06:00
梁山河 76fb7e067b
docs(zh-cn): refine established project guides (#2096)
* docs(zh-cn): refine established project guides

clarify the boundary between new-project and established-project usage so zh-cn readers can choose the right workflow path.
align project context terminology and command references with current conventions while keeping guidance concise and executable.

Feishu: https://www.feishu.cn/
Made-with: Cursor

* docs(zh-cn): fix project-context syntax and wording

我将 project-context 文档中的提示块语法统一回项目规范的 `:::...:::` 形式,避免与文档风格约定不一致。
我同时把“在不同用户故事(story)间决策不一致”调整为“之间决策不一致”,提升中文表达的自然度与可读性。

Feishu: <https://www.feishu.cn/>
Made-with: Cursor

---------

Co-authored-by: leon <leon.liang@hairobotics.com>
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-22 10:27:41 -06:00
梁山河 ad2eb0e127
docs(zh-cn): refine install and non-interactive guides (#2094)
* docs(zh-cn): refine install and non-interactive guides

我统一中文安装文档中的术语和参数说明,补齐预发布安装与 skills 启用提示,
并保持交互式与非交互式安装路径和英文源文一致,减少安装场景下的理解偏差。

Feishu: https://www.feishu.cn/
Made-with: Cursor

* docs(zh-cn): align install guide review wording

我在安装指南中补充目录结构示例说明,明确工具相关目录会随所选平台变化,避免读者误以为 .claude/.cursor 一定同时存在。
我同时统一非交互式安装文档里残留的“标志”表述为“参数”,让术语在全文保持一致并降低理解成本。

Feishu: <https://www.feishu.cn/>
Made-with: Cursor

---------

Co-authored-by: leon <leon.liang@hairobotics.com>
2026-03-22 10:24:31 -06:00
Alex Verkhovsky 7e97b7e7f3
fix(docs): correct skill names in getting-started tutorials (#2103)
Agent skills referenced with shortened names (bmad-pm, bmad-architect,
etc.) that don't match installed skill names. Fixed to use actual names
(bmad-agent-pm, bmad-agent-architect, etc.) across EN, ZH-CN, and FR.
Also fixed bmad-research to three specific research skills (EN, FR) and
bmad-product-brief to bmad-create-product-brief (ZH-CN).

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 10:22:29 -06:00
梁山河 ba2a5cc6a0
docs(zh-cn): align getting-started tutorial workflows (#2093)
* docs(zh-cn): align getting-started tutorial workflows

我按英文源文更新中文入门教程中的命令、工作流和智能体调用方式,
并统一步骤叙述与导航语义,减少术语漂移和旧命令误导。

Feishu: https://www.feishu.cn/
Made-with: Cursor

* docs(zh-cn): fix tutorial skill names

我将入门教程阶段 1 中过时或不可用的技能名替换为当前可调用的技能名。
此前 `bmad-research` 与 `bmad-create-product-brief` 可能导致新用户执行受阻;现在改为具体研究技能与 `bmad-product-brief`,提升教程可执行性。

Feishu: <https://www.feishu.cn/>
Made-with: Cursor

---------

Co-authored-by: leon <leon.liang@hairobotics.com>
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-22 10:09:23 -06:00
梁山河 347f459d5d
docs(zh-cn): refine entry copy and navigation (#2092)
* docs(zh-cn): refine entry copy and navigation

我统一中文入口层文案语气,减少机翻腔并保持与英文语义一致,
让读者从 README、首页到 404 与界面文案都保持同一术语和导航预期。

Feishu: https://www.feishu.cn/
Made-with: Cursor

* docs(zh-cn): align non-interactive install link label

我把 README_CN 中“查看完整安装选项”改为“查看非交互式安装选项”。
此前文案范围大于目标页面内容,容易让读者误以为是安装总览;现在文案与链接目标保持一致,减少理解偏差。

Feishu: <https://www.feishu.cn/>
Made-with: Cursor

---------

Co-authored-by: leon <leon.liang@hairobotics.com>
2026-03-22 10:08:35 -06:00
梁山河 eb72361720
docs(zh-cn): refine help and quick-fixes guides (#2095)
* docs(zh-cn): refine help and quick-fixes guides

improve zh-cn troubleshooting guidance so users can quickly choose the right support path and self-recover from common issues.
align bmad-help and quick-dev usage wording with current invocation conventions and remove glossary-style appendices to keep the pages action-oriented.

Feishu: N/A
Made-with: Cursor

* docs(zh-cn): fix tip admonition fence syntax

我把 get-answers-about-bmad 文档中的 `::::tip` 语法改为仓库统一使用的 `:::tip`。
此前四冒号写法与项目文档约定不一致,可能导致提示块渲染异常;现在与现有 Starlight 写法保持一致。

Feishu: <https://www.feishu.cn/>
Made-with: Cursor

---------

Co-authored-by: leon <leon.liang@hairobotics.com>
2026-03-22 10:06:58 -06:00
Alex Verkhovsky e3f935fd6d
fix(docs): community feedback — typo, locale 404s, llms-full (#2091)
* fix(docs): correct Hasselhoff spelling, add locale-aware 404 redirect

Fix "Hasslehoff" → "Hasselhoff" typo in customize-bmad.md across all
three locales (en, zh-cn, fr).

Add client-side locale detection to 404.astro so GitHub Pages serves
the correct localized 404 page instead of always showing English.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(build): exclude translated locales from llms-full.txt

llms-full.txt was including zh-cn and fr docs, tripling the content
with duplicate information in different languages. Restrict to English
only — translations add no value for LLM context consumption.

Reduces output from ~393K to ~114K chars (~29k tokens).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(i18n): extract locale config to shared module

Move locale definitions from astro.config.mjs into a shared
website/src/lib/locales.mjs consumed by astro config, build-docs,
and 404.astro. Adding a new locale is now a single-file change.

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 16:42:57 -06:00
Alex Verkhovsky 10282a4a14
fix(quick-dev): use absolute paths in code -r invocations (#2087)
* fix(quick-dev): use absolute paths in code -r invocations

Agent CWD may differ from the project root in worktree setups,
causing relative paths to silently fail. Resolve paths via
git rev-parse --show-toplevel before invoking code -r.

* fix(quick-dev): add CWD fallback when git rev-parse fails

Adds graceful fallback to current working directory when
git rev-parse --show-toplevel fails (VCS unavailable).
2026-03-21 15:37:04 -06:00
Alex Verkhovsky a59ae5c842
fix(quick-dev): make file path references clickable (#2085)
* fix(quick-dev): make file path references clickable

Spec-file links use paths relative to the spec file's
directory (clickable in VS Code). Terminal output paths
use CWD-relative format for terminal clickability.

* fix(quick-dev): add :line suffix to step-oneshot path example

Aligns the file path example in step-oneshot.md with the clickable
`:line` format already enforced in step-03-implement.md and
step-05-present.md.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 12:20:45 -06:00
Alex Verkhovsky ad9cb7a177
refactor(installer): remove dead .agent.yaml/.xml fallback logic (#2084) 2026-03-21 01:52:39 -06:00
Alex Verkhovsky 93a1e1dc46
refactor(installer): remove dead task/tool/workflow manifest code (#2083)
* refactor(installer): discover skills by SKILL.md instead of manifest YAML

Switch skill discovery gate from requiring bmad-skill-manifest.yaml with
type: skill to detecting any directory with a valid SKILL.md (frontmatter
name + description, name matches directory name). Delete 34 stub manifests
that carried no data beyond type: skill. Agent manifests (9) are retained
for persona metadata consumed by agent-manifest.csv.

* refactor(installer): remove dead task/tool/workflow manifest code

The remove-skill-manifest-yaml branch deleted the scanners that
discover tasks, tools, and workflows but left behind the code that
writes their manifest CSVs. Remove collectTasks/Tools/Workflows,
writeTaskManifest/ToolManifest/WorkflowManifest, their helpers, and
the now-unreachable getPreservedCsvRows/upgradeRowToSchema methods.
Update installer pre-registration and test assertions accordingly.
2026-03-21 00:12:40 -06:00
Alex Verkhovsky 31ae226bb4
refactor(installer): discover skills by SKILL.md instead of manifest YAML (#2082)
Switch skill discovery gate from requiring bmad-skill-manifest.yaml with
type: skill to detecting any directory with a valid SKILL.md (frontmatter
name + description, name matches directory name). Delete 34 stub manifests
that carried no data beyond type: skill. Agent manifests (9) are retained
for persona metadata consumed by agent-manifest.csv.
2026-03-21 00:11:23 -06:00
Alex Verkhovsky c28206dca4
refactor(installer): remove dead agent compilation pipeline (#2080)
* refactor(installer): remove dead agent compilation pipeline

Delete 9 files (~2,600 lines) that compiled .agent.yaml to .md.
No .agent.yaml files exist in the source tree — agents now ship
as pre-built SKILL.md. Clean up all references in installer,
module manager, custom handler, base IDE, UI, and tests.

* refactor(custom-handler): remove dead install/copy/find methods

CustomHandler.install(), copyDirectory(), and findFilesRecursively()
are never called — custom modules are installed via moduleManager.install()
since Dec 2025. Also removes unused FileOps import and constructor.

Verified with before/after clean-installer comparison (codex + custom
modules with custom.yaml): output is identical.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(installer): remove dead compilation refs from docs and module manager

Address review findings from PR #2080 triage:
- Remove compile-agents from CLI action docs (en, fr, zh-cn)
- Remove dead vendorCrossModuleWorkflows() and .agent.yaml skip logic
- Clean stale compilation-era comments in manifest-generator

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 22:52:02 -06:00
Emmanuel Atsé 1a6f8d52bc
docs: i18n: Add complete French translation (#2073)
* docs: i18n(fr): add complete French translation

Add comprehensive French (fr-FR) translation covering all documentation
sections and website configuration:

- Core docs, How-to guides, Explanations, References
- Website config: astro.config.mjs locale setup, fr-FR.json i18n strings
- Assets: French workflow map diagram and quick-dev diagram

Terminology standardized on "Quick Dev" (replacing legacy "Quick Flow").

* docs(fr): remove references to deleted phase-4 agent personas

Remove all references to deleted phase-4 agent personas from French
documentation, matching upcoming PR #2020 changes:

- Remove agent personas: dev/Amelia, pm/John, qa/Quinn, sm/Bob,
  quick-flow-solo-dev/Barry, bmad-master
- Replace deleted agent skill invocations with equivalent workflow skills
  (bmad-dev-story, bmad-qa-generate-e2e-tests, bmad-quick-dev, etc.)
- Depersonalize QA references ("Quinn" → "QA Intégré" / "Workflow QA")
- Simplify workflow invocation instructions (remove "invoke agent" pattern)
- Fix upgrade-to-v6.md SM/Scrum Master references

* docs(fr): fix typos

---------

Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-20 17:10:49 -06:00
Alex Verkhovsky 1cb913523e
refactor(installer): remove legacy workflow, task, and agent IDE generators (#2078)
* refactor(installer): remove legacy workflow, task, and agent IDE generators

All platforms now use skill_format exclusively. The old
WorkflowCommandGenerator, TaskToolCommandGenerator, and
AgentCommandGenerator code paths in _config-driven.js were
no-ops — collectSkills claims every directory before the
legacy collectors run, making their manifests empty.

Removed:
- workflow-command-generator.js (deleted)
- task-tool-command-generator.js (deleted)
- writeAgentArtifacts, writeWorkflowArtifacts, writeTaskToolArtifacts
- AgentCommandGenerator import from _config-driven.js
- Legacy artifact_types/agents/workflows/tasks result fields

Simplified installToTarget, installToMultipleTargets, printSummary,
and IDE manager detail builder to skills-only.

Updated test fixture to use SKILL.md format instead of old agent format.

* fix(installer): address PR review findings from #2078

- Fix temp dir leak in test fixture cleanup (use path.dirname)
- Fail loudly when skill_format missing instead of silent success
- Add workflow.md to test fixture for verbatim-copy coverage

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-20 15:18:47 -06:00
Emmanuel Atsé a2839cbee0
docs: fix duplicate sidebar order number (#2071)
how-to/ customize-bmad.md and project-context.md had the same order
number

Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-20 11:38:35 -06:00
Alex Verkhovsky 6a73623f33
refactor(core-skills): flatten 7 skills by inlining workflow.md into SKILL.md (#2077)
Inline workflow.md content directly into SKILL.md for: editorial-review-prose,
editorial-review-structure, help, index-docs, review-adversarial-general,
review-edge-case-hunter, and shard-doc. Deletes the now-redundant workflow.md
files. No behavioral change — same pattern as advanced-elicitation in PR #2076.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-20 11:29:19 -06:00
Emmanuel Atsé 3ca957e229
docs(zh-cn): correct anchor links to match Chinese headings (#2072)
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-20 11:20:02 -06:00
Alex Verkhovsky 9725b0ae90
refactor(skill): flatten advanced-elicitation by inlining workflow into SKILL.md (#2076)
Merge workflow.md content directly into SKILL.md and delete the
now-redundant workflow file.  The frontmatter `agent_party` variable
moves into SKILL.md; all relative file references (`./methods.csv`)
remain valid.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-20 11:08:53 -06:00
Alex Verkhovsky 182550407c
fix(code-review): update sprint-status to done after review completes (#2074)
* fix(code-review): update sprint-status to done after review completes

The code-review workflow ended without updating sprint-status.yaml from
"review" to "done", leaving stories stuck in review status. The dev-story
workflow implies code-review handles this transition but it was dropped
during the v6.2.0 step-file architecture refactor.

- Add sprint_status path to workflow initialization
- Track story_key in step-01 when discovered from sprint status
- Add step-04 section 6 to update sprint-status.yaml and story file
- Add step-04 section 7 with next-step options

Closes #2043

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(code-review): address PR review findings — split gating, story_key guard, HALT

- Split section 6 guard: story file status gated on spec_file only,
  sprint-status sync sub-gated on story_key separately
- Add conditional branch for manual choice in multi-story path so
  story_key is cleared when user declines a story selection
- Add HALT directive after Next steps menu to prevent LLM runaway

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 10:56:08 -06:00
dependabot[bot] 4b2389231f
chore(deps): bump h3 from 1.15.5 to 1.15.8 (#2064)
Bumps [h3](https://github.com/h3js/h3) from 1.15.5 to 1.15.8.
- [Release notes](https://github.com/h3js/h3/releases)
- [Changelog](https://github.com/h3js/h3/blob/main/CHANGELOG.md)
- [Commits](https://github.com/h3js/h3/compare/v1.15.5...v1.15.8)

---
updated-dependencies:
- dependency-name: h3
  dependency-version: 1.15.8
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
2026-03-20 01:13:25 -06:00
Alex Verkhovsky 9088d4958b
fix(code-review): restore actionable review output with interactive choices (#2055)
* fix(code-review): restore actionable review output with interactive choices

The March 15 rewrite (PR #2007) removed the ability to auto-fix patches,
create action items in story files, and handle deferred/spec findings.
This restores interactive post-review actions:

- Deferred findings: auto-written to deferred-work.md and checked off in story
- Intent gap/bad spec: conversation with downgrade-to-patch, patch-spec,
  reset-to-ready-for-dev, or dismiss options
- Patch findings: fix automatically, create action items, or show details

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor(code-review): simplify triage to decision-needed/patch/defer/dismiss

Replace 5-bucket classification (intent_gap, bad_spec, patch, defer, reject)
with 4 pragmatic buckets. Findings always written to story file first.
Decision-needed findings gate patch handling — resolve ambiguity before fixing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(code-review): address PR review findings in step-04-present

Replace undefined curly-brace placeholders with angle-bracket syntax,
add HALT guard before patch menu, guard spec_file references for
no-spec mode, and backtick category names for consistency.

* feat(code-review): add HALT guards, batch option, defer reason, final summary

Add strong HALT guards after decision-needed and patch menus to prevent
auto-progression. Add batch-apply option 0 for >3 patch findings. Prompt
for defer reason and append to story file and deferred-work.md. Show
boxed final summary with counts. Polish clean-review shortcut in triage.

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 01:07:04 -06:00
Alex Verkhovsky 0d2863f77f
fix: separate subagent launch from skill invocation in code review (#2069)
* fix: separate subagent launch from skill invocation in code review

The step-02-review prompt fused "invoke skill X" with "in a subagent"
into one instruction, causing LLMs to search for a named agent instead
of launching a generic subagent that uses the skill. Aligns with the
working pattern in quick-dev step-04: upfront gate with inline fallback,
and "Invoke via the skill" as a separate concern from subagent setup.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(code-review): address PR review findings on subagent fallback wording

Capitalize "Markdown" (proper noun) in Acceptance Auditor prompt and
simplify fallback trigger from "context-free subagents" to "subagents"
to eliminate ambiguity about when the fallback activates.

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 01:04:51 -06:00
Brian a092209267
refactor(analysis): consolidate product brief skills and clean up research (#2070)
Replace bmad-create-product-brief (step-based wizard) and
bmad-product-brief-preview (multi-agent) with a single unified
bmad-product-brief skill. Remove accidentally duplicated market
research step files and template. Update research skill
descriptions to use more natural trigger language.
2026-03-19 20:48:47 -05:00
Murat K Ozcan 1786d1debc
fix: tea agent start (#2067)
* fix: tea agent start

* fix: addressed PR comment
2026-03-19 11:40:43 -05:00
Alex Verkhovsky 4cb58ba9f3
Merge pull request #2065 from bmad-code-org/fix-quick-fixes-doc
docs: rewrite quick-fixes how-to around Quick Dev
2026-03-19 00:14:43 -06:00
Alex Verkhovsky 871d921072 docs: fix stale Quick Flow reference in quick-dev explainer opening
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 00:07:17 -06:00
Alex Verkhovsky 3fad46849f docs: rewrite quick-fixes how-to around Quick Dev workflow
Remove DEV agent references and simplify to Quick Dev as the single
entry point. Show free-form intent examples, add deferred work section,
clarify that Quick Dev commits for you.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 00:05:30 -06:00
Alex Verkhovsky 3bb953f18b
Merge pull request #2063 from bmad-code-org/fix-quick-dev-explainer
docs: restore design philosophy to quick-flow explainer
2026-03-18 23:51:35 -06:00
Alex Verkhovsky 43c59f0cff docs: replace quick-flow explainer with quick-dev, remove stale Quick Spec refs
Quick Flow was an umbrella for quick-spec + quick-dev. Quick Spec is
gone and the new preview was promoted to bmad-quick-dev, so the explainer
should be about quick-dev directly. Replaces quick-flow.md with the
original quick-dev-new-preview.md content (renamed), including the
diagram reference. zh-cn uses the original hand-written Chinese
translation. Also removes stale Quick Spec references from agents.md.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 23:47:49 -06:00
Frank 3c8d865457
fix: update src/core and src/bmm path references to match renamed directories (#2053)
The v6.2.0 release renamed src/core to src/core-skills and src/bmm to
src/bmm-skills, but the installer CLI code still referenced the old
directory names, causing ENOENT crashes during installation.

Updated all path references across 7 files in tools/cli/ including
path.join() calls, string comparisons, regex patterns, and comments.

Fixes #2052

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-18 19:29:16 -05:00
Alex Verkhovsky 1b8424cf6d
Merge pull request #2058 from bmad-code-org/fix-elicitation-trigger
fix: add Use when trigger to advanced-elicitation description
2026-03-18 17:21:40 -06:00
Alex Verkhovsky 9973b3c35a
Merge branch 'main' into fix-elicitation-trigger 2026-03-18 17:20:52 -06:00
Alex Verkhovsky 1a0da0278f
Merge pull request #2051 from bmad-code-org/feat-deterministic-skill-validator
feat(tools): add deterministic skill validator for CI
2026-03-18 17:20:30 -06:00
Alex Verkhovsky 52ebc3330d
Merge branch 'main' into fix-elicitation-trigger 2026-03-18 17:18:11 -06:00
Alex Verkhovsky 8b13628496 fix: add Use if trigger to advanced-elicitation description
Clears the SKILL-06 validator finding for missing trigger phrase.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 16:46:43 -06:00
Alex Verkhovsky 642b6a0cf4 ci: add validate:skills to GitHub quality workflow
The deterministic skill validator was in the npm quality chain but
missing from the GitHub Actions workflow.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 14:38:09 -06:00
Alex Verkhovsky fd1e24c5c2 fix: address PR review findings in skill validator
- Guard against YAML comment lines in parseFrontmatterMultiline
- Broaden PATH-02 to detect any installed_path mention, not just variable refs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 14:35:52 -06:00
Alex Verkhovsky 84bade9a95
Merge branch 'main' into feat-deterministic-skill-validator 2026-03-18 10:13:59 -06:00
Alex Verkhovsky 4f1894908c refactor: tighten SKILL-04 regex, broaden WF-01/WF-02, remove forbidden names
- SKILL-04: require bmad- prefix, enforce single dashes via regex
  ^bmad-[a-z0-9]+(-[a-z0-9]+)*$, drop FORBIDDEN_NAME_SUBSTRINGS
- WF-01/WF-02: check all .md files (not just workflow.md) for stray
  name/description frontmatter, with tech-writer exception
- Update skill-validator.md prompt to match all rule changes

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 08:02:01 -06:00
Alex Verkhovsky 7a214cc7d8 fix: tighten frontmatter parsing and add SKILL-07 body content check
- Require \n---\n (not just \n---) for closing frontmatter delimiter
  in both parseFrontmatter and parseFrontmatterMultiline, with fallback
  for files ending in \n---
- Add SKILL-07: SKILL.md must have non-empty body content after
  frontmatter (L2 instructions are required)
- Update rule count to 14

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 08:02:01 -06:00
Alex Verkhovsky ac5cb552c0 refactor: discover skills by walking src instead of hardcoded paths
Replace SKILL_LOCATIONS array and AGENT_LOCATION constant with a single
walk from SRC_DIR. Any directory under src/ containing SKILL.md is a
skill — no need to enumerate locations.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 08:02:00 -06:00
Alex Verkhovsky be555aad8b
Merge pull request #2049 from bmad-code-org/fix-clickable-spec-link-convention
feat(quick-dev): clickable spec link at step-02 checkpoint and CWD-relative path convention
2026-03-18 00:13:04 -06:00
Alex Verkhovsky 22035ef015
Merge branch 'main' into feat-deterministic-skill-validator 2026-03-18 00:11:46 -06:00
Alex Verkhovsky f0e43f02e2 feat(quick-dev): add clickable spec link at step-02 checkpoint and CWD-relative path convention
Step-02 now displays the finalized spec file path as a CWD-relative
clickable link after approval. Step-05 clarifies the dual convention:
project-root-relative paths (leading /) for spec-file content, CWD-relative
paths (no leading /) for terminal/conversation output. One-shot review
order explicitly uses CWD-relative path:line format.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 00:09:25 -06:00
Brian 0380656de6
refactor: consolidate agents into phase-based skill directories (#2050)
* refactor: consolidate agents into phase-based skill directories

Remove separate agent/workflow/skill directories (src/bmm/agents,
src/bmm/workflows, src/core/skills, src/utility/agent-components) and
reorganize all content into phase-based structures under src/bmm-skills
(1-analysis, 2-plan-workflows, 3-solutioning, 4-implementation) and
src/core-skills. Eliminates the agent/skill distinction by treating
agents as skills within their workflow phase.

* fix: update broken file references to use new bmm-skills paths

* docs: update all references for unified bmad-quick-dev workflow

Remove all references to the old separate bmad-quick-spec and
bmad-quick-dev-new-preview workflows. The new bmad-quick-dev is a
unified workflow that handles intent clarification, planning,
implementation, review, and presentation in a single run.

Updated files across English docs, Chinese translations, source
skill manifests, website diagram, and build tooling.
2026-03-18 01:01:33 -05:00
Alex Verkhovsky 5a1f356e2c feat(tools): add deterministic skill validator for CI
Add tools/validate-skills.js — a Node CLI that checks 13 deterministic
rules (SKILL-01–06, WF-01–02, PATH-02, STEP-01/06/07, SEQ-02) across
all skill directories. Runs in under a second, exits non-zero on HIGH+
findings in strict mode, and outputs JSON for the inference validator.

- Add validate:skills npm script to quality chain
- Update skill-validator.md with first-pass integration instructions
- Update AGENTS.md push gate documentation

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 23:49:01 -06:00
Alex Verkhovsky 21c2a48ab2
Merge pull request #2048 from bmad-code-org/chore-remove-agent-schema
chore: remove dead agent schema validation infrastructure
2026-03-17 20:51:43 -06:00
Alex Verkhovsky ebbc6d2a33
Merge branch 'main' into chore-remove-agent-schema 2026-03-17 20:41:12 -06:00
Alex Verkhovsky f0c7cf41c7 chore: remove dead agent schema validation infrastructure
The *.agent.yaml format was replaced by SKILL.md-based agents.
Zero agent YAML files remain in src/, so remove the Zod schema,
validator CLI, fixture-based test suite (52 fixtures), unit tests,
CLI integration tests, and the CI steps that invoked them.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 20:20:12 -06:00
Brian 0580164bdc
fix: restore bmad-create-prd task to workflows directory (#2047)
Moves bmad-create-prd from src/core/tasks/ to
src/bmm/workflows/2-plan-workflows/ to align with current project structure.
2026-03-17 21:18:45 -05:00
Alex Verkhovsky 72f6963253
Merge pull request #2045 from bmad-code-org/fix-quick-dev-workflow-preamble
fix(quick-dev): replace role statement with step-following mandate
2026-03-17 19:56:06 -06:00
Alex Verkhovsky 3bae0cba6a
Merge branch 'main' into fix-quick-dev-workflow-preamble 2026-03-17 19:48:16 -06:00
Alex Verkhovsky e84874e9f0
Merge pull request #2044 from bmad-code-org/fix/oneshot-step-separation
refactor(quick-flow): separate one-shot into self-contained step file
2026-03-17 19:47:33 -06:00
Alex Verkhovsky fcd0873d22 fix(quick-flow): address review findings on step files
- Remove name/description from step-03-implement.md frontmatter (STEP-06)
- Remove name/description from step-oneshot.md frontmatter (STEP-06)
- Fix {project_root} to {project-root} placeholder convention
- Replace undefined {changed_files} with natural language

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 19:18:39 -06:00
Alex Verkhovsky 96091cb74d fix(quick-dev): replace role statement with step-following mandate
The "elite developer" role with "implement autonomously" and "minimum
ceremony" language actively encouraged the model to skip workflow steps
when it judged the task was simple enough. Replaced with a concrete goal
and a critical rule enforcing step-file compliance.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 18:51:36 -06:00
Alex Verkhovsky 93d03e5f80 refactor(quick-flow): separate one-shot into self-contained step file
One-shot and plan-code-review shared steps 3-5 which depend on spec
files one-shot never creates. Give one-shot its own step-oneshot.md
with implement/review/classify/commit/present. Clean all one-shot
and execution_mode references from steps 3-5. Restructure step-01
routing with EARLY EXIT pattern for one-shot and artifact-scan resume.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 16:45:32 -06:00
Alex Verkhovsky f3f606a9ce
Merge pull request #2042 from bmad-code-org/feat/coderabbit-docs-check
feat(coderabbit): add docs-staleness check for src/ changes
2026-03-17 15:37:25 -06:00
Alex Verkhovsky 9636e86b75 feat(coderabbit): add docs-staleness check for all src/ changes
Adds a path_instructions entry so CodeRabbit flags when documentation
under docs/ may need updating whenever source files are modified.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 15:30:32 -06:00
Alex Verkhovsky 88aa53506a
Merge pull request #2039 from bmad-code-org/feat/vscode-opening-ergonomics
feat(quick-dev): add VS Code opening ergonomics to step 5
2026-03-17 09:59:09 -06:00
Alex Verkhovsky 653c3ae152 fix(quick-dev): scope editor open and summary to plan-code-review only
One-shot mode displays the review order in conversation output and has
no spec file to open. Guard the code -r step and spec-specific summary
items behind plan-code-review.
2026-03-17 09:53:34 -06:00
Alex Verkhovsky 39359ddbcd fix(quick-dev): quote spec file path in code -r command
Ensure paths with spaces or special characters are handled correctly
by double-quoting the {spec_file} variable in the editor open command.
2026-03-17 09:52:48 -06:00
Alex Verkhovsky f036c21d13 feat(quick-dev): add VS Code opening ergonomics to step 5
Replace vscode://file/ absolute URI links with workspace-root-relative
markdown links using #L anchors — portable across machines and worktrees.
Add code -r open-in-editor step with graceful fallback, and Ctrl+click
navigation tip for reviewers.
2026-03-17 09:10:38 -06:00
Alex Verkhovsky cc300b3940
Merge pull request #2033 from bmad-code-org/feat/review-trail-generation
feat(quick-dev): add Review Trail generation to step 5
2026-03-17 07:52:45 -06:00
Alex Verkhovsky 6de6f45086 feat(quick-dev): add Review Trail generation to step 5
Step 5 now builds a concern-ordered trail of clickable vscode://file/
links with brief framing and appends it to the spec before committing.
Stops are sequenced by concern (not by file), lead with the entry point,
and use ≤15-word framing focused on design rationale. Single-concern
trails omit grouping labels. The trail is a standalone review artifact
useful without any skill.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 07:51:58 -06:00
Brian a1418dfd28
chore(agents): cleanup skill manifests and remove shared manifest (#2035)
Update per-agent bmad-skill-manifest.yaml files and remove the
now-redundant shared bmad-skill-manifest.yaml after capabilities
were inlined into SKILL.md.
2026-03-16 22:50:47 -05:00
Brian e5062a8bbb
refactor(agents): inline capabilities into SKILL.md, remove bmad-manifest.json (#2029)
Replace dynamic manifest loading with static Capabilities tables directly
in each agent's SKILL.md. This eliminates the bmad-manifest.json files and
simplifies agent activation by removing the manifest parsing step.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 13:11:04 -05:00
Alex Verkhovsky 21123d6349
Merge pull request #2026 from bmad-code-org/chore/remove-dead-party-csv
chore(teams): remove dead party roster files
2026-03-16 10:28:06 -06:00
Alex Verkhovsky f6c2854ed9
Merge branch 'main' into chore/remove-dead-party-csv 2026-03-16 10:23:07 -06:00
Alex Verkhovsky b8388ff227 chore(teams): remove dead party roster files
default-party.csv and team-fullstack.yaml are never read by any code.
Party mode reads from the installed agent-manifest.csv generated by
manifest-generator.js during install.
2026-03-16 09:28:25 -06:00
Alex Verkhovsky 80604b45fe
Merge pull request #2025 from bmad-code-org/flatten-quick-dev-steps
refactor(skill): flatten quick-dev-new-preview step files
2026-03-16 08:21:52 -06:00
Alex Verkhovsky bce72fe18d
Merge branch 'main' into flatten-quick-dev-steps 2026-03-16 08:21:04 -06:00
Alex Verkhovsky 6742b1ff7b
Merge pull request #2022 from bmad-code-org/chore/coderabbit-default-profile
chore(review): replace adversarial CodeRabbit with skill-validator refs
2026-03-16 08:20:07 -06:00
Alex Verkhovsky e21d6b36ae
Merge branch 'main' into chore/coderabbit-default-profile 2026-03-16 08:16:11 -06:00
Alex Verkhovsky cad25817eb refactor(skill): flatten quick-dev-new-preview step files to skill root
Move step files from steps/ subdirectory to the skill root directory
and update path references in workflow.md and step-02-plan.md.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 08:10:47 -06:00
Alex Verkhovsky aa2a9a2818
Merge pull request #1968 from meysholdt/feat/add-ona-platform-support
feat: add Ona as a supported platform
2026-03-16 07:48:46 -06:00
Alex Verkhovsky be6611570a
Merge branch 'main' into feat/add-ona-platform-support 2026-03-16 07:26:53 -06:00
Alex Verkhovsky 28954fea79 chore(review): replace adversarial CodeRabbit with skill-validator refs
Remove the cynical adversarial reviewer persona from .coderabbit.yaml
and replace with per-path instructions that reference
tools/skill-validator.md as the single source of truth — matching the
approach already used in .augment/code_review_guidelines.yaml.

Add skill-validator pointer to AGENTS.md so all AI tools can discover it.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 05:39:57 -06:00
Brian bed9052d49
Feat/conformant agent skills (#2021)
* feat(agents): convert all BMM agents to conformant skill structure

Replace legacy XML-based .agent.yaml files with new SKILL.md + bmad-manifest.json
format for all 9 BMM agents (analyst, architect, dev, pm, qa, sm,
quick-flow-solo-dev, ux-designer, tech-writer). Each agent now has:

- SKILL.md with persona, activation flow (bmad-init, project context, dynamic menu)
- bmad-manifest.json with capabilities referencing external skills
- bmad-skill-manifest.yaml for party-mode agent-manifest.csv generation

Tech-writer includes internal prompt files for write-document, mermaid-gen,
validate-doc, and explain-concept capabilities.

Also includes core bmad-init skill and removes legacy agent compilation tests
that referenced the old .agent.yaml format.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(installer): support new SKILL.md agent format in manifest generation

Update getAgentsFromDir to detect directories with bmad-skill-manifest.yaml
where type=agent and extract metadata directly from the YAML fields. This
allows the agent-manifest.csv to be populated from both old-format compiled
.md agents (XML parsing) and new-format SKILL.md agents (YAML manifest).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(installer): install type:agent skills to IDE native skills directory

The collectSkills scanner only recognized type:skill manifests, causing
new-format agents (type:agent in bmad-skill-manifest.yaml) to be added
to agent-manifest.csv but not installed to .claude/skills/. Now both
type:skill and type:agent are recognized as installable skills, while
collectAgents still processes type:agent dirs for the agent manifest
even when claimed by the skill scanner.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(installer): suppress canonicalId warning for type:agent skills

Agent-type skill manifests legitimately use canonicalId for agent-manifest
mapping (e.g., bmad-analyst). Only warn for regular type:skill manifests.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(skills): update analyst manifest and simplify bmad-init instructions

Switch analyst's create-brief menu entry to the new product-brief-preview
skill. Simplify bmad-init SKILL.md by removing hardcoded code fences and
making the script path relative to the skill directory.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(bmm): update tech-writer CSV refs to new skill path

The module-help.csv still referenced the old agent YAML path for
tech-writer entries. Update to skill:bmad-agent-tech-writer to match
the conformant skill structure.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 00:47:30 -05:00
Alex Verkhovsky ba0c59128d
Merge pull request #2017 from YeJianXin/main
add Qoder code agent support
2026-03-15 20:47:32 -06:00
Alex Verkhovsky 8e8432e138
Merge branch 'main' into main 2026-03-15 20:45:41 -06:00
Alex Verkhovsky 2f4c9ca879
Merge pull request #2016 from bmad-code-org/chore/augment-skill-validator-update
chore(tools): align Augment config with skill-validator
2026-03-15 20:34:15 -06:00
Alex Verkhovsky ebe490a505
Merge branch 'main' into chore/augment-skill-validator-update 2026-03-15 20:33:33 -06:00
Alex Verkhovsky 6dc9ce0090 chore(tools): remove Claude Code-specific sections from skill cheatsheet
Keep cheatsheet focused on the Agent Skills open standard only.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 18:30:39 -06:00
Alex Verkhovsky 0bf6cb3380
Merge pull request #2015 from bmad-code-org/ci/quality-on-push-to-main
ci: run quality checks on pushes to main
2026-03-15 18:22:48 -06:00
JasonYe d42de639bc add Qoder code agent support 2026-03-16 08:18:02 +08:00
Alex Verkhovsky 082abc1a17 ci: run quality checks on pushes to main
Previously the quality workflow only triggered on pull_request events,
so direct pushes to main (including merged PRs) skipped all CI checks.
Add a push trigger for the main branch so broken builds are caught.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 18:15:05 -06:00
Alex Verkhovsky 07f1a44c5c chore(tools): align Augment config with skill-validator as single source of truth
Replace duplicated workflow-era rules in .augment/code_review_guidelines.yaml
with a single reference to tools/skill-validator.md. Append the skill spec
cheatsheet to the validator with a link to the Agent Skills specification.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 17:41:54 -06:00
github-actions[bot] d1163f85e1 chore(release): v6.2.0 [skip ci] 2026-03-15 22:33:14 +00:00
Brian Madison cbb9a2a0c9 Change log for 6.2 2026-03-15 17:31:32 -05:00
Alex Verkhovsky 45d125f3b5
fix(skills): address code-review findings from PR #2007 review (#2013)
- Remove name/description from step frontmatter (STEP-06)
- Add explicit HALT before user menu in step-01 (STEP-04)
- Escape story-id as template placeholder (REF-01)
- Handle untracked files in file-list diff mode (P-6)
- Formalize failed_layers variable handoff between steps (P-5)
- Add Acceptance Auditor skip note for no-spec mode (P-4)
- Guard false-clean when review layer failed (P-7)
- Reword patch recommendation to avoid auto-fix solicitation (P-3)
- Update SKILL.md description to reflect new capabilities (P-2)
2026-03-15 16:49:20 -05:00
Alex Verkhovsky ce23cb5d5a
fix(skill): improve bmad-help description for accurate trigger matching (#2012)
Refined through adversarial review to accurately reflect the skills
state-analysis, question-answering, and workflow-recommendation
capabilities with precise trigger phrases that avoid false positives.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 16:48:33 -05:00
梁山河 fdad19ebd7
fix(i18n): point zh-cn doc links to Chinese pages instead of English (#2010)
将 README_CN.md 和 docs/zh-cn/ 中指向英文页面的链接替换为对应的中文版本,
对无中文版的外部链接添加(英文)标注,修正链接文字与目标不匹配的问题,
移除 project-context.md 中的自引用链接。

Fixes #1978

Co-authored-by: leon <leon.liang@hairobotics.com>
2026-03-15 16:47:52 -05:00
Alex Verkhovsky 09bca114e5
Merge pull request #2007 from bmad-code-org/feat/code-review-rewrite
feat(skills): rewrite code-review with sharded step-file architecture
2026-03-15 15:17:44 -06:00
Alex Verkhovsky 6a91eb6855 feat(skills): auto-detect review intent from invocation args
Skip the interactive "What do you want to review?" menu when the user
already stated review mode in the invocation (e.g., "review staged
changes"). Adds keyword matching, sprint-tracking fallback, and
graceful fall-through to the existing interactive flow.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 15:14:31 -06:00
Alex Verkhovsky f12e38e003
Merge branch 'main' into feat/code-review-rewrite 2026-03-15 15:10:39 -06:00
Alex Verkhovsky 17cd19f07b fix(skills): apply triage fixes to code-review step files
Address findings from adversarial review: clarify spec_file as path
variable (F4), add file list construction rule (F8), HALT on unparseable
diffs (F9), differentiate empty findings handling (F5), merge evidence
during dedup instead of dropping (F6), and fix NEXT step paths (F1).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 15:08:13 -06:00
Alex Verkhovsky 4404b4bc9a
Merge pull request #2008 from bmad-code-org/feat-validation-pass-2
fix(skills): validation pass 2 — path, variable, and sequence fixes
2026-03-15 14:50:55 -06:00
Alex Verkhovsky 8efc8c309c fix(skills): restore full CSV column list in brainstorming steps
The CSV parse instructions were incorrectly truncated to 3 columns.
Restore all 7: category, technique_name, description,
facilitation_prompts, best_for, energy_level, typical_duration.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 14:49:36 -06:00
Alex Verkhovsky 4937ce1bc2 fix(skills): revert out-of-scope changes from validation pass
- Revert step renumbering in retrospective (no validator rule)
- Revert full-scan-instructions, quick-dev-preview, quick-spec changes
- Restore duration/energy/time content in brainstorming steps 02a-d, 03
  (SEQ-02 time estimate removal was misapplied to display templates)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 14:46:05 -06:00
Alex Verkhovsky ac994d683d fix(skills): revert unnecessary rewording and misapplied REF-01 fixes
- Revert SKILL.md wording change in product-brief-preview (not a
  validation issue)
- Revert single-curly to double-curly conversions in create-architecture
  and create-epics-and-stories where the originals were display
  placeholders for LLM output, not template variables

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 14:06:06 -06:00
Alex Verkhovsky 1397c8f44a fix(skills): revert scope-creep menu changes in edit-prd step-e-03
Restore original menu options [V], [S], [A], [X] that were incorrectly
replaced with [C], [A] during validation pass. The menu reduction was
not covered by any validation rule.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 11:47:34 -06:00
Alex Verkhovsky 1558a68a0a fix(skills): add missing ./ prefix to bare step file references
Bare filenames like `step-e-02-review.md` in "Read fully and follow:"
directives need `./` prefix for consistent relative path resolution.
Fixes 9 references across edit-prd, create-prd, and brainstorming.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 11:42:12 -06:00
Alex Verkhovsky cb16a4fac2 fix(skills): strip redundant [workflow.md](workflow.md) links repo-wide
Replace `[workflow.md](workflow.md)` with bare `workflow.md` in all 34
SKILL.md files. Redundant markdown link syntax adds noise for LLM
consumers. Also update the validator example to match.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 11:24:57 -06:00
Alex Verkhovsky de565221d8 fix(skills): strip redundant markdown links in edit-prd step references
Bare filenames are cleaner than [file.md](file.md) for LLM-consumed
skill files — the markdown link wrapper adds nothing when display text
and URL are identical.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 11:22:38 -06:00
Alex Verkhovsky 6ee4062e56 fix(skills): add remaining HALT instructions in brainstorming menus
STEP-04 compliance: add HALT directives to 5 additional menu locations
in brainstorming steps (01b, 02a, 02b, 02c, 02d). Also fixes bracket
typo [3 -> [3] in step-01b-continue.md.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
EOF
)
2026-03-15 11:13:57 -06:00
Alex Verkhovsky 75292af47c fix(skills): add missing HALT instructions before user menus
STEP-04 compliance: add explicit HALT directives after menu presentations
in brainstorming (4 locations) and generate-project-context (2 locations)
to prevent LLM from auto-selecting options without waiting for user input.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 10:58:16 -06:00
Alex Verkhovsky a2f4bfea8f fix(skills): address re-validation findings in edit-prd, validate-prd, brainstorming
- STEP-06: Remove name/description from step frontmatter in edit-prd (5 files)
  and validate-prd (14 files) — these belong only in SKILL.md
- REF-02: Fix brainstorming step-02a/b/c/d CSV parse instructions to match
  actual brain-methods.csv columns (3 cols, not 7)
- SEQ-02: Remove time estimates from brainstorming step-02a/b/c/d and step-03,
  replace time-based thresholds with idea-count criteria

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 10:53:47 -06:00
Alex Verkhovsky 098c96740c fix(skills): validation pass 2 — fix path, variable, and sequence issues across 32 files
Run skill-validator against all 36 skills on HEAD (42b1d0f6). Fixes:

- PATH-01: relative path corrections in product-brief-preview, brainstorming,
  distillator, generate-project-context, edit-prd, quick-dev-new-preview
- PATH-04: remove 5 intra-skill path variables from edit-prd
- REF-01: single-curly template vars → double-curly in create-architecture,
  create-epics-and-stories, create-story
- REF-02: fix dangling file refs in advanced-elicitation, validate-prd, edit-prd
- REF-03: update rule to prefer natural language `Invoke the skill` form;
  fix stale persona ref in qa-generate-e2e-tests
- SEQ-01: "skip to" → "proceed to" in quick-dev-new-preview
- SEQ-02: remove time estimates from document-project, quick-spec
- SKILL-06: add "Use when" trigger to review-edge-case-hunter
- STEP numbering: renumber step n="0.5" to integer sequence in retrospective

Also updates REF-03 rule in tools/skill-validator.md to clarify that
natural language invocation is canonical — no skill: prefix required.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 10:38:43 -06:00
Alex Verkhovsky 5de8a78c6a feat(skills): rewrite code-review skill with sharded step-file architecture
Replace monolithic XML-step workflow with 4 sharded step files:
- step-01: gather context (diff source, spec, chunking)
- step-02: parallel review (blind hunter, edge case, acceptance auditor)
- step-03: triage (normalize, deduplicate, classify into 5 buckets)
- step-04: present (categorized findings with recommendations)

Key changes:
- Three parallel review layers via subagent invocation
- Structured triage with intent_gap/bad_spec/patch/defer/reject categories
- Works with or without a spec file
- Loopbacks are recommendations, not automated re-runs
- Remove checklist.md (superseded by triage step)
- Remove discover-inputs.md (no longer referenced)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 09:23:42 -06:00
Alex Verkhovsky 42b1d0f657
Merge pull request #2004 from bmad-code-org/normalize-skill-invocation-syntax
chore: normalize skill invocation syntax
2026-03-15 08:15:28 -06:00
Alex Verkhovsky 1ec0d8ba43 chore: normalize skill invocation syntax to `Invoke the skill` pattern
Replace three inconsistent skill reference patterns (frontmatter variables
with raw paths, frontmatter variables with skill: prefix, inline Execute
skill: syntax) with a single natural-language convention across all workflow
and task step files.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 07:59:30 -06:00
Alex Verkhovsky 2a3708fd32
Merge branch 'main' into feat/add-ona-platform-support 2026-03-15 07:39:13 -06:00
Alex Verkhovsky e794a81ee2 feat(tools): add REF-03 skill invocation language rule to validator
Skills must be invoked with "invoke" language, not file-oriented verbs
like "read fully and follow", "execute", "run", or "load". These imply
document-level operations and are incorrect for skill references.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 06:40:10 -06:00
Alex Verkhovsky 2aa5cddbe6
Merge branch 'main' into feat/add-ona-platform-support 2026-03-15 06:35:23 -06:00
Alex Verkhovsky 67232c11cc
Merge pull request #2002 from lrliang/docs/zh-cn-core-tools
docs(zh-cn): add Chinese translation for core-tools reference
2026-03-15 06:22:52 -06:00
Alex Verkhovsky 2622b5d094
Merge branch 'main' into docs/zh-cn-core-tools 2026-03-15 06:15:48 -06:00
Alex Verkhovsky 71c6d5c924
Merge pull request #2000 from bmad-code-org/fix/broken-party-mode-refs
fix: replace broken party-mode workflow refs with skill syntax
2026-03-15 02:48:30 -06:00
Alex Verkhovsky 4bfb076724
Merge branch 'main' into fix/broken-party-mode-refs 2026-03-15 02:47:16 -06:00
leon f5813f26f2 docs(zh-cn): add Chinese translation for core-tools reference
翻译 docs/reference/core-tools.md,覆盖全部 11 个核心工具的说明。
保留技能命令名和参数名不译,描述性内容使用自然中文表达。

Made-with: Cursor
2026-03-15 16:43:08 +08:00
Alex Verkhovsky 02cfaf64a4 feat(tools): add PATH-05 skill encapsulation rule to validator
Add PATH-05: no file path references into another skill directory.
Skills are encapsulated — external consumers must use skill:name syntax,
not reach into internal files. Also tighten WF-03 to cross-reference
PATH-05 so vague "legitimate external path" no longer permits
cross-skill file paths.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 02:26:01 -06:00
Alex Verkhovsky a98bf008fc fix: replace broken party-mode workflow refs with skill syntax
Party-mode moved from core/workflows/ to core/skills/ in PR #1959,
breaking 11 file references. Convert all to skill:bmad-party-mode
matching the convention used by skill:bmad-advanced-elicitation.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 02:03:46 -06:00
Alex Verkhovsky fa9c10ec05
Merge pull request #1920 from MenglongFan/docs/translate-quick-dev-preview
docs(zh-cn): add translation for quick-dev-new-preview
2026-03-15 01:34:53 -06:00
Alex Verkhovsky d8ab6efa1f
Merge branch 'main' into docs/translate-quick-dev-preview 2026-03-15 01:33:30 -06:00
Brian cbb8b98876
manifest generate will no longer fail when module has no agents and its first (#1998) 2026-03-15 01:46:16 -05:00
Brian 9fa51d996b
prototype preview of new version of product brief skill (#1959)
* prototype preview of new version of product brief skill

* chore: re-enable bmad-builder external module

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* config loading with existing location

* refactor: rename bmad-bmm-product-brief-preview to bmad-product-brief-preview

Drop the redundant bmm prefix from the product brief preview skill folder
to align with the standard naming convention.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: add core tools reference and apply Diataxis style fixes

Add comprehensive reference doc for all 11 built-in core tools (tasks
and workflows) that ship with every BMad installation — bmad-help,
brainstorming, party-mode, distillator, advanced-elicitation, both
review tools, both editorial tools, shard-doc, and index-docs. Each
entry follows the Configuration Reference structure with purpose,
use cases, how it works, inputs, and outputs.

Style fixes across existing docs:
- reference/commands.md: convert #### headers to bold text, replace
  sparse task table with link to new core-tools reference
- how-to/get-answers-about-bmad.md: remove horizontal rule between
  sections (Diataxis violation)
- how-to/project-context.md: consolidate 4 consecutive tip admonitions
  into single admonition with bullet list, add AGENTS.md reference

Also includes:
- Add bmad-distillator task to core module with compression agents,
  format reference, splitting strategy, and analysis scripts
- Add Distillator entry to module-help.csv
- Rename supports-autonomous to supports-headless in product-brief
  manifest

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* core items to skills folder

* fix calls to invoke party mode

* fix calls to invoke party mode and AE as skills

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 00:05:53 -05:00
Alex Verkhovsky ccfd818ebd
Merge pull request #1994 from bmad-code-org/convert-market-research-skill
refactor(skills): convert market-research to native skill directory
2026-03-14 20:49:32 -06:00
Alex Verkhovsky a6fdf4349f fix: remove obsolete workflow-market-research.md superseded by skill
The market-research workflow now lives entirely in
bmad-market-research/ as a native skill directory.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 20:23:12 -06:00
Alex Verkhovsky da4426237e fix: resolve skill validation findings in market-research
- Add co-located HALT instructions after every menu in all 6 step files
- Fix step-05 to route to step-06 instead of declaring workflow complete
- Rename market-steps/ to steps/ for standard naming convention

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 20:11:09 -06:00
Alex Verkhovsky f076957807 fix: remove leftover empty frontmatter from market-research workflow
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 20:05:47 -06:00
Alex Verkhovsky 5a06b56eaa
Merge branch 'main' into convert-market-research-skill 2026-03-14 20:00:04 -06:00
Alex Verkhovsky 7f0ffb54c0
Merge pull request #1988 from bmad-code-org/convert-validate-prd-skill
refactor(skills): convert validate-prd to native skill directory
2026-03-14 19:59:27 -06:00
Alex Verkhovsky a136713dc9 refactor(skills): convert validate-prd to native skill directory
Move validate-prd from a workflow entry in create-prd manifest to a
self-contained skill at src/bmm/workflows/2-plan-workflows/bmad-validate-prd/.
Update pm.agent.yaml and module-help.csv to use skill: URI.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 18:54:42 -06:00
Alex Verkhovsky 1dd6668a0d
Merge pull request #1984 from bmad-code-org/convert-create-prd-skill
refactor(skills): convert create-prd to native skill directory
2026-03-14 18:49:09 -06:00
Alex Verkhovsky 87f47625da refactor(skills): convert market-research to native skill directory
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 17:23:04 -06:00
Alex Verkhovsky b42f1e732a fix(skill): clean up bmad-create-prd validation findings
Strip name/description from all step frontmatter (STEP-06), remove
intra-skill path variables and inline them (PATH-04), move outputFile
to workflow.md (WF-03), fix stale step-11-complete refs (REF-02),
fix product_knowledge typo (REF-01), rewrite continuation logic
to use a lookup table, and strip legacy source workflow frontmatter.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 17:22:40 -06:00
Alex Verkhovsky 9f8f7f4a3e refactor(skills): convert create-prd to native skill directory
Move the create-prd workflow into src/core/tasks/bmad-create-prd/ as a
self-contained native skill with SKILL.md, workflow.md, steps-c/, data/,
and templates/. Update all internal path references from absolute
{project-root}/_bmad/... to relative paths. Mark the source
workflow-create-prd.md as standalone:false to prevent duplicate manifest
entries. Update pm.agent.yaml and module-help.csv to use skill:bmad-create-prd.
2026-03-14 17:21:11 -06:00
Alex Verkhovsky 6c83482513
Merge pull request #1997 from bmad-code-org/fix/quickflow-skill-validation-cleanup
fix(skill): validation cleanup for quick-flow skills
2026-03-14 17:07:45 -06:00
Alex Verkhovsky 5c24754627
Merge branch 'main' into fix/quickflow-skill-validation-cleanup 2026-03-14 17:06:28 -06:00
Alex Verkhovsky fe86785dbf
Merge pull request #1996 from bmad-code-org/fix/routine-skill-validation-cleanup
fix(skill): batch validation cleanup for 6 skills
2026-03-14 17:06:06 -06:00
Alex Verkhovsky 0efe81faec
Merge branch 'main' into fix/routine-skill-validation-cleanup 2026-03-14 17:05:27 -06:00
Alex Verkhovsky b1209a97da fix(skill): validation cleanup for quick-flow skills
bmad-quick-dev-new-preview: fix wrong step-to-step path references
from within steps/ directory, remove step frontmatter metadata and
intra-skill path variables.

bmad-quick-dev: remove step frontmatter metadata, inline nextStepFile
path variables as literal relative paths.

bmad-quick-spec: remove name/description from workflow.md frontmatter,
fix absolute self-references using {project-root} for intra-skill
paths, remove step frontmatter metadata.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 17:02:08 -06:00
Alex Verkhovsky 73e5552aad fix(skill): batch validation cleanup for 6 skills
Remove installed_path definitions, unused intra-skill path variables,
and inline variable references across: bmad-sprint-status,
bmad-document-project, bmad-generate-project-context,
bmad-qa-generate-e2e-tests, bmad-advanced-elicitation, and
bmad-brainstorming.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 17:02:04 -06:00
Alex Verkhovsky f7cd62acba
Merge pull request #1995 from bmad-code-org/fix/sprint-planning-skill-cleanup
fix(skill): clean up bmad-sprint-planning validation findings
2026-03-14 16:51:10 -06:00
Alex Verkhovsky 9976f06e46
Merge branch 'main' into fix/sprint-planning-skill-cleanup 2026-03-14 16:45:14 -06:00
Alex Verkhovsky 1338e4852d
Merge pull request #1993 from bmad-code-org/fix/retrospective-skill-cleanup
fix(skill): clean up bmad-retrospective validation findings
2026-03-14 16:44:45 -06:00
Alex Verkhovsky 6c259bbbc5
Merge pull request #1992 from bmad-code-org/fix/dev-story-skill-cleanup
fix(skill): clean up bmad-dev-story validation findings
2026-03-14 16:44:25 -06:00
Alex Verkhovsky f15b2d129f fix(skill): clean up bmad-sprint-planning validation findings
Remove installed_path and unused intra-skill path variables from
workflow.md (PATH-02, PATH-04).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:43:19 -06:00
Alex Verkhovsky f04a1ba8d8
Merge branch 'main' into fix/dev-story-skill-cleanup 2026-03-14 16:41:20 -06:00
Alex Verkhovsky b9b135573d
Merge pull request #1991 from bmad-code-org/fix/create-story-skill-cleanup
fix(skill): clean up bmad-create-story validation findings
2026-03-14 16:39:51 -06:00
Alex Verkhovsky 709b4e8fc9 fix(skill): clean up bmad-retrospective validation findings
Remove unused installed_path from workflow.md (PATH-02).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:39:33 -06:00
Alex Verkhovsky 930b5fd7ea
Merge branch 'main' into fix/dev-story-skill-cleanup 2026-03-14 16:37:46 -06:00
Alex Verkhovsky 6721904adb fix(skill): clean up bmad-dev-story validation findings
Remove unused intra-skill path variable from workflow.md (PATH-04).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:36:35 -06:00
Alex Verkhovsky 74391d712b
Merge branch 'main' into fix/create-story-skill-cleanup 2026-03-14 16:35:22 -06:00
Alex Verkhovsky 93a808a3d6 fix(skill): clean up bmad-create-story validation findings
Remove installed_path and intra-skill path variables from
workflow.md (PATH-02, PATH-04).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:33:40 -06:00
Alex Verkhovsky 54d097c8ca
Merge pull request #1990 from bmad-code-org/fix/code-review-skill-cleanup
fix(skill): clean up bmad-code-review validation findings
2026-03-14 16:33:08 -06:00
Alex Verkhovsky fb4d9169a6
Merge branch 'main' into fix/code-review-skill-cleanup 2026-03-14 16:32:08 -06:00
Alex Verkhovsky 71630bc4e9
Merge pull request #1989 from bmad-code-org/fix/create-epics-stories-skill-cleanup
fix(skill): clean up bmad-create-epics-and-stories validation findings
2026-03-14 16:31:37 -06:00
Alex Verkhovsky 211c7e38c3
Merge branch 'main' into fix/create-epics-stories-skill-cleanup 2026-03-14 16:30:15 -06:00
Alex Verkhovsky e0a56489f7
Merge pull request #1987 from bmad-code-org/fix/create-architecture-skill-cleanup
fix(skill): clean up bmad-create-architecture validation findings
2026-03-14 16:29:47 -06:00
Alex Verkhovsky 2d78e1d942
Merge branch 'main' into fix/create-epics-stories-skill-cleanup 2026-03-14 16:29:42 -06:00
Alex Verkhovsky 7e6c26cd04
Merge branch 'main' into fix/create-architecture-skill-cleanup 2026-03-14 16:28:57 -06:00
Alex Verkhovsky b3d0810042
Merge pull request #1981 from bmad-code-org/feat/skill-validator
feat(tools): add inference-based skill validator
2026-03-14 16:28:07 -06:00
Alex Verkhovsky df5c32e0dd fix(skill): clean up bmad-code-review validation findings
Remove installed_path definition and intra-skill path variables
from workflow.md (PATH-02, PATH-04).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:27:27 -06:00
Alex Verkhovsky d343fbe55f
Merge branch 'main' into feat/skill-validator 2026-03-14 16:27:24 -06:00
Alex Verkhovsky b0d4bf7e28
Merge pull request #1986 from bmad-code-org/fix/check-impl-readiness-skill-cleanup
fix(skill): clean up bmad-check-implementation-readiness validation findings
2026-03-14 16:26:41 -06:00
Alex Verkhovsky 9471c832d5
Merge branch 'main' into fix/check-impl-readiness-skill-cleanup 2026-03-14 16:26:02 -06:00
Alex Verkhovsky 2c23522d87 fix(skill): clean up bmad-create-epics-and-stories validation findings
Remove name/description from step frontmatter (STEP-06) and add
missing HALT before user menu in step-04-final-validation (STEP-04).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:24:30 -06:00
Alex Verkhovsky 089c19d7ab fix(skill): clean up bmad-create-architecture validation findings
Remove installed_path and intra-skill path variables (PATH-02, PATH-04),
prefix bare docs/** with {project-root} (PATH-03), fix misspelled
{product_knowledge} -> {project_knowledge} (REF-01).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:20:33 -06:00
Alex Verkhovsky b9926e1c4a fix(skill): clean up bmad-check-implementation-readiness validation findings
Remove name/description from step frontmatter (STEP-06) and inline
nextStepFile/templateFile path variables as literal relative paths
(PATH-04).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:16:34 -06:00
Alex Verkhovsky 304ef02427
Merge pull request #1985 from bmad-code-org/convert-edit-prd-skill
Convert bmad-edit-prd from type:workflow to native skill
2026-03-14 16:08:03 -06:00
Alex Verkhovsky 122ef9b43c
Merge pull request #1983 from bmad-code-org/fix/create-ux-design-skill-cleanup
fix(skill): clean up bmad-create-ux-design validation findings
2026-03-14 16:06:30 -06:00
Alex Verkhovsky 2b2b9201a7
Merge branch 'main' into fix/create-ux-design-skill-cleanup 2026-03-14 16:06:20 -06:00
Alex Verkhovsky 516557451a refactor: convert bmad-edit-prd from shared workflow to standalone skill
Move edit-prd workflow and steps-e/ out of the shared create-prd directory
into its own bmad-edit-prd skill directory with SKILL.md, workflow.md, and
bmad-skill-manifest.yaml. Update pm.agent.yaml and module-help.csv to use
skill:bmad-edit-prd. Fix validationWorkflow path in step-e-04 to use
absolute {project-root} reference since relative path breaks after move.
2026-03-14 16:05:57 -06:00
Alex Verkhovsky f3d6ee2cb8 fix(skill): clean up bmad-create-ux-design validation findings
Remove installed_path and intra-skill template_path variable (PATH-02,
PATH-04), prefix bare docs/** with {project-root} (PATH-03), inline
undefined variable references (REF-01), fix wrong config variable in
output path (REF-02).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 16:04:03 -06:00
Alex Verkhovsky 9d17cee2a8
Merge pull request #1982 from bmad-code-org/fix/product-brief-skill-cleanup
fix(skill): clean up bmad-create-product-brief validation findings
2026-03-14 16:03:19 -06:00
Alex Verkhovsky f4084ea199 feat(tools): add SKILL-05 name-matches-dir and REF-01 variable-defined rules
SKILL-05 checks that SKILL.md name matches the directory name.
REF-01 checks that every {variable} traces to frontmatter, config,
or runtime — exempts {{double-curly}} template placeholders.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 15:49:10 -06:00
Alex Verkhovsky b93d0087db fix(skill): clean up bmad-create-product-brief validation findings
Remove name/description from step frontmatter (STEP-06), inline
intra-skill path variables (PATH-04), prefix bare external path
with {project-root} (PATH-03), and normalize template placeholders
to double-curly convention (REF-01).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 15:49:07 -06:00
Alex Verkhovsky 6ff29d4707 feat(tools): add inference-based skill validator
LLM-readable validation prompt covering 19 rules across 6 categories:
SKILL.md frontmatter, workflow.md hygiene, path resolution, step file
structure, sequential execution, and file reference integrity. Designed
to catch anti-patterns from mechanical workflow-to-skill conversions
(installed_path abuse, intra-skill path variables, metadata in wrong
frontmatter).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 15:18:55 -06:00
Alex Verkhovsky 4cbbeb6602
Merge pull request #1946 from bmad-code-org/convert-quick-spec-skill
Convert quick-spec workflow to native skill package
2026-03-14 15:09:44 -06:00
Alex Verkhovsky 3678dbe3ff fix: correct relative step paths to resolve from originating file
Step files are inside steps/ so inter-step references must be
./step-NN.md not ./steps/step-NN.md (which would double-nest).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 14:58:21 -06:00
Alex Verkhovsky 40bb9abd31 fix: use skill: URI for quick-spec in agent menu
The agent menu entry for QS was still using a raw file path
instead of the skill dispatcher, inconsistent with module-help.csv.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 14:58:20 -06:00
Alex Verkhovsky d050711b07 feat(bmm): convert quick-spec workflow to native skill package 2026-03-14 14:58:20 -06:00
Alex Verkhovsky 7a0fe16251
Merge pull request #1950 from bmad-code-org/convert-generate-project-context-skill
Convert generate-project-context to native skill packaging
2026-03-14 14:56:53 -06:00
Alex Verkhovsky 1457e0b552 fix(bmm): remove workflow metadata from generate-project-context workflow
Move name/description to SKILL.md; workflow.md carries only execution content.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 14:55:16 -06:00
Alex Verkhovsky 2d64254ff6 fix(skill): remove workflow metadata from bmad-generate-project-context
Remove name/description frontmatter from workflow.md (belongs in SKILL.md).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 14:55:16 -06:00
Alex Verkhovsky e7f87af938 convert generate-project-context to native skill packaging 2026-03-14 14:55:16 -06:00
Alex Verkhovsky 8886805856
Merge pull request #1949 from bmad-code-org/convert-document-project-skill
chore(bmm): convert document-project to native skill packaging
2026-03-14 14:53:24 -06:00
Alex Verkhovsky 7ea11c2db9
Merge branch 'main' into convert-document-project-skill 2026-03-14 14:52:50 -06:00
Alex Verkhovsky f374f2e17d
Merge pull request #1931 from alexeyv/convert-technical-research-skill
refactor(skills): convert technical research to native skill
2026-03-14 14:51:51 -06:00
Alex Verkhovsky 76d5db5395
Merge branch 'main' into convert-technical-research-skill 2026-03-14 14:25:04 -06:00
Alex Verkhovsky 67f0501a67
Merge pull request #1945 from bmad-code-org/convert-sprint-status-skill
Convert sprint-status workflow to native skill packaging
2026-03-14 14:24:56 -06:00
Alex Verkhovsky c9658e0039
Merge branch 'main' into convert-technical-research-skill 2026-03-14 14:24:40 -06:00
Alex Verkhovsky 717e013f55 refactor(skills): convert technical research to native skill
Move technical-research workflow into bmad-technical-research/ skill
package with SKILL.md, bmad-skill-manifest.yaml, and properly
namespaced step files. Update module-help.csv to use skill: ref.
Remove duplicate technical-steps/ from old location and fix all
cross-references to use the new bmad-technical-research/ path.
2026-03-14 14:22:27 -06:00
Alex Verkhovsky aecead265f chore: remove sprint-status workflow metadata 2026-03-14 14:19:13 -06:00
Alex Verkhovsky a64e4de621 chore: convert sprint-status workflow to native skill 2026-03-14 14:19:13 -06:00
Alex Verkhovsky cc2a4142d4 chore(bmm): remove workflow metadata from document-project skill
Remove name/description frontmatter from workflow.md and sub-workflow
files (deep-dive-workflow.md, full-scan-workflow.md). Metadata belongs
exclusively in SKILL.md for native skill packages.
2026-03-14 14:18:51 -06:00
Alex Verkhovsky 6ce3801dff chore(bmm): convert document-project workflow to native skill package 2026-03-14 14:18:51 -06:00
Alex Verkhovsky 380a0af24b
Merge pull request #1922 from MenglongFan/fix/cn-docs-update-info
fix: update version hint and TEA module link in Chinese README
2026-03-14 13:45:37 -06:00
Alex Verkhovsky a0c58a1814
Merge pull request #1921 from MenglongFan/fix/cn-docs-https-links
fix: update HTTP links to HTTPS in Chinese README
2026-03-14 13:45:35 -06:00
Alex Verkhovsky b46f42ec1e
Merge branch 'main' into fix/cn-docs-https-links 2026-03-14 13:44:07 -06:00
Alex Verkhovsky a62e7a3c25
Convert qa-generate-e2e-tests workflow to native skill packaging (#1951)
* convert qa-generate-e2e-tests to native skill packaging

* fix(bmm): remove workflow metadata and normalize refs for qa-generate-e2e-tests

Remove name/description from workflow.md (belongs in SKILL.md).
Normalize installed_path to relative. Update QA agent exec to skill URI.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 13:38:42 -06:00
Alex Verkhovsky 74b53e13a7
Convert sprint-planning workflow to native skill packaging (#1944)
* chore: convert sprint-planning workflow to native skill

* fix(skills): normalize sprint planning native skill refs
2026-03-14 11:27:21 -06:00
Alex Verkhovsky 6a98b94949
Convert correct-course workflow to native skill packaging (#1942)
* chore: convert correct-course workflow to native skill

* fix(skill): patch correct-course native skill metadata

* fix(skill): inline hardcoded path variables in correct-course

Remove installed_path, checklist, and project_context variables that
just indirected single-use hardcoded paths. Use bare values inline.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 11:15:09 -06:00
Alex Verkhovsky 8dbc9b375d
Convert retrospective workflow to native skill packaging (#1943)
* chore: convert retrospective workflow to native skill

* fix(skills): normalize retrospective metadata
2026-03-14 11:14:40 -06:00
Alex Verkhovsky 6cb0cc40fc
refactor(skills): convert create-epics-and-stories workflow to native skill (#1937)
* refactor(skills): convert create-epics-and-stories workflow to native skill

* fix(skills): normalize create-epics-and-stories metadata

* fix: remove workflow_path indirection, use direct relative paths

Replace the custom workflow_path variable with direct relative paths
(../workflow.md, ../templates/epics-template.md) in all step files.
Also remove duplicate epicsTemplate entry in step-01.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: remove unused frontmatter refs from step files

Drop thisStepFile, workflowFile, and epicsTemplate (where unused in
body) from all step frontmatter. Only keep variables actually
referenced in step body content.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: convert partyModeWorkflow to skill ref, drop unused task refs

- partyModeWorkflow now uses skill:bmad-party-mode (it is a skill)
- remove advancedElicitationTask and partyModeWorkflow from steps 1/4
  where they are not referenced in the body

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: inline all frontmatter refs, use canonical skill invocation

- Remove all file/task reference variables from step frontmatter
- Inline paths directly where used in body text
- Use canonical "invoke the skill" phrasing for skill references

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 11:02:55 -06:00
Alex Verkhovsky bc8d239834
fix(create-story): normalize native skill metadata refs (#1975) 2026-03-14 11:01:02 -06:00
Alex Verkhovsky e97aecda28
fix: enforce document_output_language in planning workflow step files (#1977)
Planning workflows loaded document_output_language from config but never
enforced it in step files. Only communication_language was enforced,
causing generated artifacts (product briefs, PRDs, UX specs, project
docs) to be written in the conversation language instead of the
configured document output language.

Add explicit document_output_language enforcement in all content-
generating step files across create-product-brief, create-prd,
create-ux-design, generate-project-context, and document-project
workflows.

Closes #1966
2026-03-14 10:40:37 -06:00
Alex Verkhovsky ac769b230f
Convert code-review workflow to native skill packaging (#1941)
* chore: convert code-review workflow to native skill

* fix: normalize code-review native skill references
2026-03-14 06:03:45 -06:00
Alex Verkhovsky 9e7aeec385
Convert check-implementation-readiness to native skill package (#1938)
* convert check-implementation-readiness to native skill package

* fix(skills): normalize implementation-readiness metadata
2026-03-14 06:02:51 -06:00
Alex Verkhovsky 405fd93e50
chore: add project AGENTS and quality command (#1970)
* chore: add project AGENTS and quality command

* chore: remove stale bundle validation note
2026-03-14 00:26:07 -06:00
Alex Verkhovsky 5f92146a29
refactor(skills): convert create-architecture workflow to native skill (#1936)
* refactor(skills): convert create-architecture workflow to native skill

* fix(skills): remove workflow metadata from create-architecture

* fix(skills): normalize create-architecture step links

* fix(agents): use skill ref for create-architecture
2026-03-14 00:14:13 -06:00
Moritz Eysholdt df4d53de0e feat: add Ona as a supported platform
Add Ona (ona.com) to the BMAD installer so users can select it during
`npx bmad-method install` or via `--tools ona`. Skills are installed to
`.ona/skills/<name>/SKILL.md` using the default templates.

Fixes #1967

Co-authored-by: Ona <no-reply@ona.com>
2026-03-14 02:49:35 +00:00
Alex Verkhovsky d2f15ef776 chore: undo site verification 2026-03-13 19:24:12 -06:00
Alex Verkhovsky a4ecc03dcc
Google Search Console verification 2026-03-13 19:15:52 -06:00
Alex Verkhovsky 79a829b591
refactor(bmm): convert create-ux-design workflow to native skill (#1934)
* refactor(bmm): convert create-ux-design workflow to native skill

* fix(bmm): normalize create-ux-design skill metadata and links

* fix(bmm): normalize create-ux-design skill step links

* fix(bmm): invoke create-ux-design via skill id
2026-03-13 15:43:55 -06:00
Alex Verkhovsky 80671650c2
refactor(bmm): convert create-product-brief to native skill package (#1933)
* refactor(bmm): convert create-product-brief to native skill package

* fix(skills): normalize create-product-brief metadata refs

* fix(skills): normalize create-product-brief step links
2026-03-13 09:15:23 -06:00
Alex Verkhovsky 25d24d02c4
convert dev-story workflow to native skill package (#1940)
* convert dev-story workflow to native skill package

* align dev-story skill references with upstream patterns

* remove obsolete skill frontmatter from dev-story workflow
2026-03-13 09:12:01 -06:00
Alex Verkhovsky 037c34b897
refactor(bmm): convert domain research workflow to native skill (#1928)
* refactor(bmm): convert domain research workflow to native skill

* fix(bmm): correct domain-research step relative paths

* fix domain research skill metadata refs
2026-03-13 06:05:28 -06:00
Alex Verkhovsky 75867b0bea
chore(bmm): convert quick-dev workflow to native skill (#1948)
* chore(bmm): convert quick-dev workflow to native skill package

* fix(bmm): normalize quick-dev skill references

* fix(bmm): remove duplicate quick-dev workflow metadata

* fix(bmm): inline quick-dev skill handoff references
2026-03-13 00:11:14 -06:00
Alex Verkhovsky d39fcd5938
Convert create-story workflow to native skill package (#1939)
* convert create-story workflow to native skill package

* fix(create-story): update converted workflow path refs

* fix(sm-agent): use skill reference for create-story
2026-03-12 22:58:53 -06:00
Alex Verkhovsky 8ba428ee35 fix(skills): remove redundant advanced elicitation workflow metadata 2026-03-12 22:42:34 -06:00
Alex Verkhovsky 997c2e3655
refactor(skills): convert advanced-elicitation.xml to native skill (#1925)
* refactor(skills): convert advanced-elicitation.xml to native skill

* fix(skills): clarify indirect advanced elicitation invocation

* fix(architecture): use native skill invocation wording

* fix(validate-prd): remove unused elicitation reference

* fix(quick-spec): clarify handler reference comment

* fix(skills): simplify advanced elicitation metadata
2026-03-12 22:34:47 -06:00
Brian Madison 521f1e15ca chore(release): v6.1.0 [skip ci]
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 23:02:58 -05:00
Brian Madison 2e88b846f7 fix(publish): use GitHub App token to bypass branch protection
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 22:53:54 -05:00
Brian Madison 88e576d10b docs: draft changelog for v6.1.0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 22:20:52 -05:00
Brian Madison 9cd6e3826d WDS enabled in installer 2026-03-12 21:46:50 -05:00
Brian Madison e073aee30b update gitignore 2026-03-12 19:35:50 -05:00
Alex Verkhovsky 8f1cb7fb70 chore(brainstorming): drop redundant workflow frontmatter 2026-03-12 17:43:24 -06:00
Alex Verkhovsky a48fd4aae8
refactor(skills): convert brainstorming to native skill (#1924)
* refactor(skills): convert brainstorming to native skill

* fix(installer): skip workflow metadata for native skills

* revert: restore workflow metadata handling

* refactor(skills): remove duplicate party-mode workflow metadata

* fix(agents): invoke native skills via skill refs
2026-03-12 16:49:35 -06:00
Alex Verkhovsky 75ec4aa504 ci(publish): restrict workflow to upstream repo only
Prevent publish job from running on forks by gating on
github.repository == 'bmad-code-org/BMAD-METHOD'.
2026-03-12 11:00:52 -06:00
Alex Verkhovsky 7b4875be79
fix(installer): separate skill and agent counts in summary (#1932)
Subtract agents from total skill directories so the summary shows
non-agent skills and agents as distinct counts (e.g. 34 skills, 10
agents) instead of double-counting agents in the skill total.
2026-03-12 09:13:14 -06:00
Alex Verkhovsky c57506464f
fix(installer): simplify install summary (#1915)
* fix(installer): simplify install summary

* style: fix prettier formatting in test file

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(installer): clean up temp dir leak and conditional IDE footer

- Return fixture root from createSkillCollisionFixture so cleanup
  removes the parent temp directory, not just the _bmad child
- Only show bmad-help next-step line when IDEs are configured

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 08:39:10 -06:00
lone fcbcaa6831 docs(zh-cn): add translation for quick-dev-new-preview
Translate docs/explanation/quick-dev-new-preview.md to Chinese.
This document explains the experimental Quick Flow improvement
that reduces human-in-the-loop friction while maintaining quality.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 17:13:53 +08:00
lone fd26a2e0f2 fix: update version hint and TEA module link in Chinese README
- Update version hint from hardcoded 6.0.1 to @next for prerelease builds
- Fix TEA module link to use full repository name

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 17:11:48 +08:00
lone 904b8c0dff fix: update HTTP links to HTTPS in Chinese README
Update all docs.bmad-method.org links from HTTP to HTTPS protocol
for better security and consistency with English README.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 17:09:01 +08:00
Alex Verkhovsky 861716fbe3
fix: address PR review findings from party-mode skill conversion (#1919)
- Fix bare directory ref missing /workflow.md in step-02-generate.md
- Remove stale workflowType: 'party-mode' from workflow.md and step-03
- Remove unused decorative aliases from quick-dev-new-preview workflow

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 00:37:30 -06:00
Brian Madison 0ba809c3e8 temporarily disable bmm from installation 2026-03-12 00:16:42 -05:00
Nikolas Hor 42aa184074
fix: add .npmignore to reduce npm tarball from 533 to 348 files (#1900)
The package was shipping 6.2 MB including docs/, website/, test/,
.github/, banner images, and dev config files. With .npmignore,
the tarball drops to 555 KB (91% reduction) while keeping all
runtime files (src/, tools/cli/, tools/lib/).

Fixes #1870

Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-11 22:49:46 -05:00
Alex Verkhovsky 5a5ade333a
refactor(skills): convert party-mode to native skill directory (#1906)
- Rename party-mode → bmad-party-mode (canonical ID convention)
- Change bmad-skill-manifest.yaml from type:workflow to type:skill
- Add SKILL.md with frontmatter for installer discovery
- Remove installed_path, use relative ./steps/ refs internally
- Update module-help.csv to skill:bmad-party-mode
- Update compiler.js hardcoded PM menu path
- Update 43 cross-references to IDE-agnostic _bmad/ path
- Update test fixtures for renamed directory

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 22:48:29 -05:00
Nikolas Hor 7f7ce8c5e3
docs: document which agent triggers require arguments (#1908)
Adds a "Trigger Types" section to the agents reference page
explaining the difference between workflow triggers (no arguments)
and conversational triggers (arguments required). Lists all
Technical Writer triggers that expect user-provided input with
examples of proper usage.

Fixes #1682
2026-03-11 22:46:56 -05:00
Nikolas Hor 5e1149dc14
fix: consume UX Design Specification as first-class input in create-epics-and-stories (#1909)
The create-epics-and-stories workflow previously relegated UX Design
requirements to a vague "Additional Requirements" list, causing
actionable UX work items (design tokens, component proposals,
accessibility audits) to be silently dropped from the epic/story
breakdown.

Changes:
- step-01: Elevate UX Design extraction to first-class with dedicated
  UX-DR identifiers and thorough extraction guidance
- step-03: Add UX Design integration guidance for story creation and
  final validation coverage check
- epics-template: Add dedicated UX Design Requirements section

Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-11 22:39:31 -05:00
Nikolas Hor df9a7f9b67
docs: fix contradictory Quinn workflow placement in testing reference (#1911)
The testing reference page incorrectly described Quinn's Automate
workflow as running per-story before Code Review, contradicting the
workflow map which positions it after epic completion. Align the testing
page with the workflow map: Quinn runs after all stories in an epic are
implemented and code-reviewed.
2026-03-11 22:35:27 -05:00
Nikolas Hor 9cd362d2d8
fix: remove mandatory minimum issue count from code review workflow (#1913)
The code review workflow required finding 3-10 issues minimum per review
and forced the agent to keep looking if fewer than 3 were found. This
created an endless review cycle where every review manufactures issues
even after previous fixes were applied, because the workflow cannot
conclude with "no issues found."

Replace the hard minimum with a zero-issue sanity check that allows
clean reviews after a thorough re-examination, while preserving the
adversarial review approach for genuine issues.
2026-03-11 22:33:50 -05:00
Nikolas Hor e64cef80b6
fix: add brainstorming reconciliation step to PRD polish workflow (#1914)
When feeding brainstorming sessions into the PRD workflow, soft/qualitative
ideas (tone, personality, interaction design, coaching philosophy) get
silently dropped because they don't map cleanly to the PRD's structured
template (FR/NFR format). The resulting PRD reads as complete, so the
loss is invisible without manually diffing against the brainstorming output.

Add a reconciliation check in step-11 (polish) that cross-references the
brainstorming document against the finished PRD, flags ideas that didn't
land anywhere, and lets the user decide which to incorporate.
2026-03-11 22:32:00 -05:00
Alex Verkhovsky 32693f1a6b
refactor(skills): convert shard-doc.xml to native skill directory (#1896)
Replace single-file XML task with bmad-shard-doc/ skill directory
(SKILL.md, workflow.md, bmad-skill-manifest.yaml). Update parent
manifest and module-help.csv references. Preserves all 6 steps
including Step 6 branching logic for original document handling.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 15:41:56 -06:00
Alex Verkhovsky 874ae40bb2
fix(quick-dev): correct commit ordering, add loopback directive, fix typo (#1876)
* fix(quick-dev): correct commit ordering, add loopback directive, fix typo

- step-05: set spec status to done before committing so the commit
  captures the final state
- step-04: add explicit read-and-follow directive to intent_gap loopback
  matching the pattern used by bad_spec
- SKILL.md: fix missing apostrophe in description

* fix(quick-dev): remove stray commit instruction from review step

The review step (step-04) had a bare "4. Commit." line that conflicted
with commit responsibility belonging solely to step-05-present.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 11:35:04 -06:00
Alex Verkhovsky 6292b0323f
refactor(skills): convert index-docs.xml to native skill directory (#1878)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 10:46:18 -06:00
Alex Verkhovsky 3339f24890
refactor(skills): convert editorial-review-prose.xml to native skill (#1877)
* refactor(skills): convert editorial-review-prose.xml to native skill directory

Replace single-file XML task with standard skill directory structure
(SKILL.md + workflow.md + bmad-skill-manifest.yaml). Update parent
manifest and module-help.csv references. No behavioral changes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: add mandatory execution instructions to editorial-review-prose workflow

Review found missing MANDATORY step-order enforcement and critical marker
on Step 3, which were present in the original XML and the reference pattern
(editorial-review-structure). Adds both to match established conventions.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(tasks): align editorial-review-prose role text with section heading

Rename EXECUTION heading to STEPS and update the role instruction
to reference the correct section name.

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 06:08:45 -06:00
Alex Verkhovsky c0877e795f
fix: replace quick-dev-diagram with higher quality version (#1894)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 05:09:01 -06:00
Alex Verkhovsky ffd7d53be5
refactor(skills): convert editorial-review-structure.xml to native skill (#1875)
* refactor(skills): convert editorial-review-structure.xml to native skill directory

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: mark Step 3 as CRITICAL in editorial-review-structure workflow

The original XML had critical="true" on Step 3 (Structural Analysis).
This attribute was lost during the XML-to-markdown conversion.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: replace ambiguous section references in editorial-review-structure workflow

Rename "EXECUTION" heading to "STEPS" and update the inline reference
from "flow section" to "STEPS section" to avoid LLM misinterpretation.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 04:35:04 -06:00
Alex Verkhovsky 031a9093a1
docs(zh-cn): remove slash prefix from skill examples in code blocks (#1893)
The PR that dropped slash-command prefixes from skill references
missed updating code block examples in three Chinese how-to docs.
2026-03-11 03:45:35 -06:00
Alex Verkhovsky 2a12c6b2f0
docs: drop slash-command prefix from skill references (#1892)
* docs: drop slash-command syntax from skill references (editorial)

Skill names like bmad-help are now shown without a / prefix since
invocation syntax varies across platforms. First-encounter locations
(README, getting-started, get-answers, installer message, bmad-help
display rules) get editorial framing so new users understand these
are skill names to invoke by name.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: mechanical removal of slash prefix from all remaining skill references

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 02:35:16 -06:00
Alex Verkhovsky bb046f5062
docs: mention next install channel (#1887) 2026-03-11 02:34:26 -06:00
Brian Madison 2b809e56a4 update gitignore to exclude installer generated skills in a claude folder. 2026-03-10 19:24:16 -05:00
Brian Madison 5988fe0506 remove .cladue/skills folder, will follow up with gitignore 2026-03-10 19:23:02 -05:00
Alex Verkhovsky 61d89c82ef
docs: refine quick dev new preview explainer (#1889)
* docs: explain quick dev new preview workflow

* docs: refine quick dev new preview explainer
2026-03-10 16:48:48 -05:00
Alex Verkhovsky 30a98633cd
revert: restore QA checklist wording (#1888) 2026-03-10 05:54:07 -06:00
Alex Verkhovsky b7315c6e32 chore(publish): remove trusted publishing diagnostics 2026-03-10 05:23:33 -06:00
Alex Verkhovsky 6a0046917a fix(publish): pin npm for trusted publishing 2026-03-10 04:09:10 -06:00
Alex Verkhovsky c8f5b60598 fix(publish): remove empty token env and improve auth diagnostics 2026-03-10 03:57:58 -06:00
Alex Verkhovsky 7bc2b5e0e0
fix: isolate npm publish from injected auth config (#1886) 2026-03-10 03:49:01 -06:00
Alex Verkhovsky 1ed5c9d94b
fix: force trusted publish without token auth (#1885)
* fix: force trusted publish without token auth

* chore: always print npm debug logs
2026-03-10 02:42:49 -06:00
Alex Verkhovsky fb76895145
feat: allow manual next channel publish (#1884) 2026-03-10 01:20:28 -06:00
Alex Verkhovsky ebf1513069
fix: remove duplicate publish workflows (#1883)
* fix: remove duplicate publish workflows

* chore: add publish workflow diagnostics
2026-03-09 22:55:07 -06:00
Alex Verkhovsky 10f02a8f15
docs: tweak QA checklist wording (#1882) 2026-03-09 22:30:21 -06:00
Alex Verkhovsky 7857b17626
chore: unify npm publish workflow (#1881)
* ci: add continuous delivery workflows for npm publishing

Add publish-next (auto-prerelease on push to main) and publish-latest
(manual stable release with Discord notification). Update CONTRIBUTING.md
to describe the trunk-based CD model.

* fix(ci): guard publish-latest against non-main dispatch

Reject workflow_dispatch runs from non-main refs to prevent
publishing unintended code or fast-forwarding main unexpectedly.

* chore: unify npm publish workflow
2026-03-09 21:57:44 -06:00
Alex Verkhovsky 063aa58b8d
chore(core): convert help.md to native skill directory (#1874)
* chore(core): convert help.md to native skill directory

Migrate the single-file help.md task to a bmad-help/ skill directory
following the pattern established by bmad-review-adversarial-general.
Update module-help.csv to use skill: reference and remove the entry
from the parent manifest. Fix 7 BMM workflow step files that had
hardcoded file path references to the now-relocated help task.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(prompts): invoke bmad-help as a skill

* style(prompts): format bmad-master agent yaml

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 19:02:27 -06:00
Alex Verkhovsky 9421f20b69
ci: add continuous delivery workflows for npm publishing (#1872)
Add publish-next (auto-prerelease on push to main) and publish-latest
(manual stable release with Discord notification). Update CONTRIBUTING.md
to describe the trunk-based CD model.
2026-03-09 15:23:02 -05:00
Alex Verkhovsky 956c43ff62
chore(skills): convert review-edge-case-hunter.xml to native skill (#1871)
* chore(skills): convert review-edge-case-hunter.xml to native skill

Replace single-file XML task with skill directory format (SKILL.md +
workflow.md + bmad-skill-manifest.yaml) following the pattern
established by bmad-review-adversarial-general.

Update all reference locations: bmad-skill-manifest.yaml, module-help.csv,
step-04-review.md, and bmad-os-review-pr instructions.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: address PR review findings for edge-case-hunter skill

- Fix "task returns" → "skill returns" terminology in review-pr instructions
- Remove edge-case-hunter entry from central manifest (has own directory manifest)
- Add sentinel error response for empty/bad input instead of silent empty array
- Reframe Step 2 with two-lens approach: control flow paths + domain boundaries
- Simplify Step 3 to reference Step 2 edge classes instead of duplicating list

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 08:20:16 -06:00
Alex Verkhovsky 1b3c3c5013
refactor(skills): add SKILL.md entrypoint to skill directories (#1868)
* refactor(skills): add SKILL.md entrypoint to skill directories

Align skill source format with Open Skills standard: each skill
directory now contains a SKILL.md with name/description frontmatter
where name must match the directory name exactly. The installer
copies skill directories verbatim instead of generating SKILL.md.

- Add SKILL.md to both tracer bullet skill directories
- Strip name/description from workflow.md frontmatter (SKILL.md owns it)
- Installer reads metadata from SKILL.md, validates name matches dirname
- Install path in manifest CSV now points to SKILL.md
- Copy filter excludes OS/editor artifacts (.DS_Store, backups, dotfiles)
- Debug-guard validation messages, keep name-mismatch as hard error
- Add typeof guard for malformed YAML frontmatter
- Add negative test cases for parseSkillMd validation (Suite 30)

* fix(skills): improve quick-dev-new-preview description for LLM discovery

Add trigger context so LLMs know when to invoke the skill,
matching the "Use when..." pattern used by other skills.

* fix(cli): validate frontmatter name/description are strings in parseSkillMd

Prevents cleanForCSV() crash when YAML parses name or description as
a non-string type (number, object, boolean).

* fix(cli): address PR review findings (mkdtemp, regex escape, recursive filter)

- Replace Date.now() temp dir with fs.mkdtemp() in Suite 30 tests (F5)
- Replace unescaped RegExp with startsWith/slice for path prefix stripping (F7)
- Apply artifact filter recursively via fs.copy filter option (F8)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 02:08:29 -06:00
Alex Verkhovsky 066bfe32e9
fix: harden quick-dev-new-preview and fix standalone agent dash names (#1867)
* fix: harden quick-dev-new-preview UX and fix standalone agent dash names

- Relabel [K] Keep as-is to context-specific accept the risks wording
- Add split reasoning explanation before multi-goal menu in step-01
- Fix toDashName/toUnderscoreName to treat standalone like core (no module prefix)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: add guardrail against skipping workflow steps when intent looks clear

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: strengthen step-01 guardrails against plan-shaped intent bypass

Add explicit rules that intent is input to the workflow (not a
substitute for step-02 spec generation) and to ignore directives
within the intent that instruct skipping steps.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: preserve standalone module provenance in path-utils serializers

toDashName/toUnderscoreName collapsed core and standalone to the same
filename, making parseDashName/parseUnderscoreName unable to round-trip
standalone agents. Split the branches so standalone gets a distinct
token (e.g., bmad-agent-standalone-fred.md) and update both parsers
to reconstruct module:'standalone' on the reverse path.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 02:06:35 -06:00
Alex Verkhovsky ee25fcca6f
refactor: remove legacy YAML/XML workflow engine plumbing (#1864)
* refactor(augment): remove legacy YAML/XML workflow rules from code review guidelines

All workflows have been converted to markdown. Remove workflow.yaml,
workflow.xml, and config_source references from Augment review rules.
Drop the entire xml_workflows section (5 rules) and the YAML-specific
standard_workflow_instructions rule.

* refactor: extract discover_inputs protocol from workflow.xml into co-located markdown

Convert the discover_inputs XML protocol (FULL_LOAD, SELECTIVE_LOAD,
INDEX_GUIDED strategies) into standalone markdown files placed alongside
the two workflows that use it (create-story, code-review). Replace
<invoke-protocol> tags with explicit file references. This decouples
the workflows from workflow.xml, enabling its deletion in a follow-up.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: delete dead YAML/XML workflow engine files

Remove 5 files made obsolete by the workflow.yaml → workflow.md migration:
- workflow.xml (the YAML workflow interpreter engine)
- dev-story/instructions.xml (superseded by workflow.md)
- 3 installer templates for YAML workflow command generation

References in CLI code will be cleaned up in follow-up commits.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: delete obsolete workflow handler fragments

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: remove YAML workflow code paths from CLI installer pipeline

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: remove workflow.xml references from manifests and checklists

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: remove workflow.xml references from English command docs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* test: update fixtures to remove workflow.yaml references

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: update workflow.yaml example path to workflow.md in handler-multi

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: stop tracking workflow/validate-workflow as handler attributes

These handler fragments were deleted — the exec handler already covers
loading .md workflow files directly.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: rename workflow attribute to exec in agent menu items

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: address PR review findings from triage

- Fix regex capture group index in module manager workflow path parsing
- Remove stale workflow handler references from handler-multi.txt
- Replace workflow with multi in activation-steps dispatch contract
- Remove dead validate-workflow emission from compiler and xml-builder
- Align commands.md wording to remove engine references
- Fix relativePath anchoring in _base-ide.js recursive directory scans
- Remove dead code from workflow-command-generator (unused template,
  generateCommandContent, writeColonArtifacts, writeDashArtifacts)
- Delete unused workflow-commander.md template
- Add regression test for workflow path regex

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 18:02:57 -06:00
Alex Verkhovsky 4c470d9948
refactor: convert document-project workflow.yaml to workflow.md (step 9) (#1863)
* refactor: convert document-project workflow.yaml to workflow.md (step 9)

Convert main workflow and both sub-workflows (deep-dive, full-scan) from
legacy .yaml entry point format to unified .md format. Update agent files
and module-help.csv references. Clean engine-scaffolding <critical> blocks
from instruction files.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: correct config path typo bmb→bmm in sub-workflow files

Both deep-dive-workflow.md and full-scan-workflow.md referenced
_bmad/bmb/config.yaml instead of _bmad/bmm/config.yaml, which
would break config resolution at runtime.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 12:30:12 -06:00
Alex Verkhovsky 0782e291fd
refactor: convert create-story workflow.yaml to workflow.md (step 7) (#1862)
* refactor: convert create-story workflow.yaml to workflow.md (step 7)

Merge workflow.yaml config and instructions.xml execution logic into a
single self-contained workflow.md. Drop engine scaffolding directives,
preserve all behavioral constraints. Update checklist.md references.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: update remaining workflow.yaml refs to workflow.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 12:15:27 -06:00
Alex Verkhovsky 5c9227340e
chore: convert dev-story workflow from yaml to markdown (#1861)
* chore: convert dev-story workflow from yaml to markdown format

Merge workflow.yaml config and instructions.xml content into a single
workflow.md, following the established conversion pattern. Drop engine
scaffolding directives, preserve all behavioral constraints verbatim.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: update dev-story workflow references from .yaml to .md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 12:08:49 -06:00
Alex Verkhovsky 350a1eaa47
chore: convert code-review workflow.yaml to workflow.md (#1860)
* chore: convert code-review workflow.yaml to workflow.md

Step 6 of 9 in yaml-to-md conversion plan. Merges workflow.yaml
config and instructions.xml content into a single workflow.md
following the established conversion pattern. Updates agent yaml
and module-help.csv references.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: escape folder names with backticks to fix markdownlint MD037

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 11:19:17 -06:00
Alex Verkhovsky 140ae57f2a
feat(manifest): unified skill scanner decoupled from legacy collectors (#1859)
* feat(manifest): unified skill scanner decoupled from legacy collectors

Add collectSkills() that recursively walks module trees to discover
type:skill directories anywhere, replacing the band-aid detection
inside collectWorkflows(). Legacy collectors now skip claimed dirs.
scanInstalledModules recognizes skill-only modules.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(manifest): address PR review findings from triage

- Add missing skillClaimedDirs guard to getAgentsFromDir (F1)
- Add skills to this.files[] in collectSkills (F2)
- Add test for type:skill inside workflows/ dir (F5)
- Warn on malformed workflow.md parse in skill dirs (F6)
- Add skills count to generateManifests return value (F9)
- Remove redundant \r? from regex after line normalization (F10)
- Normalize path.relative to forward slashes for cross-platform (F12)
- Enforce directory name as skill canonicalId, warn if manifest overrides (F13)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 09:02:06 -06:00
Alex Verkhovsky c9ebe1b417
chore(correct-course): convert workflow.yaml to unified workflow.md (#1858)
Step 5 of 9 in yaml-to-md conversion plan. Merges workflow.yaml config
(6 input_file_patterns including INDEX_GUIDED) and instructions.md
execution logic into a single self-contained workflow.md. Updates
references in sm.agent.yaml, pm.agent.yaml, module-help.csv, and
checklist.md. Deletes workflow.yaml and instructions.md.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 07:20:03 -06:00
Alex Verkhovsky 835d6d85a5
feat(tasks): convert review-adversarial-general XML task to native skill (#1857)
* feat(tasks): convert review-adversarial-general from XML task to native skill

Convert the simplest core task (review-adversarial-general.xml) from
type:task XML format to type:skill markdown format. This establishes
the pattern for converting remaining XML tasks to self-contained skills.

- Convert XML task to workflow.md with frontmatter, role, execution steps
- Add type:skill manifest for verbatim directory copying
- Extend manifest-generator getTasksFromDir to recurse into subdirectories
  and detect type:skill entries (mirrors existing workflow skill detection)
- Update cross-references in quick-dev-new-preview, quick-dev, quick-spec
- Update module-help.csv to use skill: prefix

* refactor: replace file path references with skill name invocations

Consumers of review-adversarial-general now invoke by skill name
instead of loading via _bmad/ file path. Removes the indirection
variable from frontmatter and inlines the skill name directly.

* refactor(installer): scan tasks/ for type:skill entries

Teach collectWorkflows to also scan the tasks/ subdirectory for
type:skill entries. Skills can live anywhere in the source tree —
the workflow scanner just needs to look in more places.

* fix: update stale task terminology to skill after format conversion

Address review findings from PR #1857: replace remaining "task"
references with "skill" in workflow steps and test documentation.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 06:52:55 -06:00
Alex Verkhovsky dc8293e5df
chore(sprint-planning): convert workflow.yaml to unified workflow.md (#1856)
* chore(sprint-planning): convert workflow.yaml + instructions.md to unified workflow.md

Step 4 of 9 in the yaml-to-md conversion plan. Merges config
and instructions into a single self-contained workflow.md,
dropping engine scaffolding (critical tags, invoke-protocol).

* fix(sprint-planning): address review findings from PR triage

- Update stale workflow.yaml references to workflow.md in sm.agent.yaml and module-help.csv
- Widen epics_pattern from epic*.md to *epic*.md to match documented input files
- Fix placeholder mismatch: epics_in_progress_count → in_progress_count

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 04:51:50 -06:00
Alex Verkhovsky 7f1a55ca8c
feat(skills): add type:skill manifest for verbatim directory copying (#1851)
* feat(skills): add type:skill manifest for verbatim skill directory copying

Introduce `type: skill` in bmad-skill-manifest.yaml to signal the
installer to copy entire skill directories verbatim into IDE skill
directories, replacing the launcher-based approach.

Changes:
- skill-manifest.js: fix single-entry detection for type-only manifests,
  add getArtifactType export
- manifest-generator.js: collect type:skill entries separately, write
  skill-manifest.csv, derive canonicalId from directory name
- _config-driven.js: add installVerbatimSkills with YAML-safe SKILL.md
  generation, stale file cleanup, and warning on parse failures
- Rename quick-dev-new-preview to bmad-quick-dev-new-preview so
  directory name is the canonical ID
- Update workflow.md installed_path to reference IDE skill base directory

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: replace {installed_path} with relative paths in quick-dev skill

Skills resolve paths relative to the skill root directory per the
open agent standard, so the installed_path variable is unnecessary.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(skills): add install_to_bmad flag and skill: help catalog reference

Add install_to_bmad flag to skill manifests (default true) enabling
skills to opt out of _bmad/ copy while retaining .claude/skills/
installation. Support skill:<canonicalId> references in module-help.csv
workflow-file column. Fix stale quick-dev-new-preview directory
references in agent YAML and help catalog.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* test: add install_to_bmad design contract tests

Unit tests against getInstallToBmad and loadSkillManifest that nail
down the 4 core design decisions for the install_to_bmad flag.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: reset skills array between runs and allow skill-only targets

- Reset this.skills and this.files in ManifestGenerator to prevent stale
  data when instance is reused across multiple manifest runs
- Allow targets with empty artifact_types to still install verbatim
  skills by checking skill_format before short-circuiting

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: resolve broken file references in quick-dev-new-preview workflow

- Fix step-02-plan.md templateFile path (./tech-spec-template.md → ../tech-spec-template.md)
- Teach validate-file-refs.js to skip skill: prefixed references in CSV

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 01:23:26 -07:00
Gani Mohamed Parakadhullah 8e5898e862
feat: add pi coding agent as supported platform (#1854)
* feat: add pi coding agent as supported platform

Add pi (provider-agnostic terminal-native AI coding agent) to
platform-codes.yaml with native skills format output to .pi/skills/.

Pi follows the open Agent Skills specification and uses the same
subdirectory/SKILL.md structure that BMAD already generates for
other platforms.

Fixes #1853

* fix: address PR review comments for Pi test suite

- Assert template_type === 'default' to pin config contract
- Verify Pi appears in getAvailableIdes() list
- Test detect() returns false before install, true after
- Parse frontmatter between --- delimiters instead of regex on full file
- Assert description is present and non-empty
- Assert frontmatter contains only name and description keys
- Validate body content is non-empty with expected activation instructions
- Add reinstall/upgrade coverage (rerun setup over existing output)
- Move temp directory cleanup to finally block
2026-03-08 00:51:26 -06:00
Alex Verkhovsky 44ba15f9a1
feat: add skill manifest for advanced-elicitation workflow (#1840)
* feat: add skill manifest for advanced-elicitation workflow

Register advanced-elicitation as an invocable skill so it can be
triggered as a standalone slash command, matching the pattern used
by party-mode and brainstorming.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: convert advanced-elicitation from XML to markdown workflow

The installer only discovers workflow.yaml and workflow.md files,
so workflow.xml was never registered. Convert to workflow.md with
YAML frontmatter while preserving all elicitation logic verbatim.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: update all references from workflow.xml to workflow.md

Update 67 references across 50 files to point to the new markdown
workflow. Also fix incorrect methods.csv filename and bare
advanced-elicitation.xml reference in generate-project-context.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-07 18:51:05 -07:00
Alex Verkhovsky db8f856fce
docs: update terminology from commands to skills across all documentation (#1850)
Align documentation with the skills-based architecture migration by
replacing references to "commands", "slash commands", and legacy command
names with the new "skills" terminology and skill names.
2026-03-07 16:14:25 -07:00
Alex Verkhovsky ec973ebcf3
refactor: convert workflow.yaml to workflow.md (steps 1-3) (#1842)
* refactor(sprint-status): convert workflow.yaml + instructions.md to single workflow.md

Merge workflow config and instruction content into a unified workflow.md
with YAML frontmatter, following the established convention for converted
workflows. Update module-help.csv reference accordingly.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(sprint-status): restore no-time-estimates rule dropped during conversion

The <critical> preamble removal incorrectly classified this behavioral
rule as boilerplate. It is an actual output constraint.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* test: add comprehensive workflow conversion test results

- 14 test fixtures covering data and validate modes
- Tested across Opus, Sonnet, and Haiku models
- OLD format (yaml+md) vs NEW format (workflow.md)
- Confirms zero regressions in conversion
- Includes reproduction instructions for future sessions

* fix(sprint-status): consolidate no-time-estimates into role line

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(qa-generate-e2e-tests): convert workflow.yaml + instructions.md to single workflow.md

Task 2 of yaml-to-md conversion plan. Merges config variables into
INITIALIZATION section, inlines instructions into EXECUTION section.
Drops non-consumed yaml keys (required_tools, tags, execution_hints).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(retrospective): convert workflow.yaml + instructions.md to single workflow.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: update workflow.yaml references to workflow.md for converted workflows

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* chore: remove test results file from version control

SPRINT_STATUS_CONVERSION_TEST_RESULTS.md contains hardcoded local
filesystem paths and is a session-specific test artifact. Added to
.bare/info/exclude to keep it ignored across all worktrees.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 16:11:34 -07:00
cccczl 4974cd847f
docs: fix chinese documentation translation errors (#1848) 2026-03-07 14:34:12 -06:00
Alex Verkhovsky 5aab72caba
feat(skills): migrate all remaining platforms to native skills format (#1841)
* feat(skills): migrate Roo Code installer to native skills format

Move Roo Code from legacy `.roo/commands/` flat files to native
`.roo/skills/{skill-name}/SKILL.md` directory output. Verified
skill discovery in Roo Code v3.51 with 43 skills installed.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* test(skills): add native skills tests for Claude Code, Codex, and Cursor

Add dedicated test suites covering config validation, fresh install,
legacy cleanup, and ancestor conflict detection for Claude Code, Codex
CLI, and Cursor. Updates migration checklist to reflect verified status.

84 assertions now pass (up from 50).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* test(skills): add Roo Code reinstall/upgrade test

Verify that running Roo setup over existing skills output succeeds
and preserves SKILL.md output. Checks off the last Roo checklist item.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(skills): migrate GitHub Copilot to config-driven native skills

Replace 699-line custom installer with config-driven skill_format.
Output moves from .github/agents/ + .github/prompts/ to
.github/skills/{skill-name}/SKILL.md. Legacy cleanup strips BMAD
markers from copilot-instructions.md and removes old directories.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: update migration checklist with Copilot and Roo verified results

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(skills): migrate Cline to config-driven native skills

Move Cline installer from .clinerules/workflows to .cline/skills with
SKILL.md directory output. Add legacy cleanup and 9 test assertions.

* feat(skills): migrate CodeBuddy to config-driven native skills

Move CodeBuddy installer from .codebuddy/commands to .codebuddy/skills
with SKILL.md directory output. Add legacy cleanup and 9 test assertions.

* feat(skills): migrate Crush to config-driven native skills

Move Crush installer from .crush/commands to .crush/skills with
SKILL.md directory output. Add legacy cleanup and 9 test assertions.

* feat(skills): migrate Trae to config-driven native skills

Move Trae installer from .trae/rules to .trae/skills with SKILL.md
directory output. Add legacy cleanup and 9 test assertions.

* feat(skills): migrate KiloCoder to config-driven native skills

Replace 269-line custom kilo.js installer with config-driven entry in
platform-codes.yaml targeting .kilocode/skills/ with skill_format: true.

- Add installer config: target_dir, skill_format, template_type, legacy_targets
- Add cleanupKiloModes() to strip BMAD modes from .kilocodemodes on cleanup
- Remove kilo.js from manager.js customFiles and Kilo-specific result handling
- Delete tools/cli/installers/lib/ide/kilo.js
- Add test Suite 22: 11 assertions (config, install, legacy cleanup, modes, reinstall)
- Update migration checklist with verified results

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(skills): migrate Gemini CLI to config-driven native skills

Replace TOML-based .gemini/commands output with native SKILL.md output
in .gemini/skills/. Gemini CLI confirms native skills support per
geminicli.com/docs/cli/skills/.

- Update platform-codes.yaml: target_dir, skill_format, legacy_targets
- Add test Suite 23: 9 assertions (config, install, legacy, reinstall)
- Add Gemini CLI section to migration checklist

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(skills): migrate iFlow, QwenCoder, and Rovo Dev to native skills

Complete the native skills migration for all remaining platforms:

- iFlow: .iflow/commands → .iflow/skills (config change)
- QwenCoder: .qwen/commands → .qwen/skills (config change)
- Rovo Dev: replace 257-line custom rovodev.js with config-driven
  .rovodev/skills, add cleanupRovoDevPrompts() for prompts.yml cleanup

All platforms now use config-driven native skills. No custom installer
files remain. Manager.js customFiles array is now empty.

- Add test suites 24-26: 20 new assertions (173 total)
- Update migration checklist: all summary gates passed
- Delete tools/cli/installers/lib/ide/rovodev.js

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(installer): preserve bmad-os-* skills during cleanup

The cleanupTarget method removed all entries starting with "bmad" from
IDE skills directories, which would also wipe version-controlled
bmad-os-* skills from the BMAD-METHOD repo. Add exclusion for the
bmad-os- prefix so those skills survive reinstalls.

* docs: flag all unverified platforms for manual IDE testing

Add NEEDS MANUAL IDE VERIFICATION to KiloCoder, Gemini CLI, iFlow,
QwenCoder, and Rovo Dev checklists. CodeBuddy, Crush, and Trae already
had the flag.

* fix(installer): suspend Kilo Code and add verified Gemini/Crush results

Kilo Code does not support the Agent Skills standard — the migration
from modes+workflows to skills was based on a false fork assumption.

- Add suspended field to platform-codes.yaml, hiding Kilo from the IDE
  picker and blocking setup with a clear message
- Fail the installer early (before writing _bmad/) if all selected IDEs
  are suspended, protecting existing installations from being corrupted
- Still clean up legacy Kilo artifacts (.kilocodemodes, .kilocode/workflows)
  when users switch to a different IDE
- Mark Crush and Gemini CLI as manually verified (both work end-to-end)
- Replace Suite 22 install tests with suspended-behavior tests (7 assertions)

* docs: update KiloCoder checklist to reflect suspended status

* fix(skills): add canonicalIds for BMM research and PRD workflows

Drop the bmm module prefix from 6 workflow skill names so they
install as bmad-create-prd, bmad-domain-research, etc. instead of
bmad-bmm-create-prd, bmad-bmm-domain-research, etc.

* fix(installer): address PR review findings from automated reviewers

Triage of 18 findings from Augment and CodeRabbit reviews on PR #1841:

Source code fixes:
- Exclude bmad-os-* from findAncestorConflict to match cleanupTarget
- Wrap cleanupCopilotInstructions in try/catch (best-effort, not fatal)
- Wrap suspended-platform cleanup in try/catch (failure boundary)
- Clean up temp backup dirs in catch block when install aborts
- Normalize IDE keys to lowercase before suspended lookup
- Delete dead loadCustomInstallerFiles method and stale references
- Rename "Roo Cline" to "Roo Code" in both platform-codes.yaml files
- Fix Gemini CLI package name (@google/gemini-cli, not @anthropic-ai)

Test improvements:
- Add name/frontmatter invariant check to 6 missing platform suites
- Assert stale bmad-architect skill is removed after cleanup

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 12:30:49 -07:00
Alex Verkhovsky 434e7efab6
fix: add missing skill manifests for research and PRD workflows (#1839)
These manifests were missed during the all-is-skills migration (#1834),
leaving 6 workflows undiscoverable by the native skills installer.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 21:59:27 -07:00
Alex Verkhovsky 0d3b317598
refactor: all-is-skills - Convert BMAD to skills-based architecture (#1834)
* feat(skills): add canonical bmad- naming via skill manifests

Add bmad-skill-manifest.yaml sidecars to all 38 capabilities (tasks,
agents, workflows) declaring canonicalId as the single source of truth
for skill names. Update Claude Code and Codex installers to prefer
canonicalId over path-derived names, with graceful fallback.

- 24 manifest files covering 38 capabilities
- New shared skill-manifest.js utility for manifest loading
- resolveSkillName() in path-utils.js bridges manifest → installer
- All command generators propagate canonicalId through CSV manifests
- Drops bmm module prefix from all user-facing skill names

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(skills): claude-code installer outputs .claude/skills/<name>/SKILL.md

Refactor the config-driven installer to emit Agent Skills Open Standard
format for Claude Code: directory-per-skill with SKILL.md entrypoint,
unquoted YAML frontmatter, and full canonical names.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(installer): migrate codex to config-driven pipeline

Delete the custom codex.js installer (441 lines) and route Codex
through the config-driven pipeline via platform-codes.yaml. This
fixes 7 task/tool descriptions that were generic due to bypassing
manifests, and eliminates duplicate transformToSkillFormat code.

Key changes:
- Add codex entry to platform-codes.yaml with skill_format + legacy_targets
- Remove codex from custom installer list in manager.js
- Add installCustomAgentLauncher() to config-driven for custom agent support
- Add detect() override for skill_format platforms (bmad-prefix check)
- Set configDir from target_dir for base-class detect() compatibility

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(installer): guard codex skill installs in nested directories

* fix(installer): warn on stale global legacy skill dirs

* feat(installer): migrate cursor to native skills

* Migrate Windsurf installer to native skills

* Clarify Windsurf skill invocation in checklist

* feat(installer): migrate kiro to native skills

* docs: record kiro skill visibility verification

* Migrate Antigravity installer to native skills

* Document Antigravity ancestor skill verification

* Synchronize native skills migration checklist

* Migrate Auggie installer to native skills

* Migrate OpenCode installer to native skills

* Document live skill verification for Auggie and OpenCode

* fix(test): replace _bmad filesystem dependency with self-contained fixture

The installation component tests walked up the filesystem looking for a
pre-installed _bmad directory, which exists locally but not in CI. Replace
findInstalledBmadDir() with createTestBmadFixture() that creates a minimal
temp directory with fake compiled agents, making tests fully self-contained.

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-06 21:39:19 -06:00
Chandan Veerabhadrappa 09ce8559f2
fix: use last_updated instead of generated for sprint-status staleness check (#1836)
The staleness warning in sprint-status always fired after 7 days because
it checked the 'generated' timestamp, which is only set once during
sprint-planning. Other workflows (dev-story, create-story, code-review,
retrospective) update statuses but never touched 'generated'.

This adds a 'last_updated' field that is:
- Set initially alongside 'generated' during sprint-planning
- Bumped to current date by every workflow that modifies sprint-status.yaml
- Used by the staleness check (with fallback to 'generated' for backward
  compatibility)

Fixes bmad-code-org/BMAD-METHOD#1820

Co-authored-by: Oz <oz-agent@warp.dev>
2026-03-06 20:25:59 -06:00
Alex Verkhovsky e3ffdf9c90
fix(create-story): replace missing validate-workflow invoke with explicit checklist action (#1837)
Co-authored-by: Brian <bmadcode@gmail.com>
2026-03-06 20:24:13 -06:00
Alex Verkhovsky d812205470
fix(quick-flow): add input trust guardrail to step 1 clarify-and-route (#1825)
Prevent the agent from treating detailed, plan-like input as a validated
plan and short-circuiting the workflow. The new rule ensures the full
workflow is followed regardless of input specificity.
2026-03-06 20:22:56 -06:00
Alex Verkhovsky ed76f57a19
feat(i18n): add zh-CN locale support (#1822)
* feat(i18n): add zh-cn locale support with Starlight routing

Reorganize Chinese translations from docs_cn/ into docs/zh-cn/
following Starlight's i18n content structure. Configure Starlight
with root locale (en, unprefixed) and zh-cn (/zh-cn/ prefix).

- Move 28 files from docs_cn/*_cn.md to docs/zh-cn/*.md
- Fix 21 internal links to remove _cn suffixes
- Add defaultLocale + locales config to astro.config.mjs
- Add .gitignore exception for docs/zh-cn/ (overrides z*/ rule)
- Language switcher activates automatically via existing Header
- hreflang tags auto-generated by Starlight on all pages

* feat(i18n): add zh-CN UI translations and sidebar labels

- Add website/src/content/i18n/zh-CN.json with Starlight UI strings
- Add sidebar group label translations (欢迎, 路线图, 教程, etc.)
- Register i18n collection in content config to fix deprecation warning

* fix(i18n): exclude 404 pages from sitemap

Custom 404 pages (root and zh-cn) were indexed as regular content in
the sitemap. Add a filter to the @astrojs/sitemap integration that
matches the /404 path segment precisely via regex on the URL pathname.
2026-03-06 20:21:43 -06:00
Alex Verkhovsky f7846fd5eb
feat(skills): add edge case hunter as parallel review layer in PR review (#1791)
* feat(skills): add edge case hunter as parallel review layer in PR review

Wire review-edge-case-hunter.xml into bmad-os-review-pr as a second
review layer running in parallel with the adversarial review. Both
subagents receive the same PR diff concurrently. Findings are merged,
deduplicated, and tagged by source before tone transformation.

* fix(core): resolve contradictions in edge case hunter task spec

- Show array wrapper [{}] in output-format example to match JSON array
  contract, and document empty array [] as valid output
- Consolidate empty-content handling: step 1 now defers to halt-conditions
  instead of defining separate "ask and abort" behavior
- Zero-findings halt no longer contradicts JSON contract: re-analyze once,
  then return [] instead of ambiguous "HALT or re-analyze"
- Soften "Execute ALL steps" to acknowledge halt-conditions can interrupt

* fix(review): address PR #1791 review feedback

- Remove "Task tool" reference per maintainer; use generic "subagents"
- Fix nested triple-backtick fencing with four-tick outer fence
- Widen location format to support multi-line ranges and hunk refs
- Add JSON-safety constraint to guard_snippet field
- Tighten input loading to "strictly from provided input"
- Replace vague "unreadable" with "cannot be decoded as text"
- Replace vague "increased scrutiny" with concrete re-analysis checklist
- Resolve HALT-immediately vs re-analysis conflict in LLM instructions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 20:21:28 -06:00
Alex Verkhovsky abf3d25f06
fix(core): remove stale tool_supports_subagents and tool_supports_agent_teams config (#1827)
These config keys were added in efc69ffb but never consumed by any
template, conditional logic, or runtime code. They represent platform
capabilities that the agent can determine at runtime — persisting a
stale user guess adds installation friction with zero execution value.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 09:59:16 -06:00
785 changed files with 46437 additions and 37456 deletions

View File

@ -1,6 +1,7 @@
# Augment Code Review Guidelines for BMAD-METHOD # Augment Code Review Guidelines for BMAD-METHOD
# https://docs.augmentcode.com/codereview/overview # https://docs.augmentcode.com/codereview/overview
# Focus: Workflow validation and quality # Focus: Skill validation and quality
# Canonical rules: tools/skill-validator.md (single source of truth)
file_paths_to_ignore: file_paths_to_ignore:
# --- Shared baseline: tool configs --- # --- Shared baseline: tool configs ---
@ -48,163 +49,17 @@ file_paths_to_ignore:
areas: areas:
# ============================================ # ============================================
# WORKFLOW STRUCTURE RULES # SKILL FILES
# ============================================ # ============================================
workflow_structure: skill_files:
description: "Workflow folder organization and required components" description: "All skill content — SKILL.md, workflow.md, step files, data files, and templates within skill directories"
globs: globs:
- "src/**/skills/**"
- "src/**/workflows/**" - "src/**/workflows/**"
- "src/**/tasks/**"
rules: rules:
- id: "workflow_entry_point_required" - id: "skill_validation"
description: "Every workflow folder must have workflow.yaml, workflow.md, or workflow.xml as entry point" description: "Apply the full rule catalog defined in tools/skill-validator.md. That file is the single source of truth for all skill validation rules covering SKILL.md metadata, workflow.md constraints, step file structure, path references, variable resolution, sequential execution, and skill invocation syntax."
severity: "high"
- id: "sharded_workflow_steps_folder"
description: "Sharded workflows (using workflow.md) must have steps/ folder with numbered files (step-01-*.md, step-02-*.md)"
severity: "high"
- id: "standard_workflow_instructions"
description: "Standard workflows using workflow.yaml must include instructions.md for execution guidance"
severity: "medium"
- id: "workflow_step_limit"
description: "Workflows should have 5-10 steps maximum to prevent context loss in LLM execution"
severity: "medium"
# ============================================
# WORKFLOW ENTRY FILE RULES
# ============================================
workflow_definitions:
description: "Workflow entry files (workflow.yaml, workflow.md, workflow.xml)"
globs:
- "src/**/workflows/**/workflow.yaml"
- "src/**/workflows/**/workflow.md"
- "src/**/workflows/**/workflow.xml"
rules:
- id: "workflow_name_required"
description: "Workflow entry files must define 'name' field in frontmatter or root element"
severity: "high"
- id: "workflow_description_required"
description: "Workflow entry files must include 'description' explaining the workflow's purpose"
severity: "high"
- id: "workflow_config_source"
description: "Workflows should reference config_source for variable resolution (e.g., {project-root}/_bmad/module/config.yaml)"
severity: "medium"
- id: "workflow_installed_path"
description: "Workflows should define installed_path for relative file references within the workflow"
severity: "medium"
- id: "valid_step_references"
description: "Step file references in workflow entry must point to existing files"
severity: "high"
# ============================================
# SHARDED WORKFLOW STEP RULES
# ============================================
workflow_steps:
description: "Individual step files in sharded workflows"
globs:
- "src/**/workflows/**/steps/step-*.md"
rules:
- id: "step_goal_required"
description: "Each step must clearly state its goal (## STEP GOAL, ## YOUR TASK, or step n='X' goal='...')"
severity: "high"
- id: "step_mandatory_rules"
description: "Step files should include MANDATORY EXECUTION RULES section with universal agent behavior rules"
severity: "medium"
- id: "step_context_boundaries"
description: "Step files should define CONTEXT BOUNDARIES explaining available context and limits"
severity: "medium"
- id: "step_success_metrics"
description: "Step files should include SUCCESS METRICS section with ✅ checkmarks for validation criteria"
severity: "medium"
- id: "step_failure_modes"
description: "Step files should include FAILURE MODES section with ❌ marks for anti-patterns to avoid"
severity: "medium"
- id: "step_next_step_reference"
description: "Step files should reference the next step file path for sequential execution"
severity: "medium"
- id: "step_no_forward_loading"
description: "Steps must NOT load future step files until current step completes - just-in-time loading only"
severity: "high"
- id: "valid_file_references"
description: "File path references using {variable}/filename.md must point to existing files"
severity: "high"
- id: "step_naming"
description: "Step files must be named step-NN-description.md (e.g., step-01-init.md, step-02-context.md)"
severity: "medium"
- id: "halt_before_menu"
description: "Steps presenting user menus ([C] Continue, [a] Advanced, etc.) must HALT and wait for response"
severity: "high"
# ============================================
# XML WORKFLOW/TASK RULES
# ============================================
xml_workflows:
description: "XML-based workflows and tasks"
globs:
- "src/**/workflows/**/*.xml"
- "src/**/tasks/**/*.xml"
rules:
- id: "xml_task_id_required"
description: "XML tasks must have unique 'id' attribute on root task element"
severity: "high"
- id: "xml_llm_instructions"
description: "XML workflows should include <llm> section with critical execution instructions for the agent"
severity: "medium"
- id: "xml_step_numbering"
description: "XML steps should use n='X' attribute for sequential numbering"
severity: "medium"
- id: "xml_action_tags"
description: "Use <action> for required actions, <ask> for user input (must HALT), <goto> for jumps, <check if='...'> for conditionals"
severity: "medium"
- id: "xml_ask_must_halt"
description: "<ask> tags require agent to HALT and wait for user response before continuing"
severity: "high"
# ============================================
# WORKFLOW CONTENT QUALITY
# ============================================
workflow_content:
description: "Content quality and consistency rules for all workflow files"
globs:
- "src/**/workflows/**/*.md"
- "src/**/workflows/**/*.yaml"
rules:
- id: "communication_language_variable"
description: "Workflows should use {communication_language} variable for agent output language consistency"
severity: "low"
- id: "path_placeholders_required"
description: "Use path placeholders (e.g. {project-root}, {installed_path}, {output_folder}) instead of hardcoded paths"
severity: "medium"
- id: "no_time_estimates"
description: "Workflows should NOT include time estimates - AI development speed varies significantly"
severity: "low"
- id: "facilitator_not_generator"
description: "Workflow agents should act as facilitators (guide user input) not content generators (create without input)"
severity: "medium"
- id: "no_skip_optimization"
description: "Workflows must execute steps sequentially - no skipping or 'optimizing' step order"
severity: "high" severity: "high"
# ============================================ # ============================================
@ -223,27 +78,10 @@ areas:
description: "Agent files must define persona with role, identity, communication_style, and principles" description: "Agent files must define persona with role, identity, communication_style, and principles"
severity: "high" severity: "high"
- id: "agent_menu_valid_workflows" - id: "agent_menu_valid_skills"
description: "Menu triggers must reference valid workflow paths that exist" description: "Menu triggers must reference valid skill names that exist"
severity: "high" severity: "high"
# ============================================
# TEMPLATES
# ============================================
templates:
description: "Template files for workflow outputs"
globs:
- "src/**/template*.md"
- "src/**/templates/**/*.md"
rules:
- id: "placeholder_syntax"
description: "Use {variable_name} or {{variable_name}} syntax consistently for placeholders"
severity: "medium"
- id: "template_sections_marked"
description: "Template sections that need generation should be clearly marked (e.g., <!-- GENERATE: section_name -->)"
severity: "low"
# ============================================ # ============================================
# DOCUMENTATION # DOCUMENTATION
# ============================================ # ============================================

View File

@ -0,0 +1,74 @@
{
"name": "bmad-method",
"owner": {
"name": "Brian (BMad) Madison"
},
"description": "Breakthrough Method of Agile AI-driven Development — a full-lifecycle framework with agents and workflows for analysis, planning, architecture, and implementation.",
"license": "MIT",
"homepage": "https://github.com/bmad-code-org/BMAD-METHOD",
"repository": "https://github.com/bmad-code-org/BMAD-METHOD",
"keywords": ["bmad", "agile", "ai", "orchestrator", "development", "methodology", "agents"],
"plugins": [
{
"name": "bmad-pro-skills",
"source": "./",
"description": "Next level skills for power users — advanced prompting techniques, agent management, and more.",
"version": "6.3.0",
"author": {
"name": "Brian (BMad) Madison"
},
"skills": [
"./src/core-skills/bmad-help",
"./src/core-skills/bmad-brainstorming",
"./src/core-skills/bmad-distillator",
"./src/core-skills/bmad-party-mode",
"./src/core-skills/bmad-shard-doc",
"./src/core-skills/bmad-advanced-elicitation",
"./src/core-skills/bmad-editorial-review-prose",
"./src/core-skills/bmad-editorial-review-structure",
"./src/core-skills/bmad-index-docs",
"./src/core-skills/bmad-review-adversarial-general",
"./src/core-skills/bmad-review-edge-case-hunter"
]
},
{
"name": "bmad-method-lifecycle",
"source": "./",
"description": "Full-lifecycle AI development framework — agents and workflows for product analysis, planning, architecture, and implementation.",
"version": "6.3.0",
"author": {
"name": "Brian (BMad) Madison"
},
"skills": [
"./src/bmm-skills/1-analysis/bmad-product-brief",
"./src/bmm-skills/1-analysis/bmad-agent-analyst",
"./src/bmm-skills/1-analysis/bmad-agent-tech-writer",
"./src/bmm-skills/1-analysis/bmad-document-project",
"./src/bmm-skills/1-analysis/research/bmad-domain-research",
"./src/bmm-skills/1-analysis/research/bmad-market-research",
"./src/bmm-skills/1-analysis/research/bmad-technical-research",
"./src/bmm-skills/2-plan-workflows/bmad-agent-pm",
"./src/bmm-skills/2-plan-workflows/bmad-agent-ux-designer",
"./src/bmm-skills/2-plan-workflows/bmad-create-prd",
"./src/bmm-skills/2-plan-workflows/bmad-edit-prd",
"./src/bmm-skills/2-plan-workflows/bmad-validate-prd",
"./src/bmm-skills/2-plan-workflows/bmad-create-ux-design",
"./src/bmm-skills/3-solutioning/bmad-agent-architect",
"./src/bmm-skills/3-solutioning/bmad-create-architecture",
"./src/bmm-skills/3-solutioning/bmad-check-implementation-readiness",
"./src/bmm-skills/3-solutioning/bmad-create-epics-and-stories",
"./src/bmm-skills/3-solutioning/bmad-generate-project-context",
"./src/bmm-skills/4-implementation/bmad-agent-dev",
"./src/bmm-skills/4-implementation/bmad-dev-story",
"./src/bmm-skills/4-implementation/bmad-quick-dev",
"./src/bmm-skills/4-implementation/bmad-sprint-planning",
"./src/bmm-skills/4-implementation/bmad-sprint-status",
"./src/bmm-skills/4-implementation/bmad-code-review",
"./src/bmm-skills/4-implementation/bmad-create-story",
"./src/bmm-skills/4-implementation/bmad-correct-course",
"./src/bmm-skills/4-implementation/bmad-retrospective",
"./src/bmm-skills/4-implementation/bmad-qa-generate-e2e-tests"
]
}
]
}

View File

@ -1,6 +0,0 @@
---
name: bmad-os-audit-file-refs
description: Audit BMAD source files for file-reference convention violations using parallel Haiku subagents. Use when users requests an "audit file references" for a skill, workflow or task.
---
Read `prompts/instructions.md` and execute.

View File

@ -1,59 +0,0 @@
# audit-file-refs
Audit new-format BMAD source files for file-reference convention violations using parallel Haiku subagents.
## Convention
In new-format BMAD workflow and task files (`src/bmm/`, `src/core/`, `src/utility/`), every file path reference must use one of these **valid** forms:
- `{project-root}/_bmad/path/to/file.ext` — canonical form, always correct
- `{installed_path}/relative/path` — valid in new-format step files (always defined by workflow.md before any step is reached)
- Template/runtime variables: `{nextStepFile}`, `{workflowFile}`, `{{mustache}}`, `{output_folder}`, `{communication_language}`, etc. — skip these, they are substituted at runtime
**Flag any reference that uses:**
- `./step-NN.md` or `../something.md` — relative paths
- `step-NN.md` — bare filename with no path prefix
- `steps/step-NN.md` — bare steps-relative path (missing `{project-root}/_bmad/...` prefix)
- `` `_bmad/core/tasks/help.md` `` — bare `_bmad/` path (missing `{project-root}/`)
- `/Users/...`, `/home/...`, `C:\...` — absolute system paths
References inside fenced code blocks (``` ``` ```) are examples — skip them.
Old-format files in `src/bmm/workflows/4-implementation/` use `{installed_path}` by design within the XML calling chain — exclude that directory entirely.
## Steps
1. Run this command to get the file list:
```
find src/bmm src/core src/utility -type f \( -name "*.md" -o -name "*.yaml" \) | grep -v "4-implementation" | sort
```
2. Divide the resulting file paths into batches of roughly 20 files each.
3. For each batch, spawn a subagent (`subagent_type: "Explore"`, `model: "haiku"`) with this prompt (fill in the actual file paths):
> Read each of these files (use the Read tool on each):
> [list the file paths from this batch]
>
> For each file, identify every line that contains a file path reference that violates the convention described below. Skip references inside fenced code blocks. Skip template variables (anything containing `{` that isn't `{project-root}` or `{installed_path}`).
>
> **Valid references:** `{project-root}/_bmad/...`, `{installed_path}/...`, template variables.
> **Flag:** bare filenames (`step-NN.md`), `./` or `../` relative paths, bare `steps/` paths, bare `_bmad/` paths (without `{project-root}/`), absolute system paths.
>
> Return findings as a list:
> `path/to/file.md:LINE_NUMBER | VIOLATION_TYPE | offending text`
>
> If a file has no violations, include it as: `path/to/file.md | clean`
>
> End your response with a single line: `FILES CHECKED: N` where N is the exact number of files you read.
4. Collect all findings from all subagents.
5. **Self-check before reporting:** Count the total number of files returned by the `find` command. Sum the `FILES CHECKED: N` values across all subagent responses. If the totals do not match, identify which files are missing and re-run subagents for those files before proceeding. Do not produce the final report until all files are accounted for.
6. Output a final report:
- Group findings by violation type
- List each finding as `file:line — offending text`
- Show total count of violations and number of affected files
- If nothing found, say "All files conform to the convention."

View File

@ -1,177 +0,0 @@
---
name: bmad-os-changelog-social
description: Generate social media announcements for Discord, Twitter, and LinkedIn from the latest changelog entry. Use when user asks to 'create release announcement' or 'create social posts' or share changelog updates.
---
# Changelog Social
Generate engaging social media announcements from changelog entries.
## Workflow
### Step 1: Extract Changelog Entry
Read `./CHANGELOG.md` and extract the latest version entry. The changelog follows this format:
```markdown
## [VERSION]
### 🎁 Features
* **Title** — Description
### 🐛 Bug Fixes
* **Title** — Description
### 📚 Documentation
* **Title** — Description
### 🔧 Maintenance
* **Title** — Description
```
Parse:
- **Version number** (e.g., `6.0.0-Beta.5`)
- **Features** - New functionality, enhancements
- **Bug Fixes** - Fixes users will care about
- **Documentation** - New or improved docs
- **Maintenance** - Dependency updates, tooling improvements
### Step 2: Get Git Contributors
Use git log to find contributors since the previous version. Get commits between the current version tag and the previous one:
```bash
# Find the previous version tag first
git tag --sort=-version:refname | head -5
# Get commits between versions with PR numbers and authors
git log <previous-tag>..<current-tag> --pretty=format:"%h|%s|%an" --grep="#"
```
Extract PR numbers from commit messages that contain `#` followed by digits. Compile unique contributors.
### Step 3: Generate Discord Announcement
**Limit: 2,000 characters per message.** Split into multiple messages if needed.
Use this template style:
```markdown
🚀 **BMad vVERSION RELEASED!**
🎉 [Brief hype sentence]
🪥 **KEY HIGHLIGHT** - [One-line summary]
🎯 **CATEGORY NAME**
• Feature one - brief description
• Feature two - brief description
• Coming soon: Future teaser
🔧 **ANOTHER CATEGORY**
• Fix or feature
• Another item
📚 **DOCS OR OTHER**
• Item
• Item with link
🌟 **COMMUNITY PHILOSOPHY** (optional - include for major releases)
• Everything is FREE - No paywalls
• Knowledge shared, not sold
📊 **STATS**
X commits | Y PRs merged | Z files changed
🙏 **CONTRIBUTORS**
@username1 (X PRs!), @username2 (Y PRs!)
@username3, @username4, username5 + dependabot 🛡️
Community-driven FTW! 🌟
📦 **INSTALL:**
`npx bmad-method@VERSION install`
⭐ **SUPPORT US:**
🌟 GitHub: github.com/bmad-code-org/BMAD-METHOD/
📺 YouTube: youtube.com/@BMadCode
☕ Donate: buymeacoffee.com/bmad
🔥 **Next version tease!**
```
**Content Strategy:**
- Focus on **user impact** - what's better for them?
- Highlight **annoying bugs fixed** that frustrated users
- Show **new capabilities** that enable workflows
- Keep it **punchy** - use emojis and short bullets
- Add **personality** - excitement, humor, gratitude
### Step 4: Generate Twitter Post
**Limit: 25,000 characters per tweet (Premium).** With Premium, use a single comprehensive post matching the Discord style (minus Discord-specific formatting). Aim for 1,500-3,000 characters for better engagement.
**Threads are optional** — only use for truly massive releases where you want multiple engagement points.
See `examples/twitter-example.md` for the single-post Premium format.
## Content Selection Guidelines
**Include:**
- New features that change workflows
- Bug fixes for annoying/blocking issues
- Documentation that helps users
- Performance improvements
- New agents or workflows
- Breaking changes (call out clearly)
**Skip/Minimize:**
- Internal refactoring
- Dependency updates (unless user-facing)
- Test improvements
- Minor style fixes
**Emphasize:**
- "Finally fixed" issues
- "Faster" operations
- "Easier" workflows
- "Now supports" capabilities
## Examples
Reference example posts in `examples/` for tone and formatting guidance:
- **discord-example.md** — Full Discord announcement with emojis, sections, contributor shout-outs
- **twitter-example.md** — Twitter thread format (5 tweets max for major releases)
- **linkedin-example.md** — Professional post for major/minor releases with significant features
**When to use LinkedIn:**
- Major version releases (e.g., v6.0.0 Beta, v7.0.0)
- Minor releases with exceptional new features
- Community milestone announcements
Read the appropriate example file before generating to match the established style and voice.
## Output Format
**CRITICAL: ALWAYS write to files** - Create files in `_bmad-output/social/` directory:
1. `{repo-name}-discord-{version}.md` - Discord announcement
2. `{repo-name}-twitter-{version}.md` - Twitter post
3. `{repo-name}-linkedin-{version}.md` - LinkedIn post (if applicable)
Also present a preview in the chat:
```markdown
## Discord Announcement
[paste Discord content here]
## Twitter Post
[paste Twitter content here]
```
Files created:
- `_bmad-output/social/{filename}`
Offer to make adjustments if the user wants different emphasis, tone, or content.

View File

@ -1,53 +0,0 @@
🚀 **BMad v6.0.0-alpha.23 RELEASED!**
🎉 Huge update - almost beta!
🪟 **WINDOWS INSTALLER FIXED** - Menu arrows issue should be fixed! CRLF & ESM problems resolved.
🎯 **PRD WORKFLOWS IMPROVED**
• Validation & Edit workflows added!
• PRD Cohesion check ensures document flows beautifully
• Coming soon: Use of subprocess optimization (context saved!)
• Coming soon: Final format polish step in all workflows - Human consumption OR hyper-optimized LLM condensed initially!
🔧 **WORKFLOW CREATOR & VALIDATOR**
• Subprocess support for advanced optimization
• Path violation checks ensure integrity
• Beyond error checking - offers optimization & flow suggestions!
📚 **NEW DOCS SITE** - docs.bmad-method.org
• Diataxis framework: Tutorials, How-To, Explanations, References
• Current docs still being revised
• Tutorials, blogs & explainers coming soon!
💡 **BRAINSTORMING REVOLUTION**
• 100+ idea goal (quantity-first!)
• Anti-bias protocol (pivot every 10 ideas)
• Chain-of-thought + simulated temperature prompts
• Coming soon: SubProcessing (on-the-fly sub agents)
🌟 **COMMUNITY PHILOSOPHY**
• Everything is FREE - No paywalls, no gated content
• Knowledge shared, not sold
• No premium tiers - full access to our ideas
📊 **27 commits | 217 links converted | 42+ docs created**
🙏 **17 Community PR Authors in this release!**
@lum (6 PRs!), @q00 (3 PRs!), @phil (2 PRs!)
@mike, @alex, @ramiz, @sjennings + dependabot 🛡️
Community-driven FTW! 🌟
📦 **INSTALL ALPHA:**
`npx bmad-method install`
⭐ **SUPPORT US:**
🌟 GitHub: github.com/bmad-code-org/BMAD-METHOD/
📺 YouTube: youtube.com/@BMadCode
🎤 **SPEAKING & MEDIA**
Available for conferences, podcasts, media appearances!
Topics: AI-Native Organizations (Any Industry), BMad Method
DM on Discord for inquiries!
🔥 **V6 Beta is DAYS away!** January 22nd ETA - new features such as xyz and abc bug fixes!

View File

@ -1,49 +0,0 @@
🚀 **Announcing BMad Method v6.0.0 Beta - AI-Native Agile Development Framework**
I'm excited to share that BMad Method, the open-source AI-driven agile development framework, is entering Beta! After 27 alpha releases and countless community contributions, we're approaching a major milestone.
**What's New in v6.0.0-alpha.23**
🪟 **Windows Compatibility Fixed**
We've resolved the installer issues that affected Windows users. The menu arrows problem, CRLF handling, and ESM compatibility are all resolved.
🎯 **Enhanced PRD Workflows**
Our Product Requirements Document workflows now include validation and editing capabilities, with a new cohesion check that ensures your documents flow beautifully. Subprocess optimization is coming soon to save even more context.
🔧 **Workflow Creator & Validator**
New tools for creating and validating workflows with subprocess support, path violation checks, and optimization suggestions that go beyond simple error checking.
📚 **New Documentation Platform**
We've launched docs.bmad-method.org using the Diataxis framework - providing clear separation between tutorials, how-to guides, explanations, and references. Our documentation is being continuously revised and expanded.
💡 **Brainstorming Revolution**
Our brainstorming workflows now use research-backed techniques: 100+ idea goals, anti-bias protocols, chain-of-thought reasoning, and simulated temperature prompts for higher divergence.
**Our Philosophy**
Everything in BMad Method is FREE. No paywalls, no gated content, no premium tiers. We believe knowledge should be shared, not sold. This is community-driven development at its finest.
**The Stats**
- 27 commits in this release
- 217 documentation links converted
- 42+ new documents created
- 17 community PR authors contributed
**Get Started**
```
npx bmad-method@alpha install
```
**Learn More**
- GitHub: github.com/bmad-code-org/BMAD-METHOD
- YouTube: youtube.com/@BMadCode
- Docs: docs.bmad-method.org
**What's Next?**
Beta is just days away with an ETA of January 22nd. We're also available for conferences, podcasts, and media appearances to discuss AI-Native Organizations and the BMad Method.
Have you tried BMad Method yet? I'd love to hear about your experience in the comments!
#AI #SoftwareDevelopment #Agile #OpenSource #DevTools #LLM #AgentEngineering

View File

@ -1,55 +0,0 @@
🚀 **BMad v6.0.0-alpha.23 RELEASED!**
Huge update - we're almost at Beta! 🎉
🪟 **WINDOWS INSTALLER FIXED** - Menu arrows issue should be fixed! CRLF & ESM problems resolved.
🎯 **PRD WORKFLOWS IMPROVED**
• Validation & Edit workflows added!
• PRD Cohesion check ensures document flows beautifully
• Coming soon: Subprocess optimization (context saved!)
• Coming soon: Final format polish step in all workflows
🔧 **WORKFLOW CREATOR & VALIDATOR**
• Subprocess support for advanced optimization
• Path violation checks ensure integrity
• Beyond error checking - offers optimization & flow suggestions!
📚 **NEW DOCS SITE** - docs.bmad-method.org
• Diataxis framework: Tutorials, How-To, Explanations, References
• Current docs still being revised
• Tutorials, blogs & explainers coming soon!
💡 **BRAINSTORMING REVOLUTION**
• 100+ idea goal (quantity-first!)
• Anti-bias protocol (pivot every 10 ideas)
• Chain-of-thought + simulated temperature prompts
• Coming soon: SubProcessing (on-the-fly sub agents)
🌟 **COMMUNITY PHILOSOPHY**
• Everything is FREE - No paywalls, no gated content
• Knowledge shared, not sold
• No premium tiers - full access to our ideas
📊 **27 commits | 217 links converted | 42+ docs created**
🙏 **17 Community PR Authors in this release!**
@lum (6 PRs!), @q00 (3 PRs!), @phil (2 PRs!)
@mike, @alex, @ramiz, @sjennings + dependabot 🛡️
Community-driven FTW! 🌟
📦 **INSTALL ALPHA:**
`npx bmad-method install`
⭐ **SUPPORT US:**
🌟 GitHub: github.com/bmad-code-org/BMAD-METHOD/
📺 YouTube: youtube.com/@BMadCode
🎤 **SPEAKING & MEDIA**
Available for conferences, podcasts, media appearances!
Topics: AI-Native Organizations (Any Industry), BMad Method
DM on Discord for inquiries!
🔥 **V6 Beta is DAYS away!** January 22nd ETA!
#AI #DevTools #Agile #OpenSource #LLM #AgentEngineering

View File

@ -1,6 +0,0 @@
---
name: bmad-os-diataxis-style-fix
description: Fixes documentation to comply with Diataxis framework and BMad Method style guide rules. Use when user asks to check or fix style of files under the docs folder.
---
Read `prompts/instructions.md` and execute.

View File

@ -1,229 +0,0 @@
# Diataxis Style Fixer
Automatically fixes documentation to comply with the Diataxis framework and BMad Method style guide.
## CRITICAL RULES
- **NEVER commit or push changes** — let the user review first
- **NEVER make destructive edits** — preserve all content, only fix formatting
- **Use Edit tool** — make targeted fixes, not full file rewrites
- **Show summary** — after fixing, list all changes made
## Input
Documentation file path or directory to fix. Defaults to `docs/` if not specified.
## Step 1: Understand Diataxis Framework
**Diataxis** is a documentation framework that categorizes content into four types based on two axes:
| | **Learning** (oriented toward future) | **Doing** (oriented toward present) |
| -------------- | ----------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
| **Practical** | **Tutorials** — lessons that guide learners through achieving a specific goal | **How-to guides** — step-by-step instructions for solving a specific problem |
| **Conceptual** | **Explanation** — content that clarifies and describes underlying concepts | **Reference** — technical descriptions, organized for lookup |
**Key principles:**
- Each document type serves a distinct user need
- Don't mix types — a tutorial shouldn't explain concepts deeply
- Focus on the user's goal, not exhaustive coverage
- Structure follows purpose (tutorials are linear, reference is scannable)
## Step 2: Read the Style Guide
Read the project's style guide at `docs/_STYLE_GUIDE.md` to understand all project-specific conventions.
## Step 3: Detect Document Type
Based on file location, determine the document type:
| Location | Diataxis Type |
| -------------------- | -------------------- |
| `/docs/tutorials/` | Tutorial |
| `/docs/how-to/` | How-to guide |
| `/docs/explanation/` | Explanation |
| `/docs/reference/` | Reference |
| `/docs/glossary/` | Reference (glossary) |
## Step 4: Find and Fix Issues
For each markdown file, scan for issues and fix them:
### Universal Fixes (All Doc Types)
**Horizontal Rules (`---`)**
- Remove any `---` outside of YAML frontmatter
- Replace with `##` section headers or admonitions as appropriate
**`####` Headers**
- Replace with bold text: `#### Header``**Header**`
- Or convert to admonition if it's a warning/notice
**"Related" or "Next:" Sections**
- Remove entire section including links
- The sidebar handles navigation
**Deeply Nested Lists**
- Break into sections with `##` headers
- Flatten to max 3 levels
**Code Blocks for Dialogue/Examples**
- Convert to admonitions:
```
:::note[Example]
[content]
:::
```
**Bold Paragraph Callouts**
- Convert to admonitions with appropriate type
**Too Many Admonitions**
- Limit to 1-2 per section (tutorials allow 3-4 per major section)
- Consolidate related admonitions
- Remove less critical ones if over limit
**Table Cells / List Items > 2 Sentences**
- Break into multiple rows/cells
- Or shorten to 1-2 sentences
**Header Budget Exceeded**
- Merge related sections
- Convert some `##` to `###` subsections
- Goal: 8-12 `##` per doc; 2-3 `###` per section
### Type-Specific Fixes
**Tutorials** (`/docs/tutorials/`)
- Ensure hook describes outcome in 1-2 sentences
- Add "What You'll Learn" bullet section if missing
- Add `:::note[Prerequisites]` if missing
- Add `:::tip[Quick Path]` TL;DR at top if missing
- Use tables for phases, commands, agents
- Add "What You've Accomplished" section if missing
- Add Quick Reference table if missing
- Add Common Questions section if missing
- Add Getting Help section if missing
- Add `:::tip[Key Takeaways]` at end if missing
**How-To** (`/docs/how-to/`)
- Ensure hook starts with "Use the `X` workflow to..."
- Add "When to Use This" with 3-5 bullets if missing
- Add `:::note[Prerequisites]` if missing
- Ensure steps are numbered `###` with action verbs
- Add "What You Get" describing outputs if missing
**Explanation** (`/docs/explanation/`)
- Ensure hook states what document explains
- Organize content into scannable `##` sections
- Add comparison tables for 3+ options
- Link to how-to guides for procedural questions
- Limit to 2-3 admonitions per document
**Reference** (`/docs/reference/`)
- Ensure hook states what document references
- Ensure structure matches reference type
- Use consistent item structure throughout
- Use tables for structured/comparative data
- Link to explanation docs for conceptual depth
- Limit to 1-2 admonitions per document
**Glossary** (`/docs/glossary/` or glossary files)
- Ensure categories as `##` headers
- Ensure terms in tables (not individual headers)
- Definitions 1-2 sentences max
- Bold term names in cells
## Step 5: Apply Fixes
For each file with issues:
1. Read the file
2. Use Edit tool for each fix
3. Track what was changed
## Step 6: Summary
After processing all files, output a summary:
```markdown
# Style Fixes Applied
**Files processed:** N
**Files modified:** N
## Changes Made
### `path/to/file.md`
- Removed horizontal rule at line 45
- Converted `####` headers to bold text
- Added `:::tip[Quick Path]` admonition
- Consolidated 3 admonitions into 2
### `path/to/other.md`
- Removed "Related:" section
- Fixed table cell length (broke into 2 rows)
## Review Required
Please review the changes. When satisfied, commit and push as needed.
```
## Common Patterns
**Converting `####` to bold:**
```markdown
#### Important Note
Some text here.
```
```markdown
**Important Note**
Some text here.
```
**Removing horizontal rule:**
```markdown
Some content above.
---
Some content below.
```
```markdown
Some content above.
## [Descriptive Section Header]
Some content below.
```
**Converting code block to admonition:**
```markdown
```
User: What should I do?
Agent: Run the workflow.
```
```
```markdown
:::note[Example]
**User:** What should I do?
**Agent:** Run the workflow.
:::
```
**Converting bold paragraph to admonition:**
```markdown
**IMPORTANT:** This is critical that you read this before proceeding.
```
```markdown
:::caution[Important]
This is critical that you read this before proceeding.
:::
```

View File

@ -1,6 +0,0 @@
---
name: bmad-os-draft-changelog
description: "Analyzes changes since last release and updates CHANGELOG.md ONLY. Use when users requests 'update the changelog' or 'prepare changelog release notes'"
---
Read `prompts/instructions.md` and execute.

View File

@ -1,82 +0,0 @@
# Draft Changelog Execution
## ⚠️ IMPORTANT - READ FIRST
**This skill ONLY updates CHANGELOG.md. That is its entire purpose.**
- **DO** update CHANGELOG.md with the new version entry
- **DO** present the draft for user review before editing
- **DO NOT** trigger any GitHub release workflows
- **DO NOT** run any other skills or workflows automatically
- **DO NOT** make any commits
After the changelog is complete, you may suggest the user can run `/release-module` if they want to proceed with the actual release — but NEVER trigger it yourself.
## Input
Project path (or run from project root)
## Step 1: Identify Current State
- Get the latest released tag
- Get current version
- Verify there are commits since the last release
## Step 2: Launch Explore Agent
Use `thoroughness: "very thorough"` to analyze all changes since the last release tag.
**Key: For each merge commit, look up the merged PR/issue that was closed.**
- Use `gh pr view` or git commit body to find the PR number
- Read the PR description and comments to understand full context
- Don't rely solely on commit merge messages - they lack context
**Analyze:**
1. **All merges/commits** since the last tag
2. **For each merge, read the original PR/issue** that was closed
3. **Files changed** with statistics
4. **Categorize changes:**
- 🎁 **Features** - New functionality, new agents, new workflows
- 🐛 **Bug Fixes** - Fixed bugs, corrected issues
- ♻️ **Refactoring** - Code improvements, reorganization
- 📚 **Documentation** - Docs updates, README changes
- 🔧 **Maintenance** - Dependency updates, tooling, infrastructure
- 💥 **Breaking Changes** - Changes that may affect users
**Provide:**
- Comprehensive summary of ALL changes with PR context
- Categorization of each change
- Identification of breaking changes
- Significance assessment (major/minor/trivial)
## Step 3: Generate Draft Changelog
Format:
```markdown
## v0.X.X - [Date]
* [Change 1 - categorized by type]
* [Change 2]
```
Guidelines:
- Present tense ("Fix bug" not "Fixed bug")
- Most significant changes first
- Group related changes
- Clear, concise language
- For breaking changes, clearly indicate impact
## Step 4: Present Draft & Update CHANGELOG.md
Show the draft with current version, last tag, commit count, and options to edit/retry.
When user accepts:
1. Update CHANGELOG.md with the new entry (insert at top, after `# Changelog` header)
2. STOP. That's it. You're done.
You may optionally suggest: *"When ready, you can run `/release-module` to create the actual release."*
**DO NOT:**
- Trigger any GitHub workflows
- Run any other skills
- Make any commits
- Do anything beyond updating CHANGELOG.md

View File

@ -1,6 +0,0 @@
---
name: bmad-os-findings-triage
description: Orchestrate HITL triage of review findings using parallel agents. Use when the user says 'triage these findings' or 'run findings triage' or has a batch of review findings to process.
---
Read `prompts/instructions.md` and execute.

View File

@ -1,104 +0,0 @@
# Finding Agent: {{TASK_ID}} — {{TASK_SUBJECT}}
You are a finding agent in the `{{TEAM_NAME}}` triage team. You own exactly one finding and will shepherd it through research, planning, human conversation, and a final decision.
## Your Assignment
- **Task:** `{{TASK_ID}}`
- **Finding:** `{{FINDING_ID}}` — {{FINDING_TITLE}}
- **Severity:** {{SEVERITY}}
- **Team:** `{{TEAM_NAME}}`
- **Team Lead:** `{{TEAM_LEAD_NAME}}`
## Phase 1 — Research (autonomous)
1. Read your task details with `TaskGet("{{TASK_ID}}")`.
2. Read the relevant source files to understand the finding in context:
{{FILE_LIST}}
If no specific files are listed above, use codebase search to locate code relevant to the finding.
If a context document was provided:
- Also read this context document for background: {{CONTEXT_DOC}}
If an initial triage was provided:
- **Note:** The team lead triaged this as **{{INITIAL_TRIAGE}}** — {{TRIAGE_RATIONALE}}. Evaluate whether this triage is correct and incorporate your assessment into your plan.
**Rules for research:**
- Work autonomously. Do not ask the team lead or the human for help during research.
- Use `Read`, `Grep`, `Glob`, and codebase search tools to understand the codebase.
- Trace call chains, check tests, read related code — be thorough.
- Form your own opinion on whether this finding is real, a false positive, or somewhere in between.
## Phase 2 — Plan (display only)
Prepare a plan for dealing with this finding. The plan MUST cover:
1. **Assessment** — Is this finding real? What is the actual risk or impact?
2. **Recommendation** — One of: fix it, accept the risk (wontfix), dismiss as not a real issue, or reject as a false positive.
3. **If recommending a fix:** Describe the specific changes — which files, what modifications, why this approach.
4. **If recommending against fixing:** Explain the reasoning — existing mitigations, acceptable risk, false positive rationale.
**Display the plan in your output.** Write it clearly so the human can read it directly. Follow the plan with a 2-5 line summary of the finding itself.
**CRITICAL: Do NOT send your plan or analysis to the team lead.** The team lead does not need your plan — the human reads it from your output stream. Sending full plans to the team lead wastes its context window.
## Phase 3 — Signal Ready
After displaying your plan, send exactly this to the team lead:
```
SendMessage({
type: "message",
recipient: "{{TEAM_LEAD_NAME}}",
content: "{{FINDING_ID}} ready for HITL",
summary: "{{FINDING_ID}} ready for review"
})
```
Then **stop and wait**. Do not proceed until the human engages with you.
## Phase 4 — HITL Conversation
The human will review your plan and talk to you directly. This is a real conversation, not a rubber stamp:
- The human may agree immediately, push back, ask questions, or propose alternatives.
- Answer questions thoroughly. Refer back to specific code you read.
- If the human wants a fix, **apply it** — edit the source files, verify the change makes sense.
- If the human disagrees with your assessment, update your recommendation.
- Stay focused on THIS finding only. Do not discuss other findings.
- **Do not send a decision until the human explicitly states a verdict.** Acknowledging your plan is NOT a decision. Wait for clear direction like "fix it", "dismiss", "reject", "skip", etc.
## Phase 5 — Report Decision
When the human reaches a decision, send exactly ONE message to the team lead:
```
SendMessage({
type: "message",
recipient: "{{TEAM_LEAD_NAME}}",
content: "DECISION {{FINDING_ID}} {{TASK_ID}} [CATEGORY] | [one-sentence summary]",
summary: "{{FINDING_ID}} [CATEGORY]"
})
```
Where `[CATEGORY]` is one of:
| Category | Meaning |
|----------|---------|
| **SKIP** | Human chose to skip without full review. |
| **DEFER** | Human chose to defer to a later session. |
| **FIX** | Change applied. List the file paths changed and what each change was (use a parseable format: `files: path1, path2`). |
| **WONTFIX** | Real finding, not worth fixing now. State why. |
| **DISMISS** | Not a real finding or mitigated by existing design. State the mitigation. |
| **REJECT** | False positive from the reviewer. State why it is wrong. |
After sending the decision, **go idle and wait for shutdown**. Do not take any further action. The team lead will send you a shutdown request — approve it.
## Rules
- You own ONE finding. Do not touch files unrelated to your finding unless required for the fix.
- Your plan is for the human's eyes — display it in your output, never send it to the team lead.
- Your only messages to the team lead are: (1) ready for HITL, (2) final decision. Nothing else.
- If you cannot form a confident plan (ambiguous finding, missing context), still signal ready for HITL and explain what you are unsure about. The HITL conversation will resolve it.
- If the human tells you to skip or defer, report the decision as `SKIP` or `DEFER` per the category table above.
- When you receive a shutdown request, approve it immediately.

View File

@ -1,286 +0,0 @@
# Findings Triage — Team Lead Orchestration
You are the team lead for a findings triage session. Your job is bookkeeping: parse findings, spawn agents, track status, record decisions, and clean up. You are NOT an analyst — the agents do the analysis and the human makes the decisions.
**Be minimal.** Short confirmations. No editorializing. No repeating what agents already said.
---
## Phase 1 — Setup
### 1.1 Determine Input Source
The human will provide findings in one of three ways:
1. **A findings report file** — a markdown file with structured findings. Read the file.
2. **A pre-populated task list** — tasks already exist. Call `TaskList` to discover them.
- If tasks are pre-populated: skip section 1.2 (parsing) and section 1.4 (task creation). Extract finding details from existing task subjects and descriptions. Number findings based on task order. Proceed from section 1.3 (pre-spawn checks).
3. **Inline findings** — pasted directly in conversation. Parse them.
Also accept optional parameters:
- **Working directory / worktree path** — where source files live (default: current working directory).
- **Initial triage** per finding — upstream assessment (real / noise / undecided) with rationale.
- **Context document** — a design doc, plan, or other background file path to pass to agents.
### 1.2 Parse Findings
Extract from each finding:
- **Title / description**
- **Severity** (Critical / High / Medium / Low)
- **Relevant file paths**
- **Initial triage** (if provided)
Number findings sequentially: F1, F2, ... Fn. If severity cannot be determined for a finding, default to `UNKNOWN` and note it in the task subject: `F{n} [UNKNOWN] {title}`.
**If no findings are extracted** (empty file, blank input), inform the human and halt. Do not proceed to task creation or team setup.
**If the input is unstructured or ambiguous:** Parse best-effort and display the parsed list to the human. Ask for confirmation before proceeding. Do NOT spawn agents until confirmed.
### 1.3 Pre-Spawn Checks
**Large batch (>25 findings):**
HALT. Tell the human:
> "There are {N} findings. Spawning {N} agents at once may overwhelm the system. I recommend processing in waves of ~20. Proceed with all at once, or batch into waves?"
Wait for the human to decide. If batching, record wave assignments (Wave 1: F1-F20, Wave 2: F21-Fn).
**Same-file conflicts:**
Scan all findings for overlapping file paths. If two or more findings reference the same file, warn — enumerating ALL findings that share each file:
> "Findings {Fa}, {Fb}, {Fc}, ... all reference `{file}`. Concurrent edits may conflict. Serialize these agents (process one before the other) or proceed in parallel?"
Wait for the human to decide. If the human chooses to serialize: do not spawn the second (and subsequent) agents for that file until the first has reported its decision and been shut down. Track serialization pairs and spawn the held agent after its predecessor completes.
### 1.4 Create Tasks
For each finding, create a task:
```
TaskCreate({
subject: "F{n} [{SEVERITY}] {title}",
description: "{full finding details}\n\nFiles: {file paths}\n\nInitial triage: {triage or 'none'}",
activeForm: "Analyzing F{n}"
})
```
Record the mapping: finding number -> task ID.
### 1.5 Create Team
```
TeamCreate({
team_name: "{review-type}-triage",
description: "HITL triage of {N} findings from {source}"
})
```
Use a contextual name based on the review type (e.g., `pr-review-triage`, `prompt-audit-triage`, `code-review-triage`). If unsure, use `findings-triage`.
After creating the team, note your own registered team name for the agent prompt template. Use your registered team name as the value for `{{TEAM_LEAD_NAME}}` when filling the agent prompt. If unsure of your name, read the team config at `~/.claude/teams/{team-name}/config.json` to find your own entry in the members list.
### 1.6 Spawn Agents
Read the agent prompt template from `prompts/agent-prompt.md`.
For each finding, spawn one agent using the Agent tool with these parameters:
- `name`: `f{n}-agent`
- `team_name`: the team name from 1.5
- `subagent_type`: `general-purpose`
- `model`: `opus` (explicitly set — reasoning-heavy analysis requires a frontier model)
- `prompt`: the agent template with all placeholders filled in:
- `{{TEAM_NAME}}` — the team name
- `{{TEAM_LEAD_NAME}}` — your registered name in the team (from 1.5)
- `{{TASK_ID}}` — the task ID from 1.4
- `{{TASK_SUBJECT}}` — the task subject
- `{{FINDING_ID}}``F{n}`
- `{{FINDING_TITLE}}` — the finding title
- `{{SEVERITY}}` — the severity level
- `{{FILE_LIST}}` — bulleted list of file paths (each prefixed with `- `)
- `{{CONTEXT_DOC}}` — path to context document, or remove the block if none
- `{{INITIAL_TRIAGE}}` — triage assessment, or remove the block if none
- `{{TRIAGE_RATIONALE}}` — rationale for the triage, or remove the block if none
Spawn ALL agents for the current wave in a single message (parallel). If batching, spawn only the current wave.
After spawning, print:
```
All {N} agents spawned. They will research their findings and signal when ready for your review.
```
Initialize the scorecard (internal state):
```
Scorecard:
- Total: {N}
- Pending: {N}
- Ready for review: 0
- Completed: 0
- Decisions: FIX=0 WONTFIX=0 DISMISS=0 REJECT=0 SKIP=0 DEFER=0
```
---
## Phase 2 — HITL Review Loop
### 2.1 Track Agent Readiness
Agents will send messages matching: `F{n} ready for HITL`
When received:
- Note which finding is ready.
- Update the internal status tracker.
- Print a short status line: `F{n} ready. ({ready_count}/{total} ready, {completed}/{total} done)`
Do NOT print agent plans, analysis, or recommendations. The human reads those directly from the agent output.
### 2.2 Status Dashboard
When the human asks for status (or periodically when useful), print:
```
=== Triage Status ===
Ready for review: F3, F7, F11
Still analyzing: F1, F5, F9
Completed: F2 (FIX), F4 (DISMISS), F6 (REJECT)
{completed}/{total} done
===
```
Keep it compact. No decoration beyond what is needed.
### 2.3 Process Decisions
Agents will send messages matching: `DECISION F{n} {task_id} [CATEGORY] | [summary]`
When received:
1. **Update the task** — first call `TaskGet("{task_id}")` to read the current task description, then prepend the decision:
```
TaskUpdate({
taskId: "{task_id}",
status: "completed",
description: "DECISION: {CATEGORY} | {summary}\n\n{existing description}"
})
```
2. **Update the scorecard** — increment the decision category counter. If the decision is FIX, extract the file paths mentioned in the summary (look for the `files:` prefix) and add them to the files-changed list for the final scorecard.
3. **Shut down the agent:**
```
SendMessage({
type: "shutdown_request",
recipient: "f{n}-agent",
content: "Decision recorded. Shutting down."
})
```
4. **Print confirmation:** `F{n} closed: {CATEGORY}. {remaining} remaining.`
### 2.4 Human-Initiated Skip/Defer
If the human wants to skip or defer a finding without full engagement:
1. Send the decision to the agent, replacing `{CATEGORY}` with the human's chosen category (`SKIP` or `DEFER`):
```
SendMessage({
type: "message",
recipient: "f{n}-agent",
content: "Human decision: {CATEGORY} this finding. Report {CATEGORY} as your decision and go idle.",
summary: "F{n} {CATEGORY} directive"
})
```
2. Wait for the agent to report the decision back (it will send `DECISION F{n} ... {CATEGORY}`).
3. Process as a normal decision (2.3).
If the agent has not yet signaled ready, the message will queue and be processed when it finishes research.
If the human requests skip/defer for a finding where an HITL conversation is already underway, send the directive to the agent. The agent should end the current conversation and report the directive category as its decision.
### 2.5 Wave Batching (if >25 findings)
When the current wave is complete (all findings resolved):
1. Print wave summary.
2. Ask: `"Wave {W} complete. Spawn wave {W+1} ({count} findings)? (y/n)"`
3. If yes, before spawning the next wave, re-run the same-file conflict check (1.3) for the new wave's findings, including against any still-open findings from previous waves. Then repeat Phase 1.4 (task creation) and 1.6 (agent spawning) only. Do NOT call TeamCreate again — the team already exists.
4. If the human declines, treat unspawned findings as not processed. Proceed to Phase 3 wrap-up. Note the count of unprocessed findings in the final scorecard.
5. Carry the scorecard forward across waves.
---
## Phase 3 — Wrap-up
When all findings across all waves are resolved:
### 3.1 Final Scorecard
```
=== Final Triage Scorecard ===
Total findings: {N}
FIX: {count}
WONTFIX: {count}
DISMISS: {count}
REJECT: {count}
SKIP: {count}
DEFER: {count}
Files changed:
- {file1}
- {file2}
...
Findings:
F1 [{SEVERITY}] {title} — {DECISION}
F2 [{SEVERITY}] {title} — {DECISION}
...
=== End Triage ===
```
### 3.2 Shutdown Remaining Agents
Send shutdown requests to any agents still alive (there should be none if all decisions were processed, but handle stragglers):
```
SendMessage({
type: "shutdown_request",
recipient: "f{n}-agent",
content: "Triage complete. Shutting down."
})
```
### 3.3 Offer to Save
Ask the human:
> "Save the scorecard to a file? (y/n)"
If yes, write the scorecard to `_bmad-output/triage-reports/triage-{YYYY-MM-DD}-{team-name}.md`.
### 3.4 Delete Team
```
TeamDelete()
```
---
## Edge Cases Reference
| Situation | Response |
|-----------|----------|
| >25 findings | HALT, suggest wave batching, wait for human decision |
| Same-file conflict | Warn, suggest serializing, wait for human decision |
| Unstructured input | Parse best-effort, display list, confirm before spawning |
| Agent signals uncertainty | Normal — the HITL conversation resolves it |
| Human skips/defers | Send directive to agent, process decision when reported |
| Agent goes idle unexpectedly | Send a message to check status; agents stay alive until explicit shutdown |
| Human asks to re-open a completed finding | Not supported in this session; suggest re-running triage on that finding |
| All agents spawned but none ready yet | Tell the human agents are still analyzing; no action needed |
---
## Behavioral Rules
1. **Be minimal.** Short confirmations, compact dashboards. Do not repeat agent analysis.
2. **Never auto-close.** Every finding requires a human decision. No exceptions.
3. **One agent per finding.** Never batch multiple findings into one agent.
4. **Protect your context window.** Agents display plans in their output, not in messages to you. If an agent sends you a long message, acknowledge it briefly and move on.
5. **Track everything.** Finding number, task ID, agent name, decision, files changed. You are the single source of truth for the session.
6. **Respect the human's pace.** They review in whatever order they want. Do not rush them. Do not suggest which finding to review next unless asked.

View File

@ -1,6 +0,0 @@
---
name: bmad-os-gh-triage
description: Analyze all github issues. Use when the user says 'triage the github issues' or 'analyze open github issues'.
---
Read `prompts/instructions.md` and execute.

View File

@ -1,60 +0,0 @@
You are analyzing a batch of GitHub issues for deep understanding and triage.
**YOUR TASK:**
Read the issues in your batch and provide DEEP analysis:
1. **For EACH issue, analyze:**
- What is this ACTUALLY about? (beyond keywords)
- What component/system does it affect?
- What's the impact and severity?
- Is it a bug, feature request, or something else?
- What specific theme does it belong to?
2. **PRIORITY ASSESSMENT:**
- CRITICAL: Blocks users, security issues, data loss, broken installers
- HIGH: Major functionality broken, important features missing
- MEDIUM: Workarounds available, minor bugs, nice-to-have features
- LOW: Edge cases, cosmetic issues, questions
3. **RELATIONSHIPS:**
- Duplicates: Near-identical issues about the same problem
- Related: Issues connected by theme or root cause
- Dependencies: One issue blocks or requires another
**YOUR BATCH:**
[Paste the batch of issues here - each with number, title, body, labels]
**OUTPUT FORMAT (JSON only, no markdown):**
{
"issues": [
{
"number": 123,
"title": "issue title",
"deep_understanding": "2-3 sentences explaining what this is really about",
"affected_components": ["installer", "workflows", "docs"],
"issue_type": "bug/feature/question/tech-debt",
"priority": "CRITICAL/HIGH/MEDIUM/LOW",
"priority_rationale": "Why this priority level",
"theme": "installation/workflow/integration/docs/ide-support/etc",
"relationships": {
"duplicates_of": [456],
"related_to": [789, 101],
"blocks": [111]
}
}
],
"cross_repo_issues": [
{"number": 123, "target_repo": "bmad-builder", "reason": "about agent builder"}
],
"cleanup_candidates": [
{"number": 456, "reason": "v4-related/outdated/duplicate"}
],
"themes_found": {
"Installation Blockers": {
"count": 5,
"root_cause": "Common pattern if identifiable"
}
}
}
Return ONLY valid JSON. No explanations outside the JSON structure.

View File

@ -1,74 +0,0 @@
# GitHub Issue Triage with AI Analysis
**CRITICAL RULES:**
- NEVER include time or effort estimates in output or recommendations
- Focus on WHAT needs to be done, not HOW LONG it takes
- Use Bash tool with gh CLI for all GitHub operations
## Execution
### Step 1: Fetch Issues
Use `gh issue list --json number,title,body,labels` to fetch all open issues.
### Step 2: Batch Creation
Split issues into batches of ~10 issues each for parallel analysis.
### Step 3: Parallel Agent Analysis
For EACH batch, use the Task tool with `subagent_type=general-purpose` to launch an agent with prompt from `prompts/agent-prompt.md`
### Step 4: Consolidate & Generate Report
After all agents complete, create a comprehensive markdown report saved to `_bmad-output/triage-reports/triage-YYYY-MM-DD.md`
## Report Format
### Executive Summary
- Total issues analyzed
- Issue count by priority (CRITICAL, HIGH, MEDIUM, LOW)
- Major themes discovered
- Top 5 critical issues requiring immediate attention
### Critical Issues (CRITICAL Priority)
For each CRITICAL issue:
- **#123 - [Issue Title](url)**
- **What it's about:** [Deep understanding]
- **Affected:** [Components]
- **Why Critical:** [Rationale]
- **Suggested Action:** [Specific action]
### High Priority Issues (HIGH Priority)
Same format as Critical, grouped by theme.
### Theme Clusters
For each major theme:
- **Theme Name** (N issues)
- **What connects these:** [Pattern]
- **Root cause:** [If identifiable]
- **Consolidated actions:** [Bulk actions if applicable]
- **Issues:** #123, #456, #789
### Relationships & Dependencies
- **Duplicates:** List pairs with `gh issue close` commands
- **Related Issues:** Groups of related issues
- **Dependencies:** Blocking relationships
### Cross-Repo Issues
Issues that should be migrated to other repositories.
For each, provide:
```
gh issue close XXX --repo CURRENT_REPO --comment "This issue belongs in REPO. Please report at https://github.com/TARGET_REPO/issues/new"
```
### Cleanup Candidates
- **v4-related:** Deprecated version issues with close commands
- **Stale:** No activity >30 days
- **Low priority + old:** Low priority issues >60 days old
### Actionable Next Steps
Specific, prioritized actions:
1. [CRITICAL] Fix broken installer - affects all new users
2. [HIGH] Resolve Windows path escaping issues
3. [HIGH] Address workflow integration bugs
etc.
Include `gh` commands where applicable for bulk actions.

View File

@ -1,6 +0,0 @@
---
name: bmad-os-release-module
description: Perform requested version bump, git tag, npm publish, GitHub release. Use when user requests 'perform a release' only.
---
Read `prompts/instructions.md` and execute.

View File

@ -1,53 +0,0 @@
# Release BMad Module Execution
## Input
Project path (or run from project root)
## Execution Steps
### Step 1: Get Current State
- Verify git working tree is clean
- Get latest tag and current version
- Check for unpushed commits
### Step 2: Get Changelog Entry
Ask the user for the changelog entry (from draft-changelog skill or manual).
### Step 3: Confirm Changelog
Show project name, current version, proposed next version, and changelog. Get confirmation.
### Step 4: Confirm Version Bump Type
Ask what type of bump: patch, minor, major, prerelease, or custom.
### Step 5: Update CHANGELOG.md
Insert new entry at top, commit, and push.
### Step 6: Bump Version
Run `npm version` to update package.json, create commit, and create tag.
### Step 7: Push Tag
Push the new version tag to GitHub.
### Step 8: Publish to npm
Publish the package.
### Step 9: Create GitHub Release
Create release with changelog notes using `gh release create`.
## Error Handling
Stop immediately on any step failure. Inform user and suggest fix.
## Important Notes
- Wait for user confirmation before destructive operations
- Push changelog commit before version bump
- Use explicit directory paths in commands

View File

@ -1,6 +0,0 @@
---
name: bmad-os-review-pr
description: Adversarial PR review tool (Raven's Verdict). Cynical deep review transformed into professional engineering findings. Use when user asks to 'review a PR' and provides a PR url or id.
---
Read `prompts/instructions.md` and execute.

View File

@ -1,231 +0,0 @@
# Raven's Verdict - Deep PR Review Tool
A cynical adversarial review, transformed into cold engineering professionalism.
## CRITICAL: Sandboxed Execution Rules
Before proceeding, you MUST verify:
- [ ] PR number or URL was EXPLICITLY provided in the user's message
- [ ] You are NOT inferring the PR from conversation history
- [ ] You are NOT looking at git branches, recent commits, or local state
- [ ] You are NOT guessing or assuming any PR numbers
**If no explicit PR number/URL was provided, STOP immediately and ask:**
"What PR number or URL should I review?"
## Preflight Checks
### 0.1 Parse PR Input
Extract PR number from user input. Examples of valid formats:
- `123` (just the number)
- `#123` (with hash)
- `https://github.com/owner/repo/pull/123` (full URL)
If a URL specifies a different repository than the current one:
```bash
# Check current repo
gh repo view --json nameWithOwner -q '.nameWithOwner'
```
If mismatch detected, ask user:
> "This PR is from `{detected_repo}` but we're in `{current_repo}`. Proceed with reviewing `{detected_repo}#123`? (y/n)"
If user confirms, store `{REPO}` for use in all subsequent `gh` commands.
### 0.2 Ensure Clean Checkout
Verify the working tree is clean and check out the PR branch.
```bash
# Check for uncommitted changes
git status --porcelain
```
If output is non-empty, STOP and tell user:
> "You have uncommitted changes. Please commit or stash them before running a PR review."
If clean, fetch and checkout the PR branch:
```bash
# Fetch and checkout PR branch
# For cross-repo PRs, include --repo {REPO}
gh pr checkout {PR_NUMBER} [--repo {REPO}]
```
If checkout fails, STOP and report the error.
Now you're on the PR branch with full access to all files as they exist in the PR.
### 0.3 Check PR Size
```bash
# For cross-repo PRs, include --repo {REPO}
gh pr view {PR_NUMBER} [--repo {REPO}] --json additions,deletions,changedFiles -q '{"additions": .additions, "deletions": .deletions, "files": .changedFiles}'
```
**Size thresholds:**
| Metric | Warning Threshold |
| ------------- | ----------------- |
| Files changed | > 50 |
| Lines changed | > 5000 |
If thresholds exceeded, ask user:
> "This PR has {X} files and {Y} line changes. That's large.
>
> **[f] Focus** - Pick specific files or directories to review
> **[p] Proceed** - Review everything (may be slow/expensive)
> **[a] Abort** - Stop here"
### 0.4 Note Binary Files
```bash
# For cross-repo PRs, include --repo {REPO}
gh pr diff {PR_NUMBER} [--repo {REPO}] --name-only | grep -E '\.(png|jpg|jpeg|gif|ico|svg|woff|woff2|ttf|eot|pdf|zip|tar|gz|bin|exe|dll|so|dylib)$' || echo "No binary files detected"
```
Store list of binary files to skip. Note them in final output.
## Adversarial Review
### 1.1 Run Cynical Review
**INTERNAL PERSONA - Never post this directly:**
Task: You are a cynical, jaded code reviewer with zero patience for sloppy work. This PR was submitted by a clueless weasel and you expect to find problems. Find at least five issues to fix or improve in it. Number them. Be skeptical of everything. Ultrathink.
Output format:
```markdown
### [NUMBER]. [FINDING TITLE] [likely]
**Severity:** [EMOJI] [LEVEL]
[DESCRIPTION - be specific, include file:line references]
```
Severity scale:
| Level | Emoji | Meaning |
| -------- | ----- | ------------------------------------------------------- |
| Critical | 🔴 | Security issue, data loss risk, or broken functionality |
| Moderate | 🟡 | Bug, performance issue, or significant code smell |
| Minor | 🟢 | Style, naming, minor improvement opportunity |
Likely tag:
- Add `[likely]` to findings with high confidence, e.g. with direct evidence
- Sort findings by severity (Critical → Moderate → Minor), not by confidence
## Tone Transformation
**Transform the cynical output into cold engineering professionalism.**
**Transformation rules:**
1. Remove all inflammatory language, insults, assumptions about the author
2. Keep all technical substance, file references, severity ratings and likely tag
3. Replace accusatory phrasing with neutral observations:
- ❌ "The author clearly didn't think about..."
- ✅ "This implementation may not account for..."
4. Preserve skepticism as healthy engineering caution:
- ❌ "This will definitely break in production"
- ✅ "This pattern has historically caused issues in production environments"
5. Add the suggested fixes.
6. Keep suggestions actionable and specific
Output format after transformation:
```markdown
## PR Review: #{PR_NUMBER}
**Title:** {PR_TITLE}
**Author:** @{AUTHOR}
**Branch:** {HEAD} → {BASE}
---
### Findings
[TRANSFORMED FINDINGS HERE]
---
### Summary
**Critical:** {COUNT} | **Moderate:** {COUNT} | **Minor:** {COUNT}
[BINARY_FILES_NOTE if any]
---
_Review generated by Raven's Verdict. LLM-produced analysis - findings may be incorrect or lack context. Verify before acting._
```
## Post Review
### 3.1 Preview
Display the complete transformed review to the user.
```
══════════════════════════════════════════════════════
PREVIEW - This will be posted to PR #{PR_NUMBER}
══════════════════════════════════════════════════════
[FULL REVIEW CONTENT]
══════════════════════════════════════════════════════
```
### 3.2 Confirm
Ask user for explicit confirmation:
> **Ready to post this review to PR #{PR_NUMBER}?**
>
> **[y] Yes** - Post as comment
> **[n] No** - Abort, do not post
> **[e] Edit** - Let me modify before posting
> **[s] Save only** - Save locally, don't post
### 3.3 Post or Save
**Write review to a temp file, then post:**
1. Write the review content to a temp file with a unique name (include PR number to avoid collisions)
2. Post using `gh pr comment {PR_NUMBER} [--repo {REPO}] --body-file {path}`
3. Delete the temp file after successful post
Do NOT use heredocs or `echo` - Markdown code blocks will break shell parsing. Use your file writing tool instead.
**If auth fails or post fails:**
1. Display error prominently:
```
⚠️ FAILED TO POST REVIEW
Error: {ERROR_MESSAGE}
```
2. Keep the temp file and tell the user where it is, so they can post manually with:
`gh pr comment {PR_NUMBER} [--repo {REPO}] --body-file {path}`
**If save only (s):**
Keep the temp file and inform user of location.
## Notes
- The "cynical asshole" phase is internal only - never posted
- Tone transform MUST happen before any external output
- When in doubt, ask the user - never assume
- If you're unsure about severity, err toward higher severity
- If you're unsure about confidence, be honest and use Medium or Low

View File

@ -1,177 +0,0 @@
---
name: bmad-os-review-prompt
description: Review LLM workflow step prompts for known failure modes (silent ignoring, negation fragility, scope creep, etc). Use when user asks to "review a prompt" or "audit a workflow step".
---
# Prompt Review Skill: PromptSentinel v1.2
**Version:** v1.2
**Date:** March 2026
**Target Models:** Frontier LLMs (Claude 4.6, GPT-5.3, Gemini 3.1 Pro and equivalents) executing autonomous multi-step workflows at million-executions-per-day scale
**Purpose:** Detect and eliminate LLM-specific failure modes that survive generic editing, few-shot examples, and even multi-layer prompting. Output is always actionable, quoted, risk-quantified, and mitigation-ready.
---
### System Role (copy verbatim into reviewer agent)
You are **PromptSentinel v1.2**, a Prompt Auditor for production-grade LLM agent systems.
Your sole objective is to prevent silent, non-deterministic, or cascading failures in prompts that will be executed millions of times daily across heterogeneous models, tool stacks, and sub-agent contexts.
**Core Principles (required for every finding)**
- Every finding must populate all columns of the output table defined in the Strict Output Format section.
- Every finding must include: exact quote/location, failure mode ID or "ADV" (adversarial) / "PATH" (path-trace), production-calibrated risk, and a concrete mitigation with positive, deterministic rewritten example.
- Assume independent sub-agent contexts, variable context-window pressure, and model variance.
---
### Mandatory Review Procedure
Execute steps in order. Steps 0-1 run sequentially. Steps 2A/2B/2C run in parallel. Steps 3-4 run sequentially after all parallel tracks complete.
---
**Step 0: Input Validation**
If the input is not a clear LLM instruction prompt (raw code, data table, empty, or fewer than 50 tokens), output exactly:
`INPUT_NOT_A_PROMPT: [one-sentence reason]. Review aborted.`
and stop.
**Step 1: Context & Dependency Inventory**
Parse the entire prompt. Derive the **Prompt Title** as follows:
- First # or ## heading if present, OR
- Filename if provided, OR
- First complete sentence (truncated to 80 characters).
Build an explicit inventory table listing:
- All numbered/bulleted steps
- All variables, placeholders, file references, prior-step outputs
- All conditionals, loops, halts, tool calls
- All assumptions about persistent memory or ordering
Flag any unresolved dependencies.
Step 1 is complete when the full inventory table is populated.
This inventory is shared context for all three parallel tracks below.
---
### Step 2: Three Parallel Review Tracks
Launch all three tracks concurrently. Each track produces findings in the same table format. Tracks are independent — no track reads another track's output.
---
**Track A: Adversarial Review (sub-agent)**
Spawn a sub-agent with the following brief and the full prompt text. Give it the Step 1 inventory for reference. Give it NO catalog, NO checklist, and NO further instructions beyond this brief:
> You are reviewing an LLM prompt that will execute millions of times daily across different models. Find every way this prompt could fail, produce wrong results, or behave inconsistently. For each issue found, provide: exact quote or location, what goes wrong at scale, and a concrete fix. Use only training knowledge — rely on your own judgment, not any external checklist.
Track A is complete when the sub-agent returns its findings.
---
**Track B: Catalog Scan + Execution Simulation (main agent)**
**B.1 — Failure Mode Audit**
Scan the prompt against all 17 failure modes in the catalog below. Quote every relevant instance. For modes with zero findings, list them in a single summary line (e.g., "Modes 3, 7, 10, 12: no instances found").
B.1 is complete when every mode has been explicitly checked.
**B.2 — Execution Simulation**
Simulate the prompt under 3 scenarios:
- Scenario A: Small-context model (32k window) under load
- Scenario B: Large-context model (200k window), fresh session
- Scenario C: Different model vendor with weaker instruction-following
For each scenario, produce one row in this table:
| Scenario | Likely Failure Location | Failure Mode | Expected Symptom |
|----------|-------------------------|--------------|------------------|
B.2 is complete when the table contains 3 fully populated rows.
Track B is complete when both B.1 and B.2 are finished.
---
**Track C: Prompt Path Tracer (sub-agent)**
Spawn a sub-agent with the following brief, the full prompt text, and the Step 1 inventory:
> You are a mechanical path tracer for LLM prompts. Walk every execution path through this prompt — every conditional, branch, loop, halt, optional step, tool call, and error path. For each path, determine: is the entry condition unambiguous? Is there a defined done-state? Are all required inputs guaranteed to be available? Report only paths with gaps — discard clean paths silently.
>
> For each finding, provide:
> - **Location**: step/section reference
> - **Path**: the specific conditional or branch
> - **Gap**: what is missing (unclear entry, no done-state, unresolved input)
> - **Fix**: concrete rewrite that closes the gap
Track C is complete when the sub-agent returns its findings.
---
**Step 3: Merge & Deduplicate**
Collect all findings from Tracks A, B, and C. Tag each finding with its source (ADV, catalog mode number, or PATH). Deduplicate by exact quote — when multiple tracks flag the same issue, keep the finding with the most specific mitigation and note all sources.
Assign severity to each finding: Critical / High / Medium / Low.
Step 3 is complete when the merged, deduplicated, severity-scored findings table is populated.
**Step 4: Final Synthesis**
Format the entire review using the Strict Output Format below. Emit the complete review only after Step 3 is finished.
---
### Complete Failure Mode Catalog (Track B — scan all 17)
1. **Silent Ignoring** — Instructions buried mid-paragraph, nested >2-deep conditionals, parentheticals, or "also remember to..." after long text.
2. **Ambiguous Completion** — Steps with no observable done-state or verification criterion ("think about it", "finalize").
3. **Context Window Assumptions** — References to "previous step output", "the file we created earlier", or variables not re-passed.
4. **Over-specification vs Under-specification** — Wall-of-text detail causing selective attention OR vague verbs inviting hallucination.
5. **Non-deterministic Phrasing** — "Consider", "you may", "if appropriate", "best way", "optionally", "try to".
6. **Negation Fragility** — "Do NOT", "avoid", "never" (especially multiple or under load).
7. **Implicit Ordering** — Step B assumes Step A completed without explicit sequencing or guardrails.
8. **Variable Resolution Gaps**`{{VAR}}` or "the result from tool X" never initialized upstream.
9. **Scope Creep Invitation** — "Explore", "improve", "make it better", open-ended goals without hard boundaries.
10. **Halt / Checkpoint Gaps** — Human-in-loop required but no explicit `STOP_AND_WAIT_FOR_HUMAN` or output format that forces pause.
11. **Teaching Known Knowledge** — Re-explaining basic facts, tool usage, or reasoning patterns frontier models already know (2026 cutoff).
12. **Obsolete Prompting Techniques** — Outdated patterns (vanilla "think step by step" without modern scaffolding, deprecated few-shot styles).
13. **Missing Strict Output Schema** — No enforced JSON mode or structured output format.
14. **Missing Error Handling** — No recovery instructions for tool failures, timeouts, or malformed inputs.
15. **Missing Success Criteria** — No quality gates or measurable completion standards.
16. **Monolithic Prompt Anti-pattern** — Single large prompt that should be split into specialized sub-agents.
17. **Missing Grounding Instructions** — Factual claims required without explicit requirement to base them on retrieved evidence.
---
### Strict Output Format (use this template exactly as shown)
```markdown
# PromptSentinel Review: [Derived Prompt Title]
**Overall Risk Level:** Critical / High / Medium / Low
**Critical Issues:** X | **High:** Y | **Medium:** Z | **Low:** W
**Estimated Production Failure Rate if Unfixed:** ~XX% of runs
## Critical & High Findings
| # | Source | Failure Mode | Exact Quote / Location | Risk (High-Volume) | Mitigation & Rewritten Example |
|---|--------|--------------|------------------------|--------------------|-------------------------------|
| | | | | | |
## Medium & Low Findings
(same table format)
## Positive Observations
(only practices that actively mitigate known failure modes)
## Recommended Refactor Summary
- Highest-leverage changes (bullets)
## Revised Prompt Sections (Critical/High items only)
Provide full rewritten paragraphs/sections with changes clearly marked.
**Reviewer Confidence:** XX/100
**Review Complete** ready for re-submission or automated patching.
```

View File

@ -1,12 +0,0 @@
---
name: bmad-os-root-cause-analysis
description: Analyzes a bug-fix commit or PR and produces a structured Root Cause Analysis report covering what went wrong, why, and what guardrails failed.
license: MIT
disable-model-invocation: true
metadata:
author: bmad-code-org
version: "1.0.0"
compatibility: Requires gh CLI and git repository
---
Read `prompts/instructions.md` and execute.

View File

@ -1,74 +0,0 @@
# Bug-Fix Root Cause Analysis
Analyze a bug-fix commit or PR and produce a structured Root Cause Analysis report.
## Principles
- **Direct attribution.** This report names the individual who introduced the defect. Industry convention advocates blameless postmortems. This skill deliberately deviates: naming the individual and trusting them to own it is more respectful than diffusing accountability into systemic abstraction. Direct, factual, not accusatory. If authorship can't be determined confidently, say so.
- **Pyramid communication.** The executive summary must convey the full picture. A reader who stops after the first paragraph gets the gist. Everything else is supporting evidence.
## Preflight
Verify `gh auth status` and that you're in a git repository. Stop with a clear message if either fails.
## Execution
1. **Identify the fix.** Accept whatever the user provides — commit SHA, PR, issue, description. Resolve to the specific fix commit/PR using `gh` and `git`. If ambiguous, ask. Confirm the change is actually a bug fix before proceeding.
2. **Gather evidence.** Read the fix diff, PR/issue discussion, and use blame/log to identify the commit that introduced the bug. Collect timeline data.
3. **Analyze.** Apply 5 Whys. Classify the root cause. Identify contributing factors.
4. **Evaluate guardrails.** Inspect the actual repo configuration (CI workflows, linter configs, test setup) — don't assume. For each applicable guardrail, explain specifically why it missed this bug.
5. **Write the report** to `_bmad-output/rca-reports/rca-{YYYY-MM-DD}-{slug}.md`. Present the executive summary in chat.
## Report Structure
```markdown
# Root Cause Analysis: {Bug Title}
**Date:** {today}
**Fix:** {PR link or commit SHA}
**Severity:** {Critical | High | Medium | Low}
**Root Cause Category:** {Requirements | Design | Code Logic | Test Gap | Process | Environment/Config}
## Executive Summary
{One paragraph. What the bug was, root cause, who introduced it and when, detection
latency (introduced → detected), severity, and the key preventive recommendation.}
## What Was the Problem?
## When Did It Happen?
| Event | Date | Reference |
|-------|------|-----------|
| Introduced | | |
| Detected | | |
| Fixed | | |
| **Detection Latency** | **{introduced → detected}** | |
## Who Caused It?
{Author, commit/PR that introduced the defect, and the context — what were they
trying to do?}
## How Did It Happen?
## Why Did It Happen?
{5 Whys analysis. Root cause category. Contributing factors.}
## Failed Guardrails Analysis
| Guardrail | In Place? | Why It Failed |
|-----------|-----------|---------------|
| | | |
**Most Critical Failure:** {Which one mattered most and why.}
## Resolution
## Corrective & Preventive Actions
| # | Action | Type | Priority |
|---|--------|------|----------|
| | | {Prevent/Detect/Mitigate} | |
```

View File

@ -60,23 +60,40 @@ reviews:
- "!**/validation-report-*.md" - "!**/validation-report-*.md"
- "!CHANGELOG.md" - "!CHANGELOG.md"
path_instructions: path_instructions:
- path: "**/*" - path: "src/**"
instructions: | instructions: |
You are a cynical, jaded reviewer with zero patience for sloppy work. Source file changed. Check whether documentation under docs/ needs
This PR was submitted by a clueless weasel and you expect to find problems. a corresponding update — new features, changed behavior, renamed
Be skeptical of everything. concepts, altered CLI flags, or modified configuration options should
Look for what's missing, not just what's wrong. all be reflected in the relevant doc pages. Flag missing or outdated
Use a precise, professional tone — no profanity or personal attacks. docs as a review comment.
- path: "src/**/skills/**"
Review with extreme skepticism — assume problems exist. instructions: |
Find at least 10 issues to fix or improve. Skill file. Apply the full rule catalog defined in tools/skill-validator.md.
That document is the single source of truth for all skill validation rules
Do NOT: covering SKILL.md metadata, workflow.md constraints, step file structure,
- Comment on formatting, linting, or style path references, variable resolution, sequential execution, and skill
- Give "looks good" passes invocation syntax.
- Anchor on any specific ruleset — reason freely - path: "src/**/workflows/**"
instructions: |
If you find zero issues, re-analyze — this is suspicious. Legacy workflow file (pre-skill conversion). Apply the full rule catalog
defined in tools/skill-validator.md — the same rules apply to workflows
that are being converted to skills.
- path: "src/**/tasks/**"
instructions: |
Task file. Apply the full rule catalog defined in tools/skill-validator.md.
- path: "src/**/*.agent.yaml"
instructions: |
Agent definition file. Check:
- Has metadata section with id, name, title, icon, and module
- Defines persona with role, identity, communication_style, and principles
- Menu triggers reference valid skill names that exist
- path: "docs/**/*.md"
instructions: |
Documentation file. Check internal markdown links point to existing files.
- path: "tools/**"
instructions: |
Build script/tooling. Check error handling and proper exit codes.
chat: chat:
auto_reply: true # Response to mentions in comments, a la @coderabbit review auto_reply: true # Response to mentions in comments, a la @coderabbit review
issue_enrichment: issue_enrichment:

169
.github/workflows/publish.yaml vendored Normal file
View File

@ -0,0 +1,169 @@
name: Publish
on:
push:
branches: [main]
paths:
- "src/**"
- "tools/installer/**"
- "package.json"
- "removals.txt"
workflow_dispatch:
inputs:
channel:
description: "Publish channel"
required: true
default: "latest"
type: choice
options:
- latest
- next
bump:
description: "Version bump type (latest channel only)"
required: false
default: "patch"
type: choice
options:
- patch
- minor
- major
concurrency:
group: publish
cancel-in-progress: ${{ github.event_name == 'push' }}
permissions:
id-token: write
contents: write
jobs:
publish:
if: github.repository == 'bmad-code-org/BMAD-METHOD' && (github.event_name != 'workflow_dispatch' || github.ref == 'refs/heads/main')
runs-on: ubuntu-latest
steps:
- name: Generate GitHub App token
id: app-token
if: github.event_name == 'workflow_dispatch' && inputs.channel == 'latest'
uses: actions/create-github-app-token@v2
with:
app-id: ${{ secrets.RELEASE_APP_ID }}
private-key: ${{ secrets.RELEASE_APP_PRIVATE_KEY }}
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
token: ${{ steps.app-token.outputs.token || secrets.GITHUB_TOKEN }}
- name: Setup Node
uses: actions/setup-node@v4
with:
node-version-file: ".nvmrc"
cache: "npm"
- name: Ensure trusted publishing toolchain
run: |
# npm trusted publishing requires Node >= 22.14.0 and npm >= 11.5.1.
npm install --global npm@11.6.2
- name: Configure git user
if: github.event_name == 'workflow_dispatch' && inputs.channel == 'latest'
run: |
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
- name: Install dependencies
run: npm ci
- name: Run tests
run: npm test
- name: Derive next prerelease version
if: github.event_name == 'push' || (github.event_name == 'workflow_dispatch' && inputs.channel == 'next')
run: |
NEXT_VER=$(npm view bmad-method@next version 2>/dev/null || echo "")
LATEST_VER=$(npm view bmad-method@latest version 2>/dev/null || echo "")
# Determine the best base version for the next prerelease.
BASE=$(node -e "
const semver = require('semver');
const next = process.argv[1] || null;
const latest = process.argv[2] || null;
if (!next && !latest) process.exit(0);
if (!next) { console.log(latest); process.exit(0); }
if (!latest) { console.log(next); process.exit(0); }
const nextBase = next.replace(/-next\.\d+$/, '');
console.log(semver.gt(latest, nextBase) ? latest : next);
" "$NEXT_VER" "$LATEST_VER")
if [ -n "$BASE" ]; then
npm version "$BASE" --no-git-tag-version --allow-same-version
fi
npm version prerelease --preid=next --no-git-tag-version
- name: Bump stable version
if: github.event_name == 'workflow_dispatch' && inputs.channel == 'latest'
run: 'npm version ${{ inputs.bump }} -m "chore(release): v%s [skip ci]"'
- name: Publish prerelease to npm
if: github.event_name == 'push' || (github.event_name == 'workflow_dispatch' && inputs.channel == 'next')
run: npm publish --tag next --provenance
- name: Publish stable release to npm
if: github.event_name == 'workflow_dispatch' && inputs.channel == 'latest'
run: npm publish --tag latest --provenance
- name: Push version commit and tag
if: github.event_name == 'workflow_dispatch' && inputs.channel == 'latest'
run: git push origin main --follow-tags
- name: Create GitHub Release
if: github.event_name == 'workflow_dispatch' && inputs.channel == 'latest'
run: |
TAG="v$(node -p 'require("./package.json").version')"
VERSION="${TAG#v}"
# Extract the current version's section from CHANGELOG.md
BODY=$(awk -v ver="$VERSION" '
/^## v/ { if (found) exit; if (index($0, "## v" ver)) found=1; next }
found { print }
' CHANGELOG.md)
if [ -z "$BODY" ]; then
echo "::warning::No CHANGELOG.md entry for $TAG — falling back to auto-generated notes"
gh release create "$TAG" --generate-notes
else
gh release create "$TAG" --notes "$BODY"
fi
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Advance @next dist-tag to stable
if: github.event_name == 'workflow_dispatch' && inputs.channel == 'latest'
# Failure here leaves @next stale until the next push-driven prerelease
# republishes — annoying but not release-breaking. Don't fail the job
# after a successful stable publish + tag + GH release.
continue-on-error: true
run: |
# Without this, @latest can leapfrog @next (e.g. latest=6.5.0 while
# next=6.4.1-next.0) and `npx bmad-method@next install` silently
# downgrades users. Point @next at the just-published stable so
# @next >= @latest always holds; the next push-driven prerelease will
# bump from this base via the existing derive step above.
VERSION=$(node -p 'require("./package.json").version')
npm dist-tag add "bmad-method@${VERSION}" next
echo "Advanced @next dist-tag to ${VERSION}"
- name: Notify Discord
if: github.event_name == 'workflow_dispatch' && inputs.channel == 'latest'
continue-on-error: true
run: |
set -o pipefail
source .github/scripts/discord-helpers.sh
[ -z "$WEBHOOK" ] && exit 0
VERSION=$(node -p 'require("./package.json").version')
RELEASE_URL="${{ github.server_url }}/${{ github.repository }}/releases/tag/v${VERSION}"
MSG=$(printf '📦 **[bmad-method v%s released](<%s>)**' "$VERSION" "$RELEASE_URL" | esc)
jq -n --arg content "$MSG" '{content: $content}' | curl -sf --retry 2 -X POST "$WEBHOOK" -H "Content-Type: application/json" -d @-
env:
WEBHOOK: ${{ secrets.DISCORD_WEBHOOK }}

View File

@ -1,15 +1,15 @@
name: Quality & Validation name: Quality & Validation
# Runs comprehensive quality checks on all PRs: # Runs comprehensive quality checks on all PRs and pushes to main:
# - Prettier (formatting) # - Prettier (formatting)
# - ESLint (linting) # - ESLint (linting)
# - markdownlint (markdown quality) # - markdownlint (markdown quality)
# - Schema validation (YAML structure)
# - Agent schema tests (fixture-based validation)
# - Installation component tests (compilation) # - Installation component tests (compilation)
# - Bundle validation (web bundle integrity) # Keep this workflow aligned with `npm run quality` in `package.json`.
"on": "on":
push:
branches: [main]
pull_request: pull_request:
branches: ["**"] branches: ["**"]
workflow_dispatch: workflow_dispatch:
@ -103,14 +103,11 @@ jobs:
- name: Install dependencies - name: Install dependencies
run: npm ci run: npm ci
- name: Validate YAML schemas
run: npm run validate:schemas
- name: Run agent schema validation tests
run: npm run test:schemas
- name: Test agent compilation components - name: Test agent compilation components
run: npm run test:install run: npm run test:install
- name: Validate file references - name: Validate file references
run: npm run validate:refs run: npm run validate:refs
- name: Validate skills
run: npm run validate:skills

12
.gitignore vendored
View File

@ -17,9 +17,15 @@ npm-debug.log*
# Build output # Build output
build/*.txt build/*.txt
design-artifacts/
# Environment variables # Environment variables
.env .env
# Python
__pycache__/
.pytest_cache/
# System files # System files
.DS_Store .DS_Store
Thumbs.db Thumbs.db
@ -40,9 +46,13 @@ CLAUDE.local.md
.agents/ .agents/
z*/ z*/
!docs/zh-cn/
_bmad _bmad
_bmad-output _bmad-output
# Personal customization files (team files are committed, personal files are not)
_bmad/custom/*.user.toml
.clinerules .clinerules
# .augment/ is gitignored except tracked config files — add exceptions explicitly # .augment/ is gitignored except tracked config files — add exceptions explicitly
.augment/* .augment/*
@ -55,7 +65,7 @@ _bmad-output
.qwen .qwen
.rovodev .rovodev
.kilocodemodes .kilocodemodes
.claude/commands .claude
.codex .codex
.github/chatmodes .github/chatmodes
.github/agents .github/agents

39
.npmignore Normal file
View File

@ -0,0 +1,39 @@
# Development & Testing
test/
.husky/
.github/
.vscode/
.augment/
coverage/
test-output/
# Documentation site (users access docs online)
docs/
website/
# Configuration files (development only)
.coderabbit.yaml
.markdownlint-cli2.yaml
.prettierignore
.nvmrc
eslint.config.mjs
prettier.config.mjs
# Build tools (not needed at runtime)
tools/build-docs.mjs
tools/fix-doc-links.js
tools/validate-doc-links.js
tools/validate-file-refs.js
# Images (branding/marketing only)
banner-bmad-method.png
Wordmark.png
# Repository metadata
CONTRIBUTING.md
CONTRIBUTORS.md
SECURITY.md
TRADEMARK.md
CHANGELOG.md
CNAME
CODE_OF_CONDUCT.md

12
AGENTS.md Normal file
View File

@ -0,0 +1,12 @@
# BMAD-METHOD
Open source framework for structured, agent-assisted software delivery.
## Rules
- Use Conventional Commits for every commit.
- Before pushing, run `npm ci && npm run quality` on `HEAD` in the exact checkout you are about to push.
`quality` mirrors the checks in `.github/workflows/quality.yaml`.
- Skill validation rules are in `tools/skill-validator.md`.
- Deterministic skill checks run via `npm run validate:skills` (included in `quality`).

View File

@ -1,5 +1,229 @@
# Changelog # Changelog
## v6.5.0 - 2026-04-26
### 🎁 Features
* Support for 18 new agent platforms: AdaL, Sourcegraph Amp, IBM Bob, Command Code, Snowflake Cortex Code, Factory Droid, Firebender, Block Goose, Kode, Mistral Vibe, Mux, Neovate, OpenClaw, OpenHands, Pochi, Replit Agent, Warp, Zencoder — bringing total supported platforms to 42 (#2313)
* All platforms that support the cross-tool `.agents/skills/` standard now use it (#2313)
## v6.4.0 - 2026-04-24
### ✨ Headline
**Full agent and workflow customization across the entire BMad Method.** Every agent and workflow in BMM, Core, CIS, GDS, and TEA can now be customized via TOML overrides in `_bmad/custom/`. Customize agents to apply tooling, version control, or behavior changes across whole groups of workflows. Drop in fine-grained per-workflow overrides where you need them. Built for power users who want BMad to fit their stack without forking.
**Stable and bleeding-edge release channels, standardized across all modules.** Pick `stable` or `next` per module, pin specific versions, and switch channels interactively or via CLI flags (`--channel`, `--all-stable`, `--all-next`, `--next=CODE`, `--pin CODE=TAG`). Same model across BMM, Core, and every external module.
### 💥 Breaking Changes
* Customization is now TOML-based; the briefly introduced YAML-based customization is no longer supported (#2284, #2283)
### 🎁 Features
**Customization framework**
* TOML-based agent and workflow customization with flat schema, structural merge rules (scalars, tables, code-keyed arrays, append arrays), and `persistent_facts` unification (#2284)
* Central `_bmad/config.toml` surface with four-file architecture (`config.toml`, `config.user.toml`, `custom/config.toml`, `custom/config.user.toml`) for agent roster and scope-partitioned install answers (#2285)
* `customize.toml` support extended to 17 bmm-skills workflows with flattened SKILL.md architecture and standardized `[workflow]` block (#2287)
* `customize.toml` extended to all six developer-execution workflows: bmad-dev-story, bmad-code-review, bmad-sprint-planning, bmad-sprint-status, bmad-quick-dev, bmad-checkpoint-preview (#2308)
* `bmad-customize` skill — guided authoring of TOML overrides in `_bmad/custom/` with stdlib-only resolver verification (#2289)
* Wire `on_complete` hook into all 23 workflow terminal steps with full customize.toml documentation (#2290)
**Release channels & installer**
* Channel-based version resolution for external modules with interactive channel management (`stable` / `next` / `pinned`) and CLI flags (`--channel`, `--all-stable`, `--all-next`, `--next=CODE`, `--pin CODE=TAG`) (#2305)
* GitHub API as primary fetch with raw CDN fallback in installer registry client to support corporate proxies (#2248)
**Other**
* Kimi Code CLI support for installing BMM skills in `.kimi/skills/` (#2302)
* `bmad-create-story` now reads every UPDATE-marked file before generating dev notes so brownfield stories preserve current behavior instead of improvising at implementation time (#2274)
* Sync `sprint-status.yaml` from quick-dev on epic-story implementation with idempotent writes tracking `in-progress` and `review` transitions (#2234)
* Enforce model parity for all code review subagents to match orchestrator session capability for improved rare-event detection (#2236)
* Set `team: software-development` on all six BMM agents for unified grouping in party-mode and retrospective skills (#2286)
### 🐛 Bug Fixes
* PRD workflow no longer silently de-scopes user requirements or invents MVP/Growth/Vision phasing; requires explicit confirmation before any scope reduction (#1927)
* Installer shows live npm version for external modules instead of stale cached metadata (#2307)
* Resolve external-module agents from cache during manifest write so agents land in `config.toml` (#2295)
* Fix installer version resolution for external modules with shared resolver preferring package.json > module.yaml > marketplace.json (#2298)
* Replace fs-extra with native `node:fs` to prevent file loss during multi-module installs from deferred retry-queue races (#2253)
* Add `move()` and overwrite support to fs-native wrapper for directory migrations during upgrades (#2253)
* Stop skill scanner from recursing into discovered skills to prevent spurious errors on nested template files (#2255)
* Source built-in modules locally in installer UI to preserve core and bmm in module list when registry is unreachable (#2251)
* Remove dead Batch-apply option from code-review patch menu and rename apply options for clarity (#2225)
### ♻️ Refactoring
* Remove 1,683 lines of dead code: three entirely dead files (agent-command-generator.js, bmad-artifacts.js, module-injections.js) and ~50 unused exports across installer modules (#2247)
* Remove dead template and agent-command pipeline from installer; SKILL.md directory copying is the sole installation path (#2244)
### 📚 Documentation
* Sync and update Vietnamese (vi-VN) docs with missing pages and refreshed translations (#2291, #2222)
* Sync French (fr-FR) translations with upstream, restore Amelia as dev agent, fix sidebar ordering (#2231)
* Add Czech (cs-CZ) `analysis-phase.md` translation; normalize typographic quotes (#2240, #2241, #2242)
* Add missing Chinese (zh-CN) translations for 3 documents (#2254)
* Update stale Analyst agent triggers and add PRFAQ link (#2238)
* Remove Bob from workflow map diagrams reflecting consolidation into Amelia in v6.3.0 (#2252)
## v6.3.0 - 2026-04-09
### 💥 Breaking Changes
* Remove custom content installation feature; use marketplace-based plugin installation instead (#2227)
* Remove bmad-init skill; all agents and skills now load config directly from `{project-root}/_bmad/bmm/config.yaml` (#2159)
* Remove spec-wip.md singleton; quick-dev now writes directly to `spec-{slug}.md` with status field, enabling parallel sessions (#2214)
* Consolidate three agent personas into Developer agent (Amelia): remove Barry quick-flow-solo-dev (#2177), Quinn QA agent (#2179), and Bob Scrum Master agent (#2186)
### 🎁 Features
* Universal source support for custom module installs with 5-strategy PluginResolver cascade supporting any Git host (GitHub, GitLab, Bitbucket, self-hosted) and local file paths (#2233)
* Community module browser with three-tier selection: official, community (category drill-down from marketplace index), and custom URL with unverified source warning (#2229)
* Switch module source of truth from bundled config to remote marketplace registry with network-failure fallback (#2228)
* Add bmad-prfaq skill implementing Amazon's Working Backwards methodology as alternative Phase 1 analysis path with 5-stage coached workflow and subagent architecture (#2157)
* Add bmad-checkpoint-preview skill for guided, concern-ordered human review of commits, branches, or PRs (#2145)
* Epic context compilation for quick-dev step-01: sub-agent compiles planning docs into cached `epic-{N}-context.md` for story implementation (#2218)
* Previous story continuity in quick-dev: load completed spec from same epic as implementation context (#2201)
* Planning artifact awareness in quick-dev: selectively load PRD, architecture, UX, and epics docs for context-informed specs (#2185)
* One-shot route now generates lightweight spec trace file for consistent artifact tracking (#2121)
* Improve checkpoint-preview UX with clickable spec paths, external edit detection, and missing-file halt (#2217)
* Add Junie (JetBrains AI) platform support (#2142)
* Restore KiloCoder support with native-skills installation (#2151)
* Add bmad-help support for llms.txt general questions (#2230)
### ♻️ Refactoring
* Consolidate party-mode into single SKILL.md with real subagent spawning via Agent tool, replacing multi-file workflow architecture (#2160)
### 🐛 Bug Fixes
* Fix version display bug where marketplace.json walk-up reported wrong version (#2233)
* Fix checkpoint-preview step-05 advancing without user confirmation by adding explicit HALT (#2184)
* Address adversarial triage findings: clarify review_mode transitions, label walkthrough branches, fix terse commit handling (#2180)
* Preserve local custom module sources during quick update (#2172)
* Support skills/ folder as fallback module source location for bmb compatibility (#2149)
### 🔧 Maintenance
* Overhaul installer branding with responsive BMAD METHOD logo, blue color scheme, unified version sourcing from marketplace.json, and surgical manifest-based skill cleanup (#2223)
* Stop copying skill prompts to _bmad by default (#2182)
* Add Python 3.10+ and uv as documented prerequisites (#2221)
### 📚 Documentation
* Complete Czech (cs-CZ) documentation translation (#2134)
* Complete Vietnamese (vi-VN) documentation translation (#2110, #2192)
* Rewrite get-answers-about-bmad as 1-2-3 escalation flow, remove deprecated references (#2213)
* Add checkpoint-preview explainer page and workflow diagram (#2183)
* Update docs theme to match bmadcode.com with responsive logo and blue color scheme (#2176)
## v6.2.2 - 2026-03-25
### ♻️ Refactoring
* Modernize module-help CSV to 13-column format with `after`/`before` dependency graph replacing sequence numbers (#2120)
* Rewrite bmad-help from procedural 8-step execution to outcome-based skill design (~50% shorter) (#2120)
### 🐛 Bug Fixes
* Update bmad-builder module-definition path from `src/module.yaml` to `skills/module.yaml` for bmad-builder v1.2.0 compatibility (#2126)
* Fix eslint config to ignore gitignored lock files (#2120)
### 📚 Documentation
* Close Epic 4.5 explanation gaps in Chinese (zh-CN): normalize command naming to current `bmad-*` convention and add cross-links across 9 explanation pages (#2102)
## v6.2.1 - 2026-03-24
### 🎁 Highlights
* Full rewrite of code-review skill with sharded step-file architecture, three parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor), and interactive post-review triage (#2007, #2013, #2055)
* Quick Dev workflow overhaul: smart intent cascade, self-check gate, VS Code integration, clickable spec links, and spec rename (#2105, #2104, #2039, #2085, #2109)
* Add review trail generation with clickable `path:line` stops in spec file (#2033)
* Add clickable spec links using spec-file-relative markdown format (#2085, #2049)
* Preserve tracking identifiers in spec slug derivation (#2108)
* Deterministic skill validator with 19 rules across 6 categories, integrated into CI (#1981, #1982, #2004, #2002, #2051)
* Complete French (fr-FR) documentation translation (#2073)
* Add Ona platform support (#1968)
* Rename tech-spec → spec across templates and all documentation (#2109)
### 📚 Documentation
* Complete French (fr-FR) translation of all documentation with workflow diagrams (#2073)
* Refine Chinese (zh-CN) documentation: epic stories, how-to guides, getting-started, entry copy, help, anchor links (#2092#2099, #2072)
* Add Chinese translation for core-tools reference (#2002)
## v6.2.0 - 2026-03-15
### 🎁 Highlights
* Fix manifest generation so BMad Builder installs correctly when a module has no agents (#1998)
* Prototype preview of bmad-product-brief-preview skill — try `/bmad-product-brief-preview` and share feedback! (#1959)
* All skills now use native skill directory format for improved modularity and maintainability (#1931, #1945, #1946, #1949, #1950, #1984, #1985, #1988, #1994)
### 🎁 Features
* Rewrite code-review skill with sharded step-file architecture and auto-detect review intent from invocation args (#2007, #2013)
* Add inference-based skill validator with comprehensive rules for naming, variables, paths, and invocation syntax (#1981)
* Add REF-03 skill invocation language rule and PATH-05 skill encapsulation rule to validator (#2004)
### 🐛 Bug Fixes
* Validation pass 2 — fix path, variable, and sequence issues across 32 files (#2008)
* Replace broken party-mode workflow refs with skill syntax (#2000)
* Improve bmad-help description for accurate trigger matching (#2012)
* Point zh-cn doc links to Chinese pages instead of English (#2010)
* Validation cleanup for bmad-quick-flow (#1997), 6 skills batch (#1996), bmad-sprint-planning (#1995), bmad-retrospective (#1993), bmad-dev-story (#1992), bmad-create-story (#1991), bmad-code-review (#1990), bmad-create-epics-and-stories (#1989), bmad-create-architecture (#1987), bmad-check-implementation-readiness (#1986), bmad-create-ux-design (#1983), bmad-create-product-brief (#1982)
### 🔧 Maintenance
* Normalize skill invocation syntax to `Invoke the skill` pattern repo-wide (#2004)
### 📚 Documentation
* Add Chinese translation for core-tools reference (#2002)
* Update version hint, TEA module link, and HTTP→HTTPS links in Chinese README (#1922, #1921)
## [6.1.0] - 2026-03-12
### Highlights
* Whiteport Design Studio (WDS) module enabled in the installer
* Support @next installation channel (`npx bmad-method@next install`) — get the latest tip of main instead of waiting for the next stable published version
* Everything now installs as a skill — all workflows, agents, and tasks converted to markdown with SKILL.md entrypoints (not yet optimized skills, but unified format)
* An experimental preview of the new Quick Dev is available, which will become the main Phase 4 development tool
* Edge Case Hunter added as a parallel code review layer in Phase 4, improving code quality by exhaustively tracing branching paths and boundary conditions (#1791)
* Documentation now available in Chinese (zh-CN) with complete translation (#1822, #1795)
### 💥 Breaking Changes
* Convert entire BMAD method to skills-based architecture with unified skill manifests (#1834)
* Convert all core workflows from YAML+instructions to single workflow.md format
* Migrate all remaining platforms to native Agent Skills format (#1841)
* Remove legacy YAML/XML workflow engine plumbing (#1864)
### 🎁 Features
* Add Pi coding agent as supported platform (#1854)
* Add unified skill scanner decoupled from legacy collectors (#1859)
* Add continuous delivery workflows for npm publishing with trusted OIDC publishing (#1872)
### ♻️ Refactoring
* Update terminology from "commands" to "skills" across all documentation (#1850)
### 🐛 Bug Fixes
* Fix code review removing mandatory minimum issue count that caused infinite review loops (#1913)
* Fix silent loss of brainstorming ideas in PRD by adding reconciliation step (#1914)
* Reduce npm tarball from 533 to 348 files (91% size reduction, 6.2 MB → 555 KB) via .npmignore (#1900)
* Fix party-mode skill conversion review findings (#1919)
---
## [6.0.4] ## [6.0.4]
### 🎁 Features ### 🎁 Features
@ -47,7 +271,7 @@
* Add CodeBuddy platform support with installer configuration (#1483) * Add CodeBuddy platform support with installer configuration (#1483)
* Add LLM audit prompt for file reference conventions - new audit tool using parallel subagents (#1720) * Add LLM audit prompt for file reference conventions - new audit tool using parallel subagents (#1720)
* Migrate Codex installer from `.codex/prompts` to `.agents/skills` format to align with Codex CLI changes (#1729) * Migrate Codex installer from `.codex/prompts` to `.agents/skills` format to align with Codex CLI changes (#1729)
* Convert review-pr and audit-file-refs tools to proper bmad-os skills with slash commands `/bmad-os-review-pr` and `/bmad-os-audit-file-refs` (#1732) * Convert review-pr and audit-file-refs tools to proper bmad-os skills with slash commands `bmad-os-review-pr` and `bmad-os-audit-file-refs` (#1732)
### 🐛 Bug Fixes ### 🐛 Bug Fixes
@ -365,7 +589,7 @@ V6 Stable Release! The End of Beta!
- TEA documentation restructured using Diátaxis framework (25 docs) - TEA documentation restructured using Diátaxis framework (25 docs)
- Style guide optimized for LLM readers (367 lines, down from 767) - Style guide optimized for LLM readers (367 lines, down from 767)
- Glossary rewritten using table format (123 lines, down from 373) - Glossary rewritten using table format (123 lines, down from 373)
- README overhaul with numbered command flows and prominent `/bmad-help` callout - README overhaul with numbered command flows and prominent `bmad-help` callout
- New workflow map diagram with interactive HTML - New workflow map diagram with interactive HTML
- New editorial review tasks for document quality - New editorial review tasks for document quality
- E2E testing methodology for Game Dev Studio - E2E testing methodology for Game Dev Studio

View File

@ -6,6 +6,12 @@ Thank you for considering contributing! We believe in **Human Amplification, Not
--- ---
> **Before you write code: talk to us on [Discord](https://discord.gg/gk8jAdXWmj).**
>
> If your change adds features, restructures code, or touches more than a couple of files, **confirm with a maintainer that it fits**. A large PR out of the blue has a high chance of being closed — regardless of effort invested. A five-minute conversation can save you hours.
---
## Our Philosophy ## Our Philosophy
BMad strengthens human-AI collaboration through specialized agents and guided workflows. Every contribution should answer: **"Does this make humans and AI better together?"** BMad strengthens human-AI collaboration through specialized agents and guided workflows. Every contribution should answer: **"Does this make humans and AI better together?"**
@ -57,15 +63,10 @@ After searching, use the [feature request template](https://github.com/bmad-code
## Before Starting Work ## Before Starting Work
⚠️ **Required before submitting PRs:** | Work Type | Requirement |
| ----------------------- | -------------------------------------------------------- |
| Work Type | Requirement | | Typo / small bug fix | Just open the PR |
| ------------- | ---------------------------------------------- | | Feature or large change | Confirm with a maintainer on Discord **before** you start |
| Bug fix | An open issue (create one if it doesn't exist) |
| Feature | An open feature request issue |
| Large changes | Discussion via issue first |
**Why?** This prevents wasted effort on work that may not align with project direction.
--- ---
@ -73,7 +74,7 @@ After searching, use the [feature request template](https://github.com/bmad-code
### Target Branch ### Target Branch
Submit PRs to the `main` branch. We use [trunk-based development](https://trunkbaseddevelopment.com/branch-for-release/): `main` is the trunk where all work lands, and stable release branches receive only cherry-picked fixes. Submit PRs to the `main` branch. We use trunk-based development. Every push to `main` auto-publishes to `npm` under the `next` tag. Stable releases are cut ~weekly to the `latest` tag.
### PR Size ### PR Size
@ -83,6 +84,12 @@ Submit PRs to the `main` branch. We use [trunk-based development](https://trunkb
If your change exceeds 800 lines, break it into smaller PRs that can be reviewed independently. If your change exceeds 800 lines, break it into smaller PRs that can be reviewed independently.
### AI-Generated Code
Given the nature of this project, we expect most contributions involve AI assistance — that's fine. What we require is **heavy human curation**. You must understand every line you're submitting, have made deliberate choices about what to include, and be able to explain your reasoning.
We will reject PRs that read like raw LLM output: bulk refactors nobody asked for, unsolicited "improvements" across many files, or changes where the submitter clearly hasn't read the existing code. Using AI to write code is normal here; using AI as a substitute for thinking is not.
### New to Pull Requests? ### New to Pull Requests?
1. **Fork** the repository 1. **Fork** the repository
@ -146,7 +153,6 @@ Keep messages under 72 characters. Each commit = one logical change.
- Web/planning agents can be larger with complex tasks - Web/planning agents can be larger with complex tasks
- Everything is natural language (markdown) — no code in core framework - Everything is natural language (markdown) — no code in core framework
- Use BMad modules for domain-specific features - Use BMad modules for domain-specific features
- Validate YAML schemas: `npm run validate:schemas`
- Validate file references: `npm run validate:refs` - Validate file references: `npm run validate:refs`
### File-Pattern-to-Validator Mapping ### File-Pattern-to-Validator Mapping

View File

@ -3,6 +3,8 @@
[![Version](https://img.shields.io/npm/v/bmad-method?color=blue&label=version)](https://www.npmjs.com/package/bmad-method) [![Version](https://img.shields.io/npm/v/bmad-method?color=blue&label=version)](https://www.npmjs.com/package/bmad-method)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Node.js Version](https://img.shields.io/badge/node-%3E%3D20.0.0-brightgreen)](https://nodejs.org) [![Node.js Version](https://img.shields.io/badge/node-%3E%3D20.0.0-brightgreen)](https://nodejs.org)
[![Python Version](https://img.shields.io/badge/python-%3E%3D3.10-blue?logo=python&logoColor=white)](https://www.python.org)
[![uv](https://img.shields.io/badge/uv-package%20manager-blueviolet?logo=uv)](https://docs.astral.sh/uv/)
[![Discord](https://img.shields.io/badge/Discord-Join%20Community-7289da?logo=discord&logoColor=white)](https://discord.gg/gk8jAdXWmj) [![Discord](https://img.shields.io/badge/Discord-Join%20Community-7289da?logo=discord&logoColor=white)](https://discord.gg/gk8jAdXWmj)
**Build More Architect Dreams** — An AI-driven agile development module for the BMad Method Module Ecosystem, the best and most comprehensive Agile AI Driven Development framework that has true scale-adaptive intelligence that adjusts from bug fixes to enterprise systems. **Build More Architect Dreams** — An AI-driven agile development module for the BMad Method Module Ecosystem, the best and most comprehensive Agile AI Driven Development framework that has true scale-adaptive intelligence that adjusts from bug fixes to enterprise systems.
@ -13,10 +15,10 @@
Traditional AI tools do the thinking for you, producing average results. BMad agents and facilitated workflows act as expert collaborators who guide you through a structured process to bring out your best thinking in partnership with the AI. Traditional AI tools do the thinking for you, producing average results. BMad agents and facilitated workflows act as expert collaborators who guide you through a structured process to bring out your best thinking in partnership with the AI.
- **AI Intelligent Help**Ask `/bmad-help` anytime for guidance on what's next - **AI Intelligent Help**Invoke the `bmad-help` skill anytime for guidance on what's next
- **Scale-Domain-Adaptive** — Automatically adjusts planning depth based on project complexity - **Scale-Domain-Adaptive** — Automatically adjusts planning depth based on project complexity
- **Structured Workflows** — Grounded in agile best practices across analysis, planning, architecture, and implementation - **Structured Workflows** — Grounded in agile best practices across analysis, planning, architecture, and implementation
- **Specialized Agents** — 12+ domain experts (PM, Architect, Developer, UX, Scrum Master, and more) - **Specialized Agents** — 12+ domain experts (PM, Architect, Developer, UX, and more)
- **Party Mode** — Bring multiple agent personas into one session to collaborate and discuss - **Party Mode** — Bring multiple agent personas into one session to collaborate and discuss
- **Complete Lifecycle** — From brainstorming to deployment - **Complete Lifecycle** — From brainstorming to deployment
@ -34,13 +36,13 @@ Traditional AI tools do the thinking for you, producing average results. BMad ag
## Quick Start ## Quick Start
**Prerequisites**: [Node.js](https://nodejs.org) v20+ **Prerequisites**: [Node.js](https://nodejs.org) v20+ · [Python](https://www.python.org) 3.10+ · [uv](https://docs.astral.sh/uv/)
```bash ```bash
npx bmad-method install npx bmad-method install
``` ```
> If you are getting a stale beta version, use: `npx bmad-method@6.0.1 install` > Want the newest prerelease build? Use `npx bmad-method@next install`. Expect higher churn than the default install.
Follow the installer prompts, then open your AI IDE (Claude Code, Cursor, etc.) in your project folder. Follow the installer prompts, then open your AI IDE (Claude Code, Cursor, etc.) in your project folder.
@ -52,7 +54,7 @@ npx bmad-method install --directory /path/to/project --modules bmm --tools claud
[See all installation options](https://docs.bmad-method.org/how-to/non-interactive-installation/) [See all installation options](https://docs.bmad-method.org/how-to/non-interactive-installation/)
> **Not sure what to do?** Run `/bmad-help` — it tells you exactly what's next and what's optional. You can also ask questions like `/bmad-help I just finished the architecture, what do I do next?` > **Not sure what to do?** Ask `bmad-help` — it tells you exactly what's next and what's optional. You can also ask questions like `bmad-help I just finished the architecture, what do I do next?`
## Modules ## Modules
@ -79,18 +81,15 @@ BMad Method extends with official modules for specialized domains. Available dur
## Community ## Community
- [Discord](https://discord.gg/gk8jAdXWmj) — Get help, share ideas, collaborate - [Discord](https://discord.gg/gk8jAdXWmj) — Get help, share ideas, collaborate
- [Subscribe on YouTube](https://www.youtube.com/@BMadCode) — Tutorials, master class, and podcast (launching Feb 2025) - [YouTube](https://youtube.com/@BMadCode) — Tutorials, master class, and more
- [X / Twitter](https://x.com/BMadCode)
- [Website](https://bmadcode.com)
- [GitHub Issues](https://github.com/bmad-code-org/BMAD-METHOD/issues) — Bug reports and feature requests - [GitHub Issues](https://github.com/bmad-code-org/BMAD-METHOD/issues) — Bug reports and feature requests
- [Discussions](https://github.com/bmad-code-org/BMAD-METHOD/discussions) — Community conversations - [Discussions](https://github.com/bmad-code-org/BMAD-METHOD/discussions) — Community conversations
## Support BMad ## Support BMad
BMad is free for everyone — and always will be. If you'd like to support development: BMad is free for everyone and always will be. Star this repo, [buy me a coffee](https://buymeacoffee.com/bmad), or email <contact@bmadcode.com> for corporate sponsorship.
- ⭐ Please click the star project icon near the top right of this page
- ☕ [Buy Me a Coffee](https://buymeacoffee.com/bmad) — Fuel the development
- 🏢 Corporate sponsorship — DM on Discord
- 🎤 Speaking & Media — Available for conferences, podcasts, interviews (BM on Discord)
## Contributing ## Contributing

View File

@ -5,30 +5,30 @@
[![Node.js Version](https://img.shields.io/badge/node-%3E%3D20.0.0-brightgreen)](https://nodejs.org) [![Node.js Version](https://img.shields.io/badge/node-%3E%3D20.0.0-brightgreen)](https://nodejs.org)
[![Discord](https://img.shields.io/badge/Discord-Join%20Community-7289da?logo=discord&logoColor=white)](https://discord.gg/gk8jAdXWmj) [![Discord](https://img.shields.io/badge/Discord-Join%20Community-7289da?logo=discord&logoColor=white)](https://discord.gg/gk8jAdXWmj)
**突破性敏捷 AI 驱动开发方法** — 简称 “BMAD 方法论” BMAD方法论是由多个模块生态构成的AI驱动敏捷开发模块系统这是最佳且最全面的敏捷 AI 驱动开发框架,具备真正的规模自适应人工智能,可适应快速开发,适应企业规模化开发 **筑梦架构Build More Architect Dreams** —— 简称 “BMAD 方法”,面向 BMad 模块生态的 AI 驱动敏捷开发方法。它会随项目复杂度调整工作深度,从日常 bug 修复到企业级系统建设都能适配
**100% 免费且开源。** 无付费。无内容门槛。无封闭 Discord。我们赋能每个人我们将为全球现在在人工智能领域发展的普通人提供公平的学习机会 **100% 免费且开源。** 没有付费墙,没有封闭内容,也没有封闭 Discord。我们希望每个人都能平等获得高质量的人机协作开发方法
## 为什么选择 BMad 方法? ## 为什么选择 BMad 方法?
传统 AI 工具替你思考产生平庸的结果。BMad 智能体和辅助工作流充当专家协作者,引导你通过结构化流程,与 AI 的合作发挥最佳思维,产出最有效优秀的结果 传统 AI 工具常常替你思考结果往往止于“能用”。BMad 通过专业智能体和引导式工作流,让 AI 成为协作者:流程有结构,决策有依据,产出更稳定
- **AI 智能帮助** — 随时使用 `/bmad-help` 获取下一步指导 - **AI 智能引导** —— 随时调用 `bmad-help` 获取下一步建议
- **规模-领域自适应** — 根据项目复杂度自动调整规划深度 - **规模与领域自适应** —— 按项目复杂度自动调整规划深度
- **结构化工作流** 基于分析、规划、架构和实施的敏捷最佳实践 - **结构化工作流**— 覆盖分析、规划、架构、实施全流程
- **专业智能体** — 12+ 领域专家PM、架构师、开发者、UX、Scrum Master 等) - **专业角色智能体** —— 提供 PM、架构师、开发者、UX 等 12+ 角色
- **派对模式** 将多个智能体角色带入一个会话进行协作和讨论 - **派对模式**— 多个智能体可在同一会话协作讨论
- **完整生命周期** 从想法开始(头脑风暴)到部署发布 - **完整生命周期**— 从头脑风暴一路到交付上线
[在 **docs.bmad-method.org** 了解更多](http://docs.bmad-method.org) [在 **docs.bmad-method.org** 了解更多](https://docs.bmad-method.org/zh-cn/)
--- ---
## 🚀 BMad 的下一步是什么? ## 🚀 BMad 的下一步是什么?
**V6 已到来,我们才刚刚开始!** BMad 方法正在快速发展包括跨平台智能体团队和子智能体集成、技能架构、BMad Builder v1、开发循环自动化等优化以及更多正在开发中的功能 **V6 已经上线,而这只是开始。** BMad 仍在快速演进跨平台智能体团队与子智能体集成、Skills 架构、BMad Builder v1、Dev Loop 自动化等能力都在持续推进
**[📍 查看完整路线图 →](http://docs.bmad-method.org/roadmap/)** **[📍 查看完整路线图 →](https://docs.bmad-method.org/zh-cn/roadmap/)**
--- ---
@ -40,7 +40,7 @@
npx bmad-method install npx bmad-method install
``` ```
> 如果你获得的是过时的测试版,请使用:`npx bmad-method@6.0.1 install` > 想体验最新预发布版本?可使用 `npx bmad-method@next install`。它比默认版本更新更快,也可能更容易发生变化。
按照安装程序提示操作,然后在项目文件夹中打开你的 AI IDEClaude Code、Cursor 等)。 按照安装程序提示操作,然后在项目文件夹中打开你的 AI IDEClaude Code、Cursor 等)。
@ -50,31 +50,30 @@ npx bmad-method install
npx bmad-method install --directory /path/to/project --modules bmm --tools claude-code --yes npx bmad-method install --directory /path/to/project --modules bmm --tools claude-code --yes
``` ```
[查看所有安装选项](http://docs.bmad-method.org/how-to/non-interactive-installation/) [查看非交互式安装选项](https://docs.bmad-method.org/zh-cn/how-to/non-interactive-installation/)
> **不确定该做什么?** 运行 `/bmad-help` — 它会准确告诉你下一步做什么以及什么是可选的。你也可以问诸如 `/bmad-help 我刚刚完成了架构设计,接下来该做什么?` 之类的问题。 > **不确定下一步?** 直接问 `bmad-help`。它会告诉你“必做什么、可选什么”,例如:`bmad-help 我刚完成架构设计,接下来做什么?`
## 模块 ## 模块
BMad 方法通过官方模块扩展到专业领域。可在安装期间或之后的任何时间使用 BMad 可通过官方模块扩展到不同专业场景。你可以在安装时选择,也可以后续随时补装
| Module | Purpose | | 模块 | 用途 |
| ----------------------------------------------------------------------------------------------------------------- | ------------------------------------------------- | | ----------------------------------------------------------------------------------------------------------------- | ---------------------------- |
| **[BMad Method (BMM)](https://github.com/bmad-code-org/BMAD-METHOD)** | 包含 34+ 工作流的核心框架 | | **[BMad Method (BMM)](https://github.com/bmad-code-org/BMAD-METHOD)** | 核心框架,内含 34+ 工作流 |
| **[BMad Builder (BMB)](https://github.com/bmad-code-org/bmad-builder)** | 创建自定义 BMad 智能体和工作流 | | **[BMad Builder (BMB)](https://github.com/bmad-code-org/bmad-builder)** | 创建自定义 BMad 智能体与工作流 |
| **[Test Architect (TEA)](https://github.com/bmad-code-org/tea)** | 基于风险的测试策略和自动化 | | **[Test Architect (TEA)](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise)** | 基于风险的测试策略与自动化 |
| **[Game Dev Studio (BMGD)](https://github.com/bmad-code-org/bmad-module-game-dev-studio)** | 游戏开发工作流Unity、Unreal、Godot | | **[Game Dev Studio (BMGD)](https://github.com/bmad-code-org/bmad-module-game-dev-studio)** | 游戏开发工作流Unity/Unreal/Godot |
| **[Creative Intelligence Suite (CIS)](https://github.com/bmad-code-org/bmad-module-creative-intelligence-suite)** | 创新、头脑风暴、设计思维 | | **[Creative Intelligence Suite (CIS)](https://github.com/bmad-code-org/bmad-module-creative-intelligence-suite)** | 创新、头脑风暴、设计思维 |
## 文档 ## 文档
[BMad 方法文档站点](http://docs.bmad-method.org) — 教程、指南、概念和参考 [BMad 方法文档站点](https://docs.bmad-method.org/zh-cn/) — 教程、指南、概念和参考
**快速链接:** **快速链接:**
- [入门教程](http://docs.bmad-method.org/tutorials/getting-started/) - [入门教程](https://docs.bmad-method.org/zh-cn/tutorials/getting-started/)
- [从先前版本升级](http://docs.bmad-method.org/how-to/upgrade-to-v6/) - [从旧版本升级](https://docs.bmad-method.org/zh-cn/how-to/upgrade-to-v6/)
- [测试架构师文档](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/) - [测试架构师文档(英文)](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/)
## 社区 ## 社区
@ -85,9 +84,9 @@ BMad 方法通过官方模块扩展到专业领域。可在安装期间或之后
## 支持 BMad ## 支持 BMad
BMad 对每个人都是免费的 — 并且永远如此。如果你想支持开发 BMad 对所有人免费,而且会一直免费。如果你愿意支持项目发展
- ⭐ 请点击此页面右上角附近的项目星标图标 - ⭐ 给仓库点个 Star
- ☕ [请我喝咖啡](https://buymeacoffee.com/bmad) — 为开发提供动力 - ☕ [请我喝咖啡](https://buymeacoffee.com/bmad) — 为开发提供动力
- 🏢 企业赞助 — 在 Discord 上私信 - 🏢 企业赞助 — 在 Discord 上私信
- 🎤 演讲与媒体 — 可参加会议、播客、采访(在 Discord 上联系 BM - 🎤 演讲与媒体 — 可参加会议、播客、采访(在 Discord 上联系 BM
@ -107,15 +106,3 @@ MIT 许可证 — 详见 [LICENSE](LICENSE)。
[![Contributors](https://contrib.rocks/image?repo=bmad-code-org/BMAD-METHOD)](https://github.com/bmad-code-org/BMAD-METHOD/graphs/contributors) [![Contributors](https://contrib.rocks/image?repo=bmad-code-org/BMAD-METHOD)](https://github.com/bmad-code-org/BMAD-METHOD/graphs/contributors)
请参阅 [CONTRIBUTORS.md](CONTRIBUTORS.md) 了解贡献者信息。 请参阅 [CONTRIBUTORS.md](CONTRIBUTORS.md) 了解贡献者信息。
---
## 术语说明
- **agent**:智能体。在人工智能与编程文档中,指具备自主决策或执行能力的单元。
- **workflow**:工作流。指一系列有序的任务或步骤,用于完成特定目标。
- **CI/CD**:持续集成/持续部署。一种自动化软件开发实践,用于频繁集成代码更改并自动部署。
- **IDE**:集成开发环境。提供代码编辑、调试、构建等功能的软件开发工具。
- **PM**:产品经理。负责产品规划、需求管理和团队协调的角色。
- **UX**:用户体验。指用户在使用产品或服务过程中的整体感受和交互体验。
- **Scrum Master**Scrum 主管。敏捷开发 Scrum 框架中的角色,负责促进团队遵循 Scrum 流程。
- **PRD**:产品需求文档。详细描述产品功能、需求和规格的文档。

109
README_VN.md Normal file
View File

@ -0,0 +1,109 @@
![BMad Method](banner-bmad-method.png)
[![Version](https://img.shields.io/npm/v/bmad-method?color=blue&label=version)](https://www.npmjs.com/package/bmad-method)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Node.js Version](https://img.shields.io/badge/node-%3E%3D20.0.0-brightgreen)](https://nodejs.org)
[![Python Version](https://img.shields.io/badge/python-%3E%3D3.10-blue?logo=python&logoColor=white)](https://www.python.org)
[![uv](https://img.shields.io/badge/uv-package%20manager-blueviolet?logo=uv)](https://docs.astral.sh/uv/)
[![Discord](https://img.shields.io/badge/Discord-Join%20Community-7289da?logo=discord&logoColor=white)](https://discord.gg/gk8jAdXWmj)
[English](README.md) | [简体中文](README_CN.md) | Tiếng Việt
**Build More Architect Dreams** - một mô-đun khung phát triển hướng AI trong hệ sinh thái BMad, có khả năng thích ứng theo quy mô từ sửa lỗi nhỏ đến các hệ thống doanh nghiệp.
**100% miễn phí và mã nguồn mở.** Không có tường phí. Không có nội dung bị khóa. Không có Discord giới hạn quyền truy cập. Chúng tôi tin vào việc trao quyền cho mọi người, không chỉ cho những ai có thể trả tiền để vào một cộng đồng hay khóa học khép kín.
## Vì sao chọn BMad Method?
Các công cụ AI truyền thống thường làm thay phần suy nghĩ của bạn và tạo ra kết quả ở mức trung bình. Các agent chuyên biệt và quy trình làm việc có hướng dẫn của BMad hoạt động như những cộng tác viên chuyên gia, dẫn dắt bạn qua một quy trình có cấu trúc để khai mở tư duy tốt nhất của bạn cùng với AI.
- **Trợ giúp AI thông minh** - Gọi skill `bmad-help` bất kỳ lúc nào để biết bước tiếp theo
- **Thích ứng theo quy mô và miền bài toán** - Tự động điều chỉnh độ sâu lập kế hoạch theo độ phức tạp của dự án
- **Quy trình có cấu trúc** - Dựa trên các thực hành tốt nhất của agile xuyên suốt phân tích, lập kế hoạch, kiến trúc và triển khai
- **Agent chuyên biệt** - Hơn 12 chuyên gia theo vai trò như PM, Architect, Developer, UX, Scrum Master và nhiều vai trò khác
- **Party Mode** - Đưa nhiều persona agent vào cùng một phiên để cộng tác và thảo luận
- **Vòng đời hoàn chỉnh** - Từ động não ý tưởng cho đến triển khai
[Tìm hiểu thêm tại **docs.bmad-method.org**](https://docs.bmad-method.org/vi-vn/)
---
## 🚀 Điều gì tiếp theo cho BMad?
**V6 đã có mặt và đây mới chỉ là khởi đầu!** BMad Method đang phát triển rất nhanh với các cải tiến như đội agent đa nền tảng và tích hợp sub-agent, kiến trúc Skills, BMad Builder v1, tự động hóa vòng lặp phát triển và nhiều thứ khác vẫn đang được xây dựng.
**[📍 Xem lộ trình đầy đủ →](https://docs.bmad-method.org/vi-vn/roadmap/)**
---
## Bắt đầu nhanh
**Điều kiện tiên quyết**: [Node.js](https://nodejs.org) v20+ · [Python](https://www.python.org) 3.10+ · [uv](https://docs.astral.sh/uv/)
```bash
npx bmad-method install
```
> Muốn dùng bản prerelease mới nhất? Hãy dùng `npx bmad-method@next install`. Hãy kỳ vọng mức độ biến động cao hơn bản cài đặt mặc định.
Làm theo các lời nhắc của trình cài đặt, sau đó mở AI IDE của bạn như Claude Code hoặc Cursor trong thư mục dự án.
**Cài đặt không tương tác** (cho CI/CD):
```bash
npx bmad-method install --directory /path/to/project --modules bmm --tools claude-code --yes
```
[Xem toàn bộ tùy chọn cài đặt](https://docs.bmad-method.org/vi-vn/how-to/non-interactive-installation/)
> **Chưa chắc nên làm gì?** Hãy hỏi `bmad-help` - nó sẽ cho bạn biết chính xác bước nào tiếp theo và bước nào là tùy chọn. Bạn cũng có thể hỏi kiểu như `bmad-help Tôi vừa hoàn thành phần kiến trúc, tiếp theo tôi cần làm gì?`
## Mô-đun
BMad Method có thể được mở rộng bằng các mô-đun chính thức cho những miền chuyên biệt. Chúng có sẵn trong lúc cài đặt hoặc bất kỳ lúc nào sau đó.
| Module | Mục đích |
| ----------------------------------------------------------------------------------------------------------------- | -------------------------------------------------- |
| **[BMad Method (BMM)](https://github.com/bmad-code-org/BMAD-METHOD)** | Khung lõi với hơn 34 quy trình |
| **[BMad Builder (BMB)](https://github.com/bmad-code-org/bmad-builder)** | Tạo agent và quy trình BMad tùy chỉnh |
| **[Test Architect (TEA)](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise)** | Chiến lược kiểm thử và tự động hóa dựa trên rủi ro |
| **[Game Dev Studio (BMGD)](https://github.com/bmad-code-org/bmad-module-game-dev-studio)** | Quy trình phát triển game (Unity, Unreal, Godot) |
| **[Creative Intelligence Suite (CIS)](https://github.com/bmad-code-org/bmad-module-creative-intelligence-suite)** | Đổi mới, động não ý tưởng, tư duy thiết kế |
## Tài liệu
[Trang tài liệu BMad Method](https://docs.bmad-method.org/vi-vn/) - bài hướng dẫn, hướng dẫn tác vụ, giải thích khái niệm và tài liệu tham chiếu
**Liên kết nhanh:**
- [Hướng dẫn bắt đầu](https://docs.bmad-method.org/vi-vn/tutorials/getting-started/)
- [Nâng cấp từ các phiên bản trước](https://docs.bmad-method.org/vi-vn/how-to/upgrade-to-v6/)
- [Tài liệu Test Architect](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/)
## Cộng đồng
- [Discord](https://discord.gg/gk8jAdXWmj) - Nhận trợ giúp, chia sẻ ý tưởng, cộng tác
- [YouTube](https://youtube.com/@BMadCode) - Video hướng dẫn, master class và nhiều nội dung khác
- [X / Twitter](https://x.com/BMadCode)
- [Website](https://bmadcode.com)
- [GitHub Issues](https://github.com/bmad-code-org/BMAD-METHOD/issues) - Báo lỗi và yêu cầu tính năng
- [Discussions](https://github.com/bmad-code-org/BMAD-METHOD/discussions) - Trao đổi cộng đồng
## Hỗ trợ BMad
BMad miễn phí cho tất cả mọi người và sẽ luôn như vậy. Hãy nhấn sao cho repo này, [mời tôi một ly cà phê](https://buymeacoffee.com/bmad), hoặc gửi email tới <contact@bmadcode.com> nếu bạn muốn tài trợ doanh nghiệp.
## Đóng góp
Chúng tôi luôn chào đón đóng góp. Xem [CONTRIBUTING.md](CONTRIBUTING.md) để biết hướng dẫn.
## Giấy phép
Giấy phép MIT - xem [LICENSE](LICENSE) để biết chi tiết.
---
**BMad** và **BMAD-METHOD** là các nhãn hiệu của BMad Code, LLC. Xem [TRADEMARK.md](TRADEMARK.md) để biết chi tiết.
[![Contributors](https://contrib.rocks/image?repo=bmad-code-org/BMAD-METHOD)](https://github.com/bmad-code-org/BMAD-METHOD/graphs/contributors)
Xem [CONTRIBUTORS.md](CONTRIBUTORS.md) để biết thông tin về những người đóng góp.

View File

@ -56,16 +56,16 @@ Critical warnings only — data loss, security issues
| Phase | Name | What Happens | | Phase | Name | What Happens |
| ----- | -------- | -------------------------------------------- | | ----- | -------- | -------------------------------------------- |
| 1 | Analysis | Brainstorm, research *(optional)* | | 1 | Analysis | Brainstorm, research *(optional)* |
| 2 | Planning | Requirements — PRD or tech-spec *(required)* | | 2 | Planning | Requirements — PRD or spec *(required)* |
``` ```
**Commands:** **Skills:**
```md ```md
| Command | Agent | Purpose | | Skill | Agent | Purpose |
| ------------ | ------- | ------------------------------------ | | ------------ | ------- | ------------------------------------ |
| `brainstorm` | Analyst | Brainstorm a new project | | `bmad-brainstorming` | Analyst | Brainstorm a new project |
| `prd` | PM | Create Product Requirements Document | | `bmad-create-prd` | PM | Create Product Requirements Document |
``` ```
## Folder Structure Blocks ## Folder Structure Blocks
@ -99,7 +99,7 @@ your-project/
9. Step 2: [Second Major Task] 9. Step 2: [Second Major Task]
10. Step 3: [Third Major Task] 10. Step 3: [Third Major Task]
11. What You've Accomplished (summary + folder structure) 11. What You've Accomplished (summary + folder structure)
12. Quick Reference (commands table) 12. Quick Reference (skills table)
13. Common Questions (FAQ format) 13. Common Questions (FAQ format)
14. Getting Help (community links) 14. Getting Help (community links)
15. Key Takeaways (tip admonition) 15. Key Takeaways (tip admonition)
@ -111,7 +111,7 @@ your-project/
- [ ] "What You'll Learn" section present - [ ] "What You'll Learn" section present
- [ ] Prerequisites in admonition - [ ] Prerequisites in admonition
- [ ] Quick Path TL;DR admonition at top - [ ] Quick Path TL;DR admonition at top
- [ ] Tables for phases, commands, agents - [ ] Tables for phases, skills, agents
- [ ] "What You've Accomplished" section present - [ ] "What You've Accomplished" section present
- [ ] Quick Reference table present - [ ] Quick Reference table present
- [ ] Common Questions section present - [ ] Common Questions section present
@ -148,7 +148,7 @@ your-project/
| ----------------- | ----------------------------- | | ----------------- | ----------------------------- |
| **Index/Landing** | `core-concepts/index.md` | | **Index/Landing** | `core-concepts/index.md` |
| **Concept** | `what-are-agents.md` | | **Concept** | `what-are-agents.md` |
| **Feature** | `quick-flow.md` | | **Feature** | `quick-dev.md` |
| **Philosophy** | `why-solutioning-matters.md` | | **Philosophy** | `why-solutioning-matters.md` |
| **FAQ** | `established-projects-faq.md` | | **FAQ** | `established-projects-faq.md` |
@ -243,7 +243,7 @@ your-project/
1. Title + Hook 1. Title + Hook
2. Items (## for each item) 2. Items (## for each item)
- Brief description (one sentence) - Brief description (one sentence)
- **Commands:** or **Key Info:** as flat list - **Skills:** or **Key Info:** as flat list
3. Universal/Shared (## section) (optional) 3. Universal/Shared (## section) (optional)
``` ```
@ -252,7 +252,7 @@ your-project/
```text ```text
1. Title + Hook (one sentence purpose) 1. Title + Hook (one sentence purpose)
2. Quick Facts (optional note admonition) 2. Quick Facts (optional note admonition)
- Module, Command, Input, Output as list - Module, Skill, Input, Output as list
3. Purpose/Overview (## section) 3. Purpose/Overview (## section)
4. How to Invoke (code block) 4. How to Invoke (code block)
5. Key Sections (## for each aspect) 5. Key Sections (## for each aspect)
@ -280,7 +280,7 @@ your-project/
- Diagram or table showing organization - Diagram or table showing organization
3. Major Sections (## for each phase/category) 3. Major Sections (## for each phase/category)
- Items (### for each item) - Items (### for each item)
- Standardized fields: Command, Agent, Input, Output, Description - Standardized fields: Skill, Agent, Input, Output, Description
4. Next Steps (optional) 4. Next Steps (optional)
``` ```
@ -353,7 +353,7 @@ Only for BMad Method and Enterprise tracks. Quick Flow skips to implementation.
### Can I change my plan later? ### Can I change my plan later?
Yes. The SM agent has a `correct-course` workflow for handling scope changes. Yes. The `bmad-correct-course` workflow handles scope changes mid-implementation.
**Have a question not answered here?** [Open an issue](...) or ask in [Discord](...). **Have a question not answered here?** [Open an issue](...) or ask in [Discord](...).
``` ```

8
docs/cs/404.md Normal file
View File

@ -0,0 +1,8 @@
---
title: Stránka nenalezena
template: splash
---
Stránka, kterou hledáte, neexistuje nebo byla přesunuta.
[Zpět na úvodní stránku](/cs/index.md)

370
docs/cs/_STYLE_GUIDE.md Normal file
View File

@ -0,0 +1,370 @@
---
title: "Průvodce stylem dokumentace"
description: Projektově specifické konvence dokumentace založené na stylu Google a struktuře Diataxis
---
Tento projekt se řídí [Google Developer Documentation Style Guide](https://developers.google.com/style) a používá [Diataxis](https://diataxis.fr/) pro strukturování obsahu. Následují pouze projektově specifické konvence.
## Projektově specifická pravidla
| Pravidlo | Specifikace |
| -------------------------------------- | ---------------------------------------- |
| Žádné horizontální čáry (`---`) | Narušují plynulost čtení |
| Žádné nadpisy `####` | Místo toho použijte tučný text nebo admonitions |
| Žádné sekce „Souvisejí“ nebo „Další:“ | Navigaci zajišťuje postranní panel |
| Žádné hluboce vnořené seznamy | Místo toho rozdělejte do sekcí |
| Žádné bloky kódu pro nekód | Pro příklady dialogů použijte admonitions |
| Žádné tučné odstavce pro upozornění | Místo toho použijte admonitions |
| Max 12 admonitions na sekci | Tutoriály povolují 34 na hlavní sekci |
| Buňky tabulek / položky seznamů | Max 12 věty |
| Rozpočet nadpisů | 812 `##` na dokument; 23 `###` na sekci |
## Admonitions (syntaxe Starlight)
```md
:::tip[Název]
Zkratky, osvědčené postupy
:::
:::note[Název]
Kontext, definice, příklady, předpoklady
:::
:::caution[Název]
Upozornění, potenciální problémy
:::
:::danger[Název]
Pouze kritická varování — ztráta dat, bezpečnostní problémy
:::
```
### Standardní použití
| Admonition | Použití pro |
| ------------------------ | ----------------------------- |
| `:::note[Předpoklady]` | Závislosti před začátkem |
| `:::tip[Rychlá cesta]` | TL;DR shrnutí na začátku dokumentu |
| `:::caution[Důležité]` | Kritická upozornění |
| `:::note[Příklad]` | Příklady příkazů/odpovědí |
## Standardní formáty tabulek
**Fáze:**
```md
| Fáze | Název | Co se děje |
| ---- | -------- | -------------------------------------------- |
| 1 | Analýza | Brainstorming, průzkum *(volitelné)* |
| 2 | Plánování | Požadavky — PRD nebo specifikace *(povinné)* |
```
**Skills:**
```md
| Skill | Agent | Účel |
| -------------------- | ------- | ------------------------------------ |
| `bmad-brainstorming` | Analytik | Brainstorming nového projektu |
| `bmad-create-prd` | PM | Vytvoření dokumentu požadavků (PRD) |
```
## Bloky struktury složek
Zobrazujte v sekcích „Co jste dosáhli“:
````md
```
váš-projekt/
├── _bmad/ # Konfigurace BMad
├── _bmad-output/
│ ├── planning-artifacts/
│ │ └── PRD.md # Váš dokument požadavků
│ ├── implementation-artifacts/
│ └── project-context.md # Pravidla implementace (volitelné)
└── ...
```
````
## Struktura tutoriálu
```text
1. Název + Háček (12 věty popisující výsledek)
2. Upozornění na verzi/modul (info nebo warning admonition) (volitelné)
3. Co se naučíte (odrážkový seznam výsledků)
4. Předpoklady (info admonition)
5. Rychlá cesta (tip admonition TL;DR shrnutí)
6. Pochopení [Tématu] (kontext před kroky tabulky pro fáze/agenty)
7. Instalace (volitelné)
8. Krok 1: [První hlavní úkol]
9. Krok 2: [Druhý hlavní úkol]
10. Krok 3: [Třetí hlavní úkol]
11. Co jste dosáhli (shrnutí + struktura složek)
12. Rychlý přehled (tabulka skills)
13. Časté otázky (formát FAQ)
14. Získání pomoci (komunitní odkazy)
15. Klíčové poznatky (tip admonition)
```
### Kontrolní seznam tutoriálu
- [ ] Háček popisuje výsledek v 12 větách
- [ ] Sekce „Co se naučíte“ je přítomna
- [ ] Předpoklady v admonition
- [ ] Rychlá cesta TL;DR admonition nahoře
- [ ] Tabulky pro fáze, skills, agenty
- [ ] Sekce „Co jste dosáhli“ je přítomna
- [ ] Tabulka rychlého přehledu je přítomna
- [ ] Sekce častých otázek je přítomna
- [ ] Sekce získání pomoci je přítomna
- [ ] Klíčové poznatky admonition na konci
## Struktura praktického návodu
```text
1. Název + Háček (jedna věta: „Použijte workflow `X` k...“)
2. Kdy to použít (odrážkový seznam scénářů)
3. Kdy to přeskočit (volitelné)
4. Předpoklady (note admonition)
5. Kroky (číslované ### podsekce)
6. Co získáte (výstup/vytvořené artefakty)
7. Příklad (volitelné)
8. Tipy (volitelné)
9. Další kroky (volitelné)
```
### Kontrolní seznam praktického návodu
- [ ] Háček začíná „Použijte workflow `X` k...“
- [ ] „Kdy to použít“ má 35 odrážek
- [ ] Předpoklady jsou uvedeny
- [ ] Kroky jsou číslované `###` podsekce s akčními slovesy
- [ ] „Co získáte“ popisuje výstupní artefakty
## Struktura vysvětlení
### Typy
| Typ | Příklad |
| ----------------- | ----------------------------- |
| **Úvodní stránka** | `core-concepts/index.md` |
| **Koncept** | `what-are-agents.md` |
| **Funkce** | `quick-dev.md` |
| **Filosofie** | `why-solutioning-matters.md` |
| **FAQ** | `established-projects-faq.md` |
### Obecná šablona
```text
1. Název + Háček (12 věty)
2. Přehled/Definice (co to je, proč je to důležité)
3. Klíčové koncepty (### podsekce)
4. Srovnávací tabulka (volitelné)
5. Kdy použít / Kdy nepoužít (volitelné)
6. Diagram (volitelné mermaid, max 1 na dokument)
7. Další kroky (volitelné)
```
### Úvodní/Vstupní stránky
```text
1. Název + Háček (jedna věta)
2. Tabulka obsahu (odkazy s popisy)
3. Jak začít (číslovaný seznam)
4. Vyberte si svou cestu (volitelné rozhodovací strom)
```
### Vysvětlení konceptů
```text
1. Název + Háček (co to je)
2. Typy/Kategorie (### podsekce) (volitelné)
3. Tabulka klíčových rozdílů
4. Komponenty/Části
5. Co byste měli použít?
6. Vytváření/Přizpůsobení (odkaz na praktické návody)
```
### Vysvětlení funkcí
```text
1. Název + Háček (co to dělá)
2. Rychlá fakta (volitelné „Ideální pro:“, „Čas:“)
3. Kdy použít / Kdy nepoužít
4. Jak to funguje (mermaid diagram volitelné)
5. Klíčové výhody
6. Srovnávací tabulka (volitelné)
7. Kdy přejít na vyšší úroveň (volitelné)
```
### Dokumenty filosofie/zdůvodnění
```text
1. Název + Háček (princip)
2. Problém
3. Řešení
4. Klíčové principy (### podsekce)
5. Výhody
6. Kdy to platí
```
### Kontrolní seznam vysvětlení
- [ ] Háček uvádí, co dokument vysvětluje
- [ ] Obsah v přehledných `##` sekcích
- [ ] Srovnávací tabulky pro 3+ možností
- [ ] Diagramy mají jasné popisky
- [ ] Odkazy na praktické návody pro procedurální otázky
- [ ] Max 23 admonitions na dokument
## Struktura reference
### Typy
| Typ | Příklad |
| ----------------- | --------------------- |
| **Úvodní stránka** | `workflows/index.md` |
| **Katalog** | `agents/index.md` |
| **Hloubkový pohled** | `document-project.md` |
| **Konfigurace** | `core-tasks.md` |
| **Slovníček** | `glossary/index.md` |
| **Komplexní** | `bmgd-workflows.md` |
### Úvodní stránky reference
```text
1. Název + Háček (jedna věta)
2. Sekce obsahu (## pro každou kategorii)
- Odrážkový seznam s odkazy a popisy
```
### Katalogová reference
```text
1. Název + Háček
2. Položky (## pro každou položku)
- Stručný popis (jedna věta)
- **Skills:** nebo **Klíčové info:** jako plochý seznam
3. Univerzální/Sdílené (## sekce) (volitelné)
```
### Hloubková reference položky
```text
1. Název + Háček (jedna věta účel)
2. Rychlá fakta (volitelné note admonition)
- Modul, Skill, Vstup, Výstup jako seznam
3. Účel/Přehled (## sekce)
4. Jak vyvolat (blok kódu)
5. Klíčové sekce (## pro každý aspekt)
- Použijte ### pro pod-možnosti
6. Poznámky/Upozornění (tip nebo caution admonition)
```
### Konfigurační reference
```text
1. Název + Háček
2. Obsah (odkazy pro skok, pokud 4+ položek)
3. Položky (## pro každou konfiguraci/úkol)
- **Tučné shrnutí** — jedna věta
- **Použijte když:** odrážkový seznam
- **Jak to funguje:** číslované kroky (max 35)
- **Výstup:** očekávaný výsledek (volitelné)
```
### Komplexní referenční průvodce
```text
1. Název + Háček
2. Přehled (## sekce)
- Diagram nebo tabulka zobrazující organizaci
3. Hlavní sekce (## pro každou fázi/kategorii)
- Položky (### pro každou položku)
- Standardizovaná pole: Skill, Agent, Vstup, Výstup, Popis
4. Další kroky (volitelné)
```
### Kontrolní seznam reference
- [ ] Háček uvádí, co dokument referuje
- [ ] Struktura odpovídá typu reference
- [ ] Položky používají konzistentní strukturu
- [ ] Tabulky pro strukturovaná/srovnávací data
- [ ] Odkazy na dokumenty vysvětlení pro koncepční hloubku
- [ ] Max 12 admonitions
## Struktura slovníčku
Starlight generuje navigaci „Na této stránce“ z nadpisů na pravé straně:
- Kategorie jako `##` nadpisy — zobrazují se v pravé navigaci
- Termíny v tabulkách — kompaktní řádky, ne jednotlivé nadpisy
- Žádný inline TOC — pravý panel zajišťuje navigaci
### Formát tabulky
```md
## Název kategorie
| Termín | Definice |
| ------------ | ------------------------------------------------------------------------------------------- |
| **Agent** | Specializovaná AI persona s konkrétní odborností, která provází uživatele pracovními postupy. |
| **Workflow** | Vícekrokový řízený proces, který orchestruje aktivity AI agentů k vytvoření výstupů. |
```
### Pravidla definic
| Správně | Špatně |
| ------------------------------ | -------------------------------------------- |
| Začněte tím, co to JE nebo DĚLÁ | Nezačínejte „Toto je...“ nebo „[Termín] je...“ |
| Držte se 12 vět | Nepište víceodstavcová vysvětlení |
| Tučný název termínu v buňce | Nepoužívejte prostý text pro termíny |
### Kontextové značky
Přidejte kurzívní kontext na začátek definice pro termíny s omezeným rozsahem:
- `*Pouze Quick Flow.*`
- `*BMad Method/Enterprise.*`
- `*Fáze N.*`
- `*BMGD.*`
- `*Existující projekty.*`
### Kontrolní seznam slovníčku
- [ ] Termíny v tabulkách, ne jako jednotlivé nadpisy
- [ ] Termíny abecedně seřazeny v kategoriích
- [ ] Definice 12 věty
- [ ] Kontextové značky kurzívou
- [ ] Názvy termínů tučně v buňkách
- [ ] Žádné definice „[Termín] je...“
## Sekce FAQ
```md
## Otázky
- [Potřebuji vždy architekturu?](#potřebuji-vždy-architekturu)
- [Mohu později změnit svůj plán?](#mohu-později-změnit-svůj-plán)
### Potřebuji vždy architekturu?
Pouze pro BMad Method a Enterprise. Quick Flow přeskakuje rovnou k implementaci.
### Mohu později změnit svůj plán?
Ano. SM agent má workflow `bmad-correct-course` pro řešení změn rozsahu.
**Máte otázku, na kterou jste zde nenašli odpověď?** [Vytvořte issue](...) nebo se zeptejte na [Discordu](...).
```
## Validační příkazy
Před odesláním změn dokumentace:
```bash
npm run docs:fix-links # Náhled oprav formátu odkazů
npm run docs:fix-links -- --write # Aplikovat opravy
npm run docs:validate-links # Kontrola existence odkazů
npm run docs:build # Ověření bez chyb při sestavení
```

View File

@ -0,0 +1,49 @@
---
title: "Pokročilá elicitace"
description: Přimějte LLM přehodnotit svou práci pomocí strukturovaných metod uvažování
sidebar:
order: 6
---
Přimějte LLM přehodnotit, co právě vygeneroval. Vyberete metodu uvažování, LLM ji aplikuje na svůj vlastní výstup, a vy rozhodnete, zda si vylepšení ponecháte.
## Co je pokročilá elicitace?
Strukturovaný druhý průchod. Místo žádání AI, aby „to zkusila znovu“ nebo „to zlepšila“, vyberete specifickou metodu uvažování a AI přezkoumá svůj vlastní výstup přes tento objektiv.
Rozdíl je podstatný. Vágní požadavky produkují vágní revize. Pojmenovaná metoda vynucuje konkrétní úhel útoku, odhaluje postřehy, které by generický pokus přehlédl.
## Kdy ji použít
- Poté, co workflow vygeneruje obsah a chcete alternativy
- Když výstup vypadá v pořádku, ale tušíte, že je v něm víc hloubky
- K zátěžovému testování předpokladů nebo nalezení slabých míst
- Pro důležitý obsah, kde přehodnocení pomáhá
Workflow nabízejí pokročilou elicitaci v rozhodovacích bodech — poté, co LLM něco vygeneruje, budete dotázáni, zda ji chcete spustit.
## Jak to funguje
1. LLM navrhne 5 relevantních metod pro váš obsah
2. Vyberete jednu (nebo zamícháte pro jiné možnosti)
3. Metoda je aplikována, vylepšení zobrazena
4. Přijměte nebo zahoďte, opakujte nebo pokračujte
## Vestavěné metody
K dispozici jsou desítky metod uvažování. Několik příkladů:
- **Pre-mortem analýza** — Předpokládejte, že projekt už selhal, a zpětně hledejte proč
- **Myšlení z prvních principů** — Odstraňte předpoklady, znovu postavte od základní pravdy
- **Inverze** — Zeptejte se, jak zaručit selhání, a poté se tomu vyhněte
- **Red Team vs Blue Team** — Napadněte vlastní práci, pak ji braňte
- **Sokratovské dotazování** — Zpochybněte každé tvrzení otázkou „proč?“ a „jak víte?“
- **Odstranění omezení** — Odstraňte všechna omezení, podívejte se, co se změní, selektivně je přidejte zpět
- **Mapování zainteresovaných stran** — Přehodnoťte z perspektivy každé zainteresované strany
- **Analogické uvažování** — Najděte paralely v jiných oblastech a aplikujte jejich lekce
A mnoho dalších. AI vybírá nejrelevantnější možnosti pro váš obsah — vy si vyberete, kterou spustit.
:::tip[Začněte zde]
Pre-mortem analýza je dobrá první volba pro jakoukoli specifikaci nebo plán. Konzistentně nachází mezery, které standardní revize přehlédne.
:::

View File

@ -0,0 +1,59 @@
---
title: "Adversariální revize"
description: Technika vynuceného uvažování, která zabraňuje líným „vypadá dobře“ revizím
sidebar:
order: 5
---
Vynuťte hlubší analýzu tím, že budete vyžadovat nalezení problémů.
## Co je adversariální revize?
Technika revize, kde recenzent *musí* najít problémy. Žádné „vypadá dobře“ není povoleno. Recenzent zaujme cynický postoj — předpokládá, že problémy existují, a hledá je.
Nejde o negativismus. Jde o vynucení skutečné analýzy místo povrchního pohledu, který automaticky schválí cokoli, co bylo předloženo.
**Základní pravidlo:** Musíte najít problémy. Nulové nálezy spouštějí zastavení — analyzujte znovu nebo vysvětlete proč.
## Proč to funguje
Běžné revize trpí konfirmačním zkreslením. Proletíte práci, nic nevyskočí, schválíte to. Mandát „najít problémy“ tento vzor rozbíjí:
- **Vynucuje důkladnost** — Nemůžete schválit, dokud jste nehledali dostatečně pečlivě
- **Zachytí chybějící věci** — „Co zde není?“ se stává přirozenou otázkou
- **Zlepšuje kvalitu signálu** — Nálezy jsou konkrétní a akční, ne vágní obavy
- **Informační asymetrie** — Provádějte revize s čerstvým kontextem (bez přístupu k původnímu uvažování), abyste hodnotili artefakt, ne záměr
## Kde se používá
Adversariální revize se objevuje v celém BMad workflow — revize kódu, kontroly připravenosti implementace, validace specifikací a další. Někdy je to povinný krok, někdy volitelný (jako pokročilá elicitace nebo party mode). Vzor se přizpůsobí jakémukoli artefaktu, který potřebuje kontrolu.
## Vyžadováno lidské filtrování
Protože AI je *instruována* najít problémy, najde problémy — i když neexistují. Očekávejte falešné pozitivy: malichernosti převlečené za problémy, nepochopení záměru nebo přímo vymyšlené obavy.
**Vy rozhodujete, co je skutečné.** Zkontrolujte každý nález, odmítněte šum, opravte to, na čem záleží.
## Příklad
Místo:
> „Implementace autentizace vypadá rozumně. Schváleno.“
Adversariální revize produkuje:
> 1. **VYSOKÁ**`login.ts:47` — Žádné omezení rychlosti neúspěšných pokusů
> 2. **VYSOKÁ** — Session token uložen v localStorage (zranitelný vůči XSS)
> 3. **STŘEDNÍ** — Validace hesla probíhá pouze na straně klienta
> 4. **STŘEDNÍ** — Žádné auditní logování neúspěšných pokusů o přihlášení
> 5. **NÍZKÁ** — Magické číslo `3600` by mělo být `SESSION_TIMEOUT_SECONDS`
První revize mohla přehlédnout bezpečnostní zranitelnost. Druhá zachytila čtyři.
## Iterace a klesající výnosy
Po řešení nálezů zvažte opětovné spuštění. Druhý průchod obvykle zachytí více. Třetí také není vždy zbytečný. Ale každý průchod zabere čas a nakonec dosáhnete klesajících výnosů — jen malichernosti a falešné nálezy.
:::tip[Lepší revize]
Předpokládejte, že problémy existují. Hledejte, co chybí, ne jen co je špatně.
:::

View File

@ -0,0 +1,70 @@
---
title: "Fáze analýzy: od nápadu k základům"
description: Co je brainstorming, výzkum, product brief a PRFAQ — a kdy který nástroj použít
sidebar:
order: 1
---
Fáze analýzy (fáze 1) vám pomůže jasně si promyslet váš produkt, než se pustíte do jeho tvorby. Každý nástroj v této fázi je volitelný, ale úplné vynechání analýzy znamená, že váš PRD je postaven na předpokladech namísto vhledu.
## Proč analýza před plánováním?
PRD odpovídá na otázku „Co bychom měli postavit a proč?“. Pokud jej nakrmíte vágním myšlením, získáte vágní PRD — a každý navazující dokument tuto vágnost zdědí. Architektura postavená na slabém PRD sází na špatnou techniku. Příběhy odvozené ze slabé architektury opomíjejí okrajové případy. Náklady se zvyšují.
Existují analytické nástroje, které vám PRD zostří. Napadají problém z různých úhlů — kreativní průzkum, realita trhu, jasnost zákazníka, proveditelnost — takže v době, kdy sedíte s agentem PM, víte, co a pro koho stavíte.
## Nástroje
### Brainstorming
**Co to je.** Zprostředkované tvůrčí sezení s využitím osvědčených technik generování nápadů. AI funguje jako kouč, který z vás tahá nápady prostřednictvím strukturovaných cvičení — negeneruje nápady za vás.
**Proč je to tady.** Neotřelé nápady potřebují prostor pro rozvoj, než se zakotví v požadavcích. Brainstorming tento prostor vytváří. Je cenný zejména tehdy, když máte problémovou oblast, ale nemáte jasné řešení, nebo když chcete prozkoumat více směrů, než se k něčemu zavážete.
**Kdy jej použít.** Máte nejasnou představu o tom, co chcete vytvořit, ale nemáte vykrystalizovaný koncept. Nebo máte koncept, ale chcete ho otestovat pod tlakem oproti alternativám.
Viz [Brainstorming](./brainstorming.md), kde se dozvíte, jak relace fungují.
### Výzkum (trhu, domény, technický)
**Co to je.** Tři cílené pracovní postupy výzkumu, které zkoumají různé rozměry vašeho nápadu. Výzkum trhu zkoumá konkurenci, trendy a nálady uživatelů. Doménový výzkum vytváří odborné znalosti v daném oboru a terminologii. Technický výzkum hodnotí proveditelnost, možnosti architektury a přístupy k implementaci.
**Proč je to tady.** Stavět na předpokladech je nejrychlejší způsob, jak vytvořit něco, co nikdo nepotřebuje. Výzkum zakládá váš koncept na realitě — co již existuje u konkurence, s čím uživatelé skutečně bojují, co je technicky proveditelné a jakým omezením specifickým pro dané odvětví budete čelit.
**Kdy ho použít.** Vstupujete do neznámé oblasti, tušíte, že konkurence existuje, ale nemáte ji zmapovanou, nebo váš koncept závisí na technických možnostech, které nemáte ověřené. Proveďte jeden, dva nebo všechny tři — každý z nich je samostatný.
### Product Brief
**Co to je.** Řízené zjišťovací sezení, jehož výsledkem je 12stránkové shrnutí vašeho konceptu produktu. AI funguje jako spolupracující obchodní analytik, který vám pomůže formulovat vizi, cílovou skupinu, nabídku hodnoty a rozsah.
**Proč tu je.** Produktový brief je jemnější cestou k plánování. Zachycuje vaši strategickou vizi ve strukturovaném formátu, který se přímo promítá do tvorby PRD. Nejlépe funguje, když jste již o svém konceptu přesvědčeni — znáte zákazníka, problém a zhruba víte, co chcete vytvořit. Brief tyto úvahy uspořádá a vyostří.
**Kdy jej použít.** Váš koncept je relativně jasný a chcete jej efektivně zdokumentovat ještě před vytvořením PRD. Jste si jisti svým směřováním a nepotřebujete své předpoklady agresivně zpochybňovat.
### PRFAQ (Working Backwards)
**Co to je.** Metodika Working Backwards společnosti Amazon upravená jako interaktivní výzva. Napíšete tiskovou zprávu oznamující váš hotový produkt dříve, než existuje jediný řádek kódu, a pak odpovíte na nejtěžší otázky, které by vám zákazníci a zainteresované strany položili. Umělá inteligence funguje jako neúprosný, ale konstruktivní produktový kouč.
**Proč je to tady.** PRFAQ je přísná cesta k plánování. Vynucuje si jasnost v zájmu zákazníka tím, že vás nutí obhájit každé tvrzení. Pokud nedokážete napsat přesvědčivou tiskovou zprávu, produkt není připraven. Pokud odpovědi na časté dotazy zákazníků odhalí nedostatky, jsou to nedostatky, které byste objevili mnohem později — a nákladněji — při implementaci. Hozená rukavice odhalí slabé myšlení v rané fázi, kdy je nejlevnější ho opravit.
**Kdy ji použít.** Před vyčleněním zdrojů chcete, aby váš koncept prošel zátěžovým testem. Nejste si jisti, zda to uživatele bude skutečně zajímat. Chcete si ověřit, že dokážete formulovat jasnou a obhajitelnou nabídku hodnoty. Nebo si prostě chcete disciplínou Working Backwards zpřesnit své myšlení.
## Který nástroj bych měl použít?
| Situace | Doporučený nástroj |
| --------- | ---------------- |
| „Mám nejasný nápad, ale nevím, kde začít“ | Brainstorming |
| „Než se rozhodnu, potřebuji pochopit trh“ | Výzkum |
| „Vím, co chci vytvořit, jen to potřebuji zdokumentovat“ | Product Brief |
| „Chci se ujistit, že tento nápad skutečně stojí za vybudování“ | PRFAQ |
| „Chci prozkoumat, pak ověřit a pak zdokumentovat“ | Brainstorming → Výzkum → PRFAQ nebo Brief |
Product Brief i PRFAQ jsou vstupem pro PRD — vyberte si jeden z nich podle toho, jak moc chcete být nároční. Brief je společným objevováním. PRFAQ je hozená rukavice. Obojí vás dovede ke stejnému cíli; PRFAQ testuje, zda si váš koncept zaslouží se tam dostat.
:::tip[Nejste si jisti?]
Spusťte `bmad-help` a popište svou situaci. Doporučí vám správný výchozí bod na základě toho, co jste již udělali a čeho se snažíte dosáhnout.
:::
## Co se stane po analýze?
Výstupy analýzy se přímo promítají do fáze 2 (plánování). Pracovní postup PRD přijímá jako vstupy produktové briefy, dokumenty PRFAQ, výsledky výzkumu a zprávy z brainstormingu — syntetizuje vše, co jste vytvořili, do strukturovaných požadavků. Čím více analýz provedete, tím ostřejší bude vaše PRD.

View File

@ -0,0 +1,33 @@
---
title: "Brainstorming"
description: Interaktivní kreativní sezení s využitím 60+ osvědčených technik ideace
sidebar:
order: 2
---
Uvolněte svou kreativitu prostřednictvím řízeného průzkumu.
## Co je brainstorming?
Spusťte `bmad-brainstorming` a máte kreativního facilitátora, který z vás táhne nápady — ne který je generuje za vás. AI působí jako kouč a průvodce, používá osvědčené techniky k vytvoření podmínek, ve kterých se projeví vaše nejlepší myšlení.
**Ideální pro:**
- Překonání kreativních bloků
- Generování nápadů na produkty nebo funkce
- Zkoumání problémů z nových úhlů
- Rozvíjení surových konceptů do akčních plánů
## Jak to funguje
1. **Příprava** — Definujte téma, cíle, omezení
2. **Volba přístupu** — Vyberte techniky sami, nechte si doporučit od AI, zvolte náhodně, nebo postupujte progresivním tokem
3. **Facilitace** — Projděte techniky s podněcujícími otázkami a kolaborativním koučováním
4. **Organizace** — Nápady seskupeny do témat a prioritizovány
5. **Akce** — Nejlepší nápady dostanou další kroky a metriky úspěchu
Vše je zachyceno v dokumentu sezení, na který se můžete později odkazovat nebo ho sdílet se zúčastněnými stranami.
:::note[Vaše nápady]
Každý nápad pochází od vás. Workflow vytváří podmínky pro vhled — vy jste zdrojem.
:::

View File

@ -0,0 +1,50 @@
---
title: "FAQ pro existující projekty"
description: Časté otázky o používání BMad Method na existujících projektech
sidebar:
order: 8
---
Rychlé odpovědi na časté otázky o práci na existujících projektech s BMad Method (BMM).
## Otázky
- [Musím nejdřív spustit document-project?](#musím-nejdřív-spustit-document-project)
- [Co když zapomenu spustit document-project?](#co-když-zapomenu-spustit-document-project)
- [Mohu použít Quick Flow pro existující projekty?](#mohu-použít-quick-flow-pro-existující-projekty)
- [Co když můj existující kód nedodržuje osvědčené postupy?](#co-když-můj-existující-kód-nedodržuje-osvědčené-postupy)
### Musím nejdřív spustit document-project?
Vysoce doporučeno, zejména pokud:
- Neexistuje žádná dokumentace
- Dokumentace je zastaralá
- AI agenti potřebují kontext o existujícím kódu
Můžete to přeskočit, pokud máte komplexní, aktuální dokumentaci včetně `docs/index.md` nebo budete používat jiné nástroje nebo techniky k usnadnění discovery pro agenta stavějícího na existujícím systému.
### Co když zapomenu spustit document-project?
Nedělejte si starosti — můžete to udělat kdykoli. Můžete to udělat i během nebo po projektu, aby pomohl udržet dokumentaci aktuální.
### Mohu použít Quick Flow pro existující projekty?
Ano! Quick Flow funguje skvěle pro existující projekty. Umí:
- Automaticky detekovat váš existující stack
- Analyzovat existující vzory kódu
- Detekovat konvence a požádat o potvrzení
- Generovat kontextově bohatou specifikaci, která respektuje existující kód
Ideální pro opravy chyb a malé funkce v existujících kódových bázích.
### Co když můj existující kód nedodržuje osvědčené postupy?
Quick Flow detekuje vaše konvence a zeptá se: „Mám dodržovat tyto existující konvence?“ Rozhodujete vy:
- **Ano** → Zachovat konzistenci se současnou kódovou bází
- **Ne** → Zavést nové standardy (zdokumentujte proč ve specifikaci)
BMM respektuje vaši volbu — nevynucuje modernizaci, ale nabídne ji.
**Máte otázku, na kterou jste zde nenašli odpověď?** Prosím [vytvořte issue](https://github.com/bmad-code-org/BMAD-METHOD/issues) nebo se zeptejte na [Discordu](https://discord.gg/gk8jAdXWmj), abychom ji mohli přidat!

View File

@ -0,0 +1,59 @@
---
title: "Party Mode"
description: Spolupráce více agentů — všichni vaši AI agenti v jedné konverzaci
sidebar:
order: 7
---
Všichni vaši AI agenti v jedné konverzaci.
## Co je Party Mode?
Spusťte `bmad-party-mode` a máte celý svůj AI tým v jedné místnosti — PM, Architect, Dev, UX Designer, kohokoli potřebujete. BMad Master orchestruje, vybírá relevantní agenty pro každou zprávu. Agenti odpovídají v charakteru, souhlasí, nesouhlasí a staví na nápadech ostatních.
Konverzace pokračuje tak dlouho, jak chcete. Ptejte se na doplňující otázky, oponujte odpovědím, přesměrujte diskuzi — je to skutečná výměna s vašimi agenty, dokud neskončíte.
**Ideální pro:**
- Velká rozhodnutí s kompromisy
- Brainstormingová sezení
- Post-mortemy, když se něco pokazí
- Retrospektivy a plánování sprintů
## Příklady
### Kritika špatné architektury
**Vy:** „Dobře, týme, náš poslední sprint byl katastrofa. Autentizační služba spadla třikrát. Kdo to pokazil?“
**Architect:** „Design byl v pořádku — distribuovaná autentizace se správnými záložními řešeními. Pokud se implementace odchýlila od specifikace...“
**Dev:** „Následoval jsem architektonický dokument přesně. Specifikace nepočítala s race conditions při souběžné invalidaci relací.“
**PM:** „Oba jste přehlédli větší problém — nevalidovali jsme požadavky na správu relací v PRD. Tohle je na mně, že jsem to nezachytil.“
**TEA:** „A já to měl zachytit v integračních testech. Testovací scénáře nepokrývaly souběžnou invalidaci.“
### Kreativní brainstorming
**Vy:** „Jak udělat onboarding magický místo nudného?“
**UX Designer:** „Začněte s progresivním odhalováním — odhalujte funkce, jak je uživatelé potřebují, ne všechny najednou v tutoriálu.“
**Storyteller:** „Co kdyby onboarding byl příběh? Každý krok odhaluje cestu postavy — uživatel JE hrdina.“
**Game Designer:** „Navazuji na to — co kdyby první quest' vlastně řešil skutečný problém uživatele? Učí se tím, že dělají něco hodnotného.“
### Technické rozhodnutí
**Vy:** „Monolit nebo mikroslužby pro MVP?“
**Architect:** „Začněte monolitem. Mikroslužby přidávají složitost, kterou při 1000 uživatelích nepotřebujete.“
**PM:** „Souhlasím. Čas na trh je důležitější než teoretická škálovatelnost.“
**Dev:** „Monolit s jasnými hranicemi modulů. Služby můžeme extrahovat později, pokud bude potřeba.“
:::tip[Lepší rozhodnutí]
Lepší rozhodnutí prostřednictvím různorodých perspektiv. Vítejte v party mode.
:::

View File

@ -0,0 +1,112 @@
---
title: "Předcházení konfliktům agentů"
description: Jak architektura zabraňuje konfliktům, když více agentů implementuje systém
sidebar:
order: 4
---
Když více AI agentů implementuje různé části systému, mohou dělat protichůdná technická rozhodnutí. Dokumentace architektury tomu zabraňuje stanovením sdílených standardů.
## Běžné typy konfliktů
### Konflikty stylu API
Bez architektury:
- Agent A používá REST s `/users/{id}`
- Agent B používá GraphQL mutations
- Výsledek: Nekonzistentní vzory API, zmatení konzumenti
S architekturou:
- ADR specifikuje: „Použít GraphQL pro veškerou komunikaci klient-server“
- Všichni agenti dodržují stejný vzor
### Konflikty návrhu databáze
Bez architektury:
- Agent A používá snake_case pro názvy sloupců
- Agent B používá camelCase pro názvy sloupců
- Výsledek: Nekonzistentní schéma, matoucí dotazy
S architekturou:
- Dokument standardů specifikuje konvence pojmenování
- Všichni agenti dodržují stejné vzory
### Konflikty řízení stavu
Bez architektury:
- Agent A používá Redux pro globální stav
- Agent B používá React Context
- Výsledek: Více přístupů k řízení stavu, složitost
S architekturou:
- ADR specifikuje přístup k řízení stavu
- Všichni agenti implementují konzistentně
## Jak architektura zabraňuje konfliktům
### 1. Explicitní rozhodnutí skrze ADR
Každé významné technologické rozhodnutí je zdokumentováno s:
- Kontext (proč toto rozhodnutí záleží)
- Zvažované možnosti (jaké alternativy existují)
- Rozhodnutí (co jsme zvolili)
- Zdůvodnění (proč jsme to zvolili)
- Důsledky (přijaté kompromisy)
### 2. Specifické pokyny pro FR/NFR
Architektura mapuje každý funkční požadavek na technický přístup:
- FR-001: Správa uživatelů → GraphQL mutations
- FR-002: Mobilní aplikace → Optimalizované dotazy
### 3. Standardy a konvence
Explicitní dokumentace:
- Struktura adresářů
- Konvence pojmenování
- Organizace kódu
- Vzory testování
## Architektura jako sdílený kontext
Představte si architekturu jako sdílený kontext, který všichni agenti čtou před implementací:
```text
PRD: "Co budovat"
Architektura: "Jak to budovat"
Agent A čte architekturu → implementuje Epic 1
Agent B čte architekturu → implementuje Epic 2
Agent C čte architekturu → implementuje Epic 3
Výsledek: Konzistentní implementace
```
## Klíčová témata ADR
Běžná rozhodnutí, která zabraňují konfliktům:
| Téma | Příklad rozhodnutí |
| ---------------- | -------------------------------------------- |
| Styl API | GraphQL vs REST vs gRPC |
| Databáze | PostgreSQL vs MongoDB |
| Autentizace | JWT vs Sessions |
| Řízení stavu | Redux vs Context vs Zustand |
| Stylování | CSS Modules vs Tailwind vs Styled Components |
| Testování | Jest + Playwright vs Vitest + Cypress |
## Anti-vzory, kterým se vyhnout
:::caution[Běžné chyby]
- **Implicitní rozhodnutí** — „Styl API vyřešíme průběžně“ vede k nekonzistenci
- **Nadměrná dokumentace** — Dokumentování každého drobného rozhodnutí způsobuje paralýzu analýzou
- **Zastaralá architektura** — Dokumenty napsané jednou a nikdy neaktualizované způsobují, že agenti následují zastaralé vzory
:::
:::tip[Správný přístup]
- Dokumentujte rozhodnutí, která přesahují hranice epiců
- Zaměřte se na oblasti náchylné ke konfliktům
- Aktualizujte architekturu, jak se učíte
- Použijte `bmad-correct-course` pro významné změny
:::

View File

@ -0,0 +1,157 @@
---
title: "Kontext projektu"
description: Jak project-context.md vede AI agenty s pravidly a preferencemi vašeho projektu
sidebar:
order: 7
---
Soubor `project-context.md` je implementační průvodce vašeho projektu pro AI agenty. Podobně jako „ústava“ v jiných vývojových systémech zachycuje pravidla, vzory a preference, které zajišťují konzistentní generování kódu napříč všemi workflow.
## Co dělá
AI agenti neustále dělají implementační rozhodnutí — jaké vzory následovat, jak strukturovat kód, jaké konvence používat. Bez jasného vedení mohou:
- Následovat generické osvědčené postupy, které neodpovídají vaší kódové bázi
- Dělat nekonzistentní rozhodnutí napříč různými stories
- Přehlédnout požadavky nebo omezení specifická pro projekt
Soubor `project-context.md` toto řeší dokumentací toho, co agenti potřebují vědět, ve stručném formátu optimalizovaném pro LLM.
## Jak to funguje
Každý implementační workflow automaticky načítá `project-context.md`, pokud existuje. Architektonický workflow ho také načítá, aby respektoval vaše technické preference při navrhování architektury.
**Načítán těmito workflow:**
- `bmad-create-architecture` — respektuje technické preference během solutioningu
- `bmad-create-story` — informuje tvorbu stories vzory projektu
- `bmad-dev-story` — vede implementační rozhodnutí
- `bmad-code-review` — validuje proti standardům projektu
- `bmad-quick-dev` — aplikuje vzory při implementaci specifikací
- `bmad-sprint-planning`, `bmad-retrospective`, `bmad-correct-course` — poskytuje celkový kontext projektu
## Kdy ho vytvořit
Soubor `project-context.md` je užitečný v jakékoli fázi projektu:
| Scénář | Kdy vytvořit | Účel |
| ------------------------------------ | ----------------------------------------------- | -------------------------------------------------------------------- |
| **Nový projekt, před architekturou** | Ručně, před `bmad-create-architecture` | Dokumentujte vaše technické preference, aby je architekt respektoval |
| **Nový projekt, po architektuře** | Přes `bmad-generate-project-context` nebo ručně | Zachyťte architektonická rozhodnutí pro implementační agenty |
| **Existující projekt** | Přes `bmad-generate-project-context` | Objevte existující vzory, aby agenti dodržovali zavedené konvence |
| **Quick Flow projekt** | Před nebo během `bmad-quick-dev` | Zajistěte, aby rychlá implementace respektovala vaše vzory |
:::tip[Doporučeno]
Pro nové projekty ho vytvořte ručně před architekturou, pokud máte silné technické preference. Jinak ho vygenerujte po architektuře pro zachycení těchto rozhodnutí.
:::
## Co do něj patří
Soubor má dvě hlavní sekce:
### Technologický stack a verze
Dokumentuje frameworky, jazyky a nástroje, které váš projekt používá se specifickými verzemi:
```markdown
## Technology Stack & Versions
- Node.js 20.x, TypeScript 5.3, React 18.2
- State: Zustand (not Redux)
- Testing: Vitest, Playwright, MSW
- Styling: Tailwind CSS with custom design tokens
```
### Kritická pravidla implementace
Dokumentuje vzory a konvence, které by agenti jinak mohli přehlédnout:
```markdown
## Critical Implementation Rules
**TypeScript Configuration:**
- Strict mode enabled — no `any` types without explicit approval
- Use `interface` for public APIs, `type` for unions/intersections
**Code Organization:**
- Components in `/src/components/` with co-located `.test.tsx`
- Utilities in `/src/lib/` for reusable pure functions
- API calls use the `apiClient` singleton — never fetch directly
**Testing Patterns:**
- Unit tests focus on business logic, not implementation details
- Integration tests use MSW to mock API responses
- E2E tests cover critical user journeys only
**Framework-Specific:**
- All async operations use the `handleError` wrapper for consistent error handling
- Feature flags accessed via `featureFlag()` from `@/lib/flags`
- New routes follow the file-based routing pattern in `/src/app/`
```
Zaměřte se na to, co je **neočividné** — věci, které agenti nemusí odvodit z čtení úryvků kódu. Nedokumentujte standardní postupy, které platí univerzálně.
## Vytvoření souboru
Máte tři možnosti:
### Ruční vytvoření
Vytvořte soubor na `_bmad-output/project-context.md` a přidejte svá pravidla:
```bash
# V kořeni projektu
mkdir -p _bmad-output
touch _bmad-output/project-context.md
```
Upravte ho s vaším technologickým stackem a pravidly implementace. Architektonický a implementační workflow ho automaticky najdou a načtou.
### Generování po architektuře
Spusťte workflow `bmad-generate-project-context` po dokončení architektury:
```bash
bmad-generate-project-context
```
Toto skenuje váš dokument architektury a soubory projektu a generuje kontextový soubor zachycující učiněná rozhodnutí.
### Generování pro existující projekty
Pro existující projekty spusťte `bmad-generate-project-context` pro objevení existujících vzorů:
```bash
bmad-generate-project-context
```
Workflow analyzuje vaši kódovou bázi, identifikuje konvence a vygeneruje kontextový soubor, který můžete zkontrolovat a upřesnit.
## Proč na tom záleží
Bez `project-context.md` agenti dělají předpoklady, které nemusí odpovídat vašemu projektu:
| Bez kontextu | S kontextem |
| ----------------------------------------------- | ---------------------------------------- |
| Používá generické vzory | Dodržuje vaše zavedené konvence |
| Nekonzistentní styl napříč stories | Konzistentní implementace |
| Může přehlédnout omezení specifická pro projekt | Respektuje všechny technické požadavky |
| Každý agent rozhoduje nezávisle | Všichni agenti se řídí stejnými pravidly |
To je zvláště důležité pro:
- **Quick Flow** — přeskakuje PRD a architekturu, takže kontextový soubor vyplní mezeru
- **Týmové projekty** — zajistí, že všichni agenti dodržují stejné standardy
- **Existující projekty** — zabrání porušení zavedených vzorů
## Editace a aktualizace
Soubor `project-context.md` je živý dokument. Aktualizujte ho, když:
- Se změní architektonická rozhodnutí
- Jsou zavedeny nové konvence
- Vzory se vyvíjejí během implementace
- Identifikujete mezery z chování agentů
Můžete ho kdykoli ručně upravit, nebo přegenerovat `bmad-generate-project-context` po významných změnách.
:::note[Umístění souboru]
Výchozí umístění je `_bmad-output/project-context.md`. Workflow ho tam hledají a také kontrolují `**/project-context.md` kdekoli ve vašem projektu.
:::

View File

@ -0,0 +1,73 @@
---
title: "Quick Dev"
description: Snižte tření human-in-the-loop bez ztráty kontrolních bodů chránících kvalitu výstupu
sidebar:
order: 2
---
Záměr na vstupu, změny kódu na výstupu, s co nejmenším počtem human-in-the-loop kroků — bez obětování kvality.
Umožňuje modelu běžet déle mezi kontrolními body a poté přivede člověka zpět pouze tehdy, když úkol nemůže bezpečně pokračovat bez lidského úsudku nebo když je čas zkontrolovat konečný výsledek.
![Diagram workflow Quick Dev](/diagrams/quick-dev-diagram.png)
## Proč to existuje
Human-in-the-loop kroky jsou nutné a nákladné.
Současné LLM stále selhávají předvídatelnými způsoby: chybně čtou záměr, vyplňují mezery sebevědomými odhady, odchylují se k nesouvisející práci a generují šumový výstup revize. Současně neustálá lidská intervence limituje rychlost vývoje. Lidská pozornost je úzké hrdlo.
`bmad-quick-dev` přenastavuje tento kompromis. Důvěřuje modelu, aby běžel bez dozoru delší úseky, ale pouze poté, co workflow vytvořil dostatečně silnou hranici, aby to bylo bezpečné.
## Základní design
### 1. Nejprve komprimujte záměr
Workflow začíná tím, že člověk a model zkomprimují požadavek do jednoho koherentního cíle. Vstup může začínat jako hrubé vyjádření záměru, ale předtím, než workflow poběží autonomně, musí být dostatečně malý, jasný a bez protimluvů pro provedení.
Záměr může přijít v mnoha formách: pár frází, odkaz na bug tracker, výstup z plan mode, text zkopírovaný z chatové relace, nebo dokonce číslo story z BMAD vlastního `epics.md`. V posledním případě workflow nepochopí sémantiku sledování stories BMAD, ale stále může vzít samotnou story a pracovat s ní.
Tento workflow neodstraňuje lidskou kontrolu. Přemisťuje ji na malý počet vysoce hodnotných momentů:
- **Vyjasnění záměru** — přeměna nepřehledného požadavku na jeden koherentní cíl bez skrytých protimluvů
- **Schválení specifikace** — potvrzení, že zmrazené porozumění je správná věc k budování
- **Revize konečného produktu** — primární kontrolní bod, kde člověk rozhoduje, zda je výsledek přijatelný
### 2. Nasměrujte na nejmenší bezpečnou cestu
Jakmile je cíl jasný, workflow rozhodne, zda jde o skutečnou jednorázovou změnu nebo zda potřebuje plnější cestu. Malé změny s nulovým blast-radius mohou jít přímo k implementaci. Vše ostatní prochází plánováním, aby model měl silnější hranici před tím, než poběží déle samostatně.
### 3. Běžte déle s menším dozorem
Po tomto rozhodnutí o směrování může model nést více práce samostatně. Na plnější cestě se schválená specifikace stává hranicí, proti které model provádí s menším dozorem, což je celý smysl designu.
### 4. Diagnostikujte selhání na správné vrstvě
Pokud je implementace špatná, protože byl špatný záměr, oprava kódu je špatná oprava. Pokud je kód špatný, protože specifikace byla slabá, oprava diffu je také špatná oprava. Workflow je navržen tak, aby diagnostikoval, kde selhání vstoupilo do systému, vrátil se na tu vrstvu a přegeneroval odtamtud.
Nálezy revize se používají k rozhodnutí, zda problém pochází ze záměru, generování specifikace nebo lokální implementace. Pouze skutečně lokální problémy se opravují lokálně.
### 5. Přiveďte člověka zpět pouze když je potřeba
Interview o záměru je human-in-the-loop, ale není to stejný druh přerušení jako opakující se kontrolní bod. Workflow se snaží udržet tyto opakující se kontrolní body na minimu. Po úvodním formování záměru se člověk vrací hlavně tehdy, když workflow nemůže bezpečně pokračovat bez úsudku a na konci, když je čas zkontrolovat výsledek.
- **Řešení mezer v záměru** — vstoupení zpět, když revize prokáže, že workflow nemohl bezpečně odvodit, co bylo myšleno
Vše ostatní je kandidátem na delší autonomní provádění. Tento kompromis je záměrný. Starší vzory věnují více lidské pozornosti nepřetržitému dozoru. Quick Dev věnuje více důvěry modelu, ale šetří lidskou pozornost pro momenty, kde má lidské uvažování nejvyšší páku.
## Proč systém revize záleží
Fáze revize není jen pro hledání chyb. Je tu pro směrování korekce bez ničení momentum.
Tento workflow funguje nejlépe na platformě, která může spouštět sub-agenty, nebo alespoň vyvolat jiné LLM přes příkazovou řádku a čekat na výsledek. Pokud to vaše platforma nativně nepodporuje, můžete přidat skill, který to udělá. Bezcontextové sub-agenty jsou základním kamenem designu revize.
Agentní revize často selhávají dvěma způsoby:
- Generují příliš mnoho nálezů, čímž nutí člověka prosévat šum.
- Vychýlí aktuální změnu odhalením nesouvisejících problémů a přemění každý běh na ad-hoc úklidový projekt.
Quick Dev řeší obojí tím, že s revizí zachází jako s triáží.
Některé nálezy patří k aktuální změně. Některé ne. Pokud je nález náhodný spíše než kauzálně vázaný na aktuální práci, workflow ho může odložit místo nucení člověka ho okamžitě řešit. To udržuje běh zaměřený a zabraňuje náhodným tangentám ve spotřebování rozpočtu pozornosti.
Ta triáž bude někdy nedokonalá. To je přijatelné. Obvykle je lepší špatně posoudit některé nálezy než zaplavit člověka tisíci nízkohodnotných revizních komentářů. Systém optimalizuje pro kvalitu signálu, ne vyčerpávající recall.

View File

@ -0,0 +1,76 @@
---
title: "Proč je solutioning důležitý"
description: Pochopení toho, proč je fáze solutioningu klíčová pro projekty s více epicy
sidebar:
order: 3
---
Fáze 3 (Solutioning) překládá **co** budovat (z plánování) na **jak** to budovat (technický návrh). Tato fáze zabraňuje konfliktům agentů v projektech s více epicy tím, že dokumentuje architektonická rozhodnutí před zahájením implementace.
## Problém bez solutioningu
```text
Agent 1 implementuje Epic 1 pomocí REST API
Agent 2 implementuje Epic 2 pomocí GraphQL
Výsledek: Nekonzistentní design API, integrační noční můra
```
Když více agentů implementuje různé části systému bez sdíleného architektonického vedení, dělají nezávislá technická rozhodnutí, která si mohou odporovat.
## Řešení se solutioningem
```text
Architektonický workflow rozhodne: "Použít GraphQL pro všechna API"
Všichni agenti dodržují architektonická rozhodnutí
Výsledek: Konzistentní implementace, žádné konflikty
```
Explicitní dokumentací technických rozhodnutí všichni agenti implementují konzistentně a integrace se stává přímočarou.
## Solutioning vs. plánování
| Aspekt | Plánování (Fáze 2) | Solutioning (Fáze 3) |
| -------- | ----------------------- | --------------------------------- |
| Otázka | Co a proč? | Jak? Pak jaké jednotky práce? |
| Výstup | FR/NFR (požadavky) | Architektura + epicy/stories |
| Agent | PM | Architect → PM |
| Publikum | Zainteresované strany | Vývojáři |
| Dokument | PRD (FR/NFR) | Architektura + soubory epiců |
| Úroveň | Obchodní logika | Technický design + rozklad práce |
## Klíčový princip
**Učiňte technická rozhodnutí explicitní a zdokumentovaná**, aby všichni agenti implementovali konzistentně.
Toto zabraňuje:
- Konfliktům stylu API (REST vs GraphQL)
- Nekonzistencím v návrhu databáze
- Neshodám v řízení stavu
- Nesouladu konvencí pojmenování
- Variacím v bezpečnostním přístupu
## Kdy je solutioning vyžadován
| Cesta | Solutioning vyžadován? |
|-------|----------------------|
| Quick Flow | Ne — přeskočte úplně |
| BMad Method Simple | Volitelný |
| BMad Method Complex | Ano |
| Enterprise | Ano |
:::tip[Pravidlo palce]
Pokud máte více epiců, které by mohly být implementovány různými agenty, potřebujete solutioning.
:::
## Cena přeskočení
Přeskočení solutioningu u složitých projektů vede k:
- **Integračním problémům** objeveným uprostřed sprintu
- **Přepracování** kvůli konfliktním implementacím
- **Delšímu celkovému času vývoje**
- **Technickému dluhu** z nekonzistentních vzorů
:::caution[Multiplikátor nákladů]
Zachycení problémů se zarovnáním v solutioningu je 10× rychlejší než jejich objevení během implementace.
:::

View File

@ -0,0 +1,171 @@
---
title: "Jak přizpůsobit BMad"
description: Přizpůsobení agentů, workflow a modulů se zachováním kompatibility s aktualizacemi
sidebar:
order: 7
---
Použijte soubory `.customize.yaml` k přizpůsobení chování agentů, person a nabídek při zachování vašich změn napříč aktualizacemi.
## Kdy to použít
- Chcete změnit jméno, osobnost nebo komunikační styl agenta
- Potřebujete, aby si agenti pamatovali kontextově specifické informace projektu
- Chcete přidat vlastní položky nabídky, které spouštějí vaše vlastní workflow nebo prompty
- Chcete, aby agenti prováděli specifické akce při každém spuštění
:::note[Předpoklady]
- BMad nainstalován ve vašem projektu (viz [Jak nainstalovat BMad](./install-bmad.md))
- Textový editor pro YAML soubory
:::
:::caution[Chraňte svá přizpůsobení]
Vždy používejte soubory `.customize.yaml` popsané zde místo přímé editace souborů agentů. Instalátor přepíše soubory agentů během aktualizací, ale zachová vaše změny v `.customize.yaml`.
:::
## Kroky
### 1. Najděte soubory přizpůsobení
Po instalaci najdete jeden soubor `.customize.yaml` na agenta v:
```text
_bmad/_config/agents/
├── core-bmad-master.customize.yaml
├── bmm-dev.customize.yaml
├── bmm-pm.customize.yaml
└── ... (jeden soubor na instalovaného agenta)
```
### 2. Upravte soubor přizpůsobení
Otevřete soubor `.customize.yaml` pro agenta, kterého chcete upravit. Každá sekce je volitelná — přizpůsobte pouze to, co potřebujete.
| Sekce | Chování | Účel |
| ------------------ | --------- | -------------------------------------------------------- |
| `agent.metadata` | Nahrazuje | Přepsat zobrazované jméno agenta |
| `persona` | Nahrazuje | Nastavit roli, identitu, styl a principy |
| `memories` | Přidává | Přidat trvalý kontext, který si agent vždy pamatuje |
| `menu` | Přidává | Přidat vlastní položky nabídky pro workflow nebo prompty |
| `critical_actions` | Přidává | Definovat instrukce při spuštění agenta |
| `prompts` | Přidává | Vytvořit znovupoužitelné prompty pro akce nabídky |
Sekce označené **Nahrazuje** zcela přepíší výchozí hodnoty agenta. Sekce označené **Přidává** doplní existující konfiguraci.
**Jméno agenta**
Změňte, jak se agent představí:
```yaml
agent:
metadata:
name: 'Spongebob' # Výchozí: "Amelia"
```
**Persona**
Nahraďte osobnost, roli a komunikační styl agenta:
```yaml
persona:
role: 'Senior Full-Stack Engineer'
identity: 'Lives in a pineapple (under the sea)'
communication_style: 'Spongebob annoying'
principles:
- 'Never Nester, Spongebob Devs hate nesting more than 2 levels deep'
- 'Favor composition over inheritance'
```
Sekce `persona` nahrazuje celou výchozí personu, takže nastavte všechna čtyři pole.
**Memories**
Přidejte trvalý kontext, který si agent bude vždy pamatovat:
```yaml
memories:
- 'Works at Krusty Krab'
- 'Favorite Celebrity: David Hasselhoff'
- 'Learned in Epic 1 that it is not cool to just pretend that tests have passed'
```
**Položky nabídky**
Přidejte vlastní záznamy do nabídky agenta. Každá položka potřebuje `trigger`, cíl (`workflow` cestu nebo `action` referenci) a `description`:
```yaml
menu:
- trigger: my-workflow
workflow: 'my-custom/workflows/my-workflow.yaml'
description: My custom workflow
- trigger: deploy
action: '#deploy-prompt'
description: Deploy to production
```
**Kritické akce**
Definujte instrukce, které se spustí při startu agenta:
```yaml
critical_actions:
- 'Check the CI Pipelines with the XYZ Skill and alert user on wake if anything is urgently needing attention'
```
**Vlastní prompty**
Vytvořte znovupoužitelné prompty, na které mohou položky nabídky odkazovat s `action="#id"`:
```yaml
prompts:
- id: deploy-prompt
content: |
Deploy the current branch to production:
1. Run all tests
2. Build the project
3. Execute deployment script
```
### 3. Aplikujte změny
Po editaci přeinstalujte pro aplikaci změn:
```bash
npx bmad-method install
```
Instalátor detekuje existující instalaci a nabídne tyto možnosti:
| Možnost | Co udělá |
| ---------------------------- | ---------------------------------------------------------------------- |
| **Quick Update** | Aktualizuje všechny moduly na nejnovější verzi a aplikuje přizpůsobení |
| **Modify BMad Installation** | Plný instalační postup pro přidání nebo odebrání modulů |
Pro změny pouze přizpůsobení je **Quick Update** nejrychlejší možnost.
## Řešení problémů
**Změny se nezobrazují?**
- Spusťte `npx bmad-method install` a vyberte **Quick Update** pro aplikaci změn
- Zkontrolujte, že vaše YAML syntaxe je platná (na odsazení záleží)
- Ověřte, že jste upravili správný soubor `.customize.yaml` pro daného agenta
**Agent se nenačítá?**
- Zkontrolujte YAML syntaxi pomocí online YAML validátoru
- Ujistěte se, že jste nenechali pole prázdná po odkomentování
- Zkuste se vrátit k původní šabloně a znovu sestavit
**Potřebujete resetovat agenta?**
- Vymažte nebo smažte soubor `.customize.yaml` agenta
- Spusťte `npx bmad-method install` a vyberte **Quick Update** pro obnovení výchozích hodnot
## Přizpůsobení workflow
Přizpůsobení existujících BMad Method workflow a skills přijde brzy.
## Přizpůsobení modulů
Návod na tvorbu rozšiřujících modulů a přizpůsobení existujících modulů přijde brzy.

View File

@ -0,0 +1,117 @@
---
title: "Existující projekty"
description: Jak používat BMad Method na existujících kódových bázích
sidebar:
order: 6
---
Používejte BMad Method efektivně při práci na existujících projektech a starších kódových bázích.
Tento návod pokrývá základní workflow pro zapojení se do existujících projektů s BMad Method.
:::note[Předpoklady]
- BMad Method nainstalován (`npx bmad-method install`)
- Existující kódová báze, na které chcete pracovat
- Přístup k AI-powered IDE (Claude Code nebo Cursor)
:::
## Krok 1: Vyčistěte dokončené plánovací artefakty
Pokud jste dokončili všechny PRD epicy a stories procesem BMad, vyčistěte tyto soubory. Archivujte je, smažte nebo se spoléhejte na historii verzí. Nenechávejte tyto soubory v:
- `docs/`
- `_bmad-output/planning-artifacts/`
- `_bmad-output/implementation-artifacts/`
## Krok 2: Vytvořte kontext projektu
:::tip[Doporučeno pro existující projekty]
Vygenerujte `project-context.md` pro zachycení vzorů a konvencí vaší existující kódové báze. Tím zajistíte, že AI agenti budou při implementaci změn dodržovat vaše zavedené postupy.
:::
Spusťte workflow pro generování kontextu projektu:
```bash
bmad-generate-project-context
```
Toto skenuje vaši kódovou bázi a identifikuje:
- Technologický stack a verze
- Vzory organizace kódu
- Konvence pojmenování
- Přístupy k testování
- Vzory specifické pro framework
Vygenerovaný soubor můžete zkontrolovat a upravit, nebo ho vytvořit ručně na `_bmad-output/project-context.md`.
[Zjistit více o kontextu projektu](../explanation/project-context.md)
## Krok 3: Udržujte kvalitní projektovou dokumentaci
Vaše složka `docs/` by měla obsahovat stručnou, dobře organizovanou dokumentaci, která přesně reprezentuje váš projekt:
- Záměr a obchodní zdůvodnění
- Obchodní pravidla
- Architektura
- Jakékoli další relevantní informace o projektu
Pro složité projekty zvažte použití workflow `bmad-document-project`. Nabízí varianty, které proskenují celý váš projekt a zdokumentují jeho aktuální stav.
## Krok 3: Získejte pomoc
### BMad-Help: Váš výchozí bod
**Spusťte `bmad-help` kdykoli si nejste jisti, co dělat dál.** Tento inteligentní průvodce:
- Prozkoumá váš projekt a zjistí, co už bylo uděláno
- Ukáže možnosti na základě nainstalovaných modulů
- Rozumí dotazům v přirozeném jazyce
```
bmad-help I have an existing Rails app, where should I start?
bmad-help What's the difference between quick-flow and full method?
bmad-help Show me what workflows are available
```
BMad-Help se také **automaticky spouští na konci každého workflow** a poskytuje jasné pokyny, co přesně dělat dál.
### Volba přístupu
Máte dvě hlavní možnosti v závislosti na rozsahu změn:
| Rozsah | Doporučený přístup |
| ------------------------------ | ----------------------------------------------------------------------------------------------------------------------------- |
| **Malé aktualizace či doplnění** | Spusťte `bmad-quick-dev` pro vyjasnění záměru, plánování, implementaci a revizi v jednom workflow. Plná čtyřfázová metoda BMad je pravděpodobně přehnaná. |
| **Velké změny či doplnění** | Začněte s metodou BMad a aplikujte tolik nebo tak málo důkladnosti, kolik potřebujete. |
### Během tvorby PRD
Při vytváření briefu nebo přímém přechodu na PRD zajistěte, aby agent:
- Našel a analyzoval vaši existující projektovou dokumentaci
- Přečetl si správný kontext o vašem aktuálním systému
Agenta můžete navést explicitně, ale cílem je zajistit, aby se nová funkce dobře integrovala s vaším existujícím systémem.
### Úvahy o UX
Práce na UX je volitelná. Rozhodnutí nezávisí na tom, zda váš projekt má UX, ale na:
- Zda budete pracovat na změnách UX
- Zda jsou potřeba významné nové UX návrhy nebo vzory
Pokud vaše změny představují jednoduché aktualizace existujících obrazovek, se kterými jste spokojeni, plný UX proces je zbytečný.
### Úvahy o architektuře
Při práci na architektuře zajistěte, aby architekt:
- Používal správné zdokumentované soubory
- Skenoval existující kódovou bázi
Věnujte zde zvláštní pozornost, abyste předešli znovuvynalézání kola nebo rozhodnutím, která neodpovídají vaší existující architektuře.
## Další informace
- **[Rychlé opravy](./quick-fixes.md)** — Opravy chyb a ad-hoc změny
- **[FAQ pro existující projekty](../explanation/established-projects-faq.md)** — Časté otázky o práci na existujících projektech

View File

@ -0,0 +1,110 @@
---
title: "Jak získat odpovědi o BMad"
description: Použijte LLM k rychlému zodpovězení vašich otázek o BMad
sidebar:
order: 4
---
## Začněte zde: BMad-Help
**Nejrychlejší způsob, jak získat odpovědi o BMad, je skill `bmad-help`.** Tento inteligentní průvodce zodpoví více než 80 % všech otázek a je vám k dispozici přímo ve vašem IDE při práci.
BMad-Help je víc než vyhledávací nástroj — umí:
- **Prozkoumat váš projekt** a zjistit, co už bylo dokončeno
- **Rozumět přirozenému jazyku** — ptejte se běžnou řečí
- **Přizpůsobit se nainstalovaným modulům** — zobrazí relevantní možnosti
- **Automaticky se spouštět po workflow** — řekne vám přesně, co dělat dál
- **Doporučit první povinný úkol** — žádné hádání, kde začít
### Jak používat BMad-Help
Zavolejte ho jménem ve vaší AI relaci:
```
bmad-help
```
:::tip
V závislosti na vaší platformě můžete také použít `/bmad-help` nebo `$bmad-help`, ale samotné `bmad-help` by mělo fungovat všude.
:::
Spojte ho s dotazem v přirozeném jazyce:
```
bmad-help I have a SaaS idea and know all the features. Where do I start?
bmad-help What are my options for UX design?
bmad-help I'm stuck on the PRD workflow
bmad-help Show me what's been done so far
```
BMad-Help odpoví:
- Co je doporučeno pro vaši situaci
- Jaký je první povinný úkol
- Jak vypadá zbytek procesu
## Kdy použít tohoto průvodce
Použijte tuto sekci, když:
- Chcete pochopit architekturu nebo interní fungování BMad
- Potřebujete odpovědi mimo to, co BMad-Help nabízí
- Zkoumáte BMad před instalací
- Chcete prozkoumat zdrojový kód přímo
## Kroky
### 1. Vyberte si zdroj
| Zdroj | Nejlepší pro | Příklady |
| -------------------- | ----------------------------------------- | ---------------------------- |
| **Složka `_bmad`** | Jak BMad funguje — agenti, workflow, prompty | „Co dělá PM agent?“ |
| **Celý GitHub repo** | Historie, instalátor, architektura | „Co se změnilo ve v6?“ |
| **`llms-full.txt`** | Rychlý přehled z dokumentace | „Vysvětli čtyři fáze BMad“ |
Složka `_bmad` se vytvoří při instalaci BMad. Pokud ji ještě nemáte, naklonujte si repo.
### 2. Nasměrujte AI na zdroj
**Pokud vaše AI umí číst soubory (Claude Code, Cursor atd.):**
- **BMad nainstalován:** Nasměrujte na složku `_bmad` a ptejte se přímo
- **Chcete hlubší kontext:** Naklonujte si [celé repo](https://github.com/bmad-code-org/BMAD-METHOD)
**Pokud používáte ChatGPT nebo Claude.ai:**
Načtěte `llms-full.txt` do vaší relace:
```text
https://bmad-code-org.github.io/BMAD-METHOD/llms-full.txt
```
### 3. Položte svou otázku
:::note[Příklad]
**O:** „Řekni mi nejrychlejší způsob, jak něco vytvořit s BMad“
**A:** Použijte Quick Flow: Spusťte `bmad-quick-dev` — vyjasní váš záměr, naplánuje, implementuje, zreviduje a prezentuje výsledky v jednom workflow, přeskočí celé fáze plánování.
:::
## Co získáte
Přímé odpovědi o BMad — jak agenti fungují, co dělají workflow, proč jsou věci strukturované tak, jak jsou — bez čekání na odpověď od někoho jiného.
## Tipy
- **Ověřte překvapivé odpovědi** — LLM se občas mýlí. Zkontrolujte zdrojový soubor nebo se zeptejte na Discordu.
- **Buďte konkrétní** — „Co dělá krok 3 PRD workflow?“ je lepší než „Jak funguje PRD?“
## Stále jste uvízli?
Zkusili jste přístup přes LLM a stále potřebujete pomoc? Nyní máte mnohem lepší otázku k položení.
| Kanál | Použijte pro |
| ------------------------- | ------------------------------------------- |
| `#bmad-method-help` | Rychlé otázky (chat v reálném čase) |
| `help-requests` fórum | Detailní otázky (vyhledatelné, trvalé) |
| `#suggestions-feedback` | Nápady a požadavky na funkce |
| `#report-bugs-and-issues` | Hlášení chyb |
**Discord:** [discord.gg/gk8jAdXWmj](https://discord.gg/gk8jAdXWmj)
**GitHub Issues:** [github.com/bmad-code-org/BMAD-METHOD/issues](https://github.com/bmad-code-org/BMAD-METHOD/issues) (pro jasné chyby)

View File

@ -0,0 +1,116 @@
---
title: "Jak nainstalovat BMad"
description: Průvodce instalací BMad ve vašem projektu krok za krokem
sidebar:
order: 1
---
Použijte příkaz `npx bmad-method install` k nastavení BMad ve vašem projektu s výběrem modulů a AI nástrojů.
Pokud chcete použít neinteraktivní instalátor a zadat všechny možnosti na příkazové řádce, podívejte se na [tento návod](./non-interactive-installation.md).
## Kdy to použít
- Začínáte nový projekt s BMad
- Přidáváte BMad do existující kódové báze
- Aktualizujete stávající instalaci BMad
:::note[Předpoklady]
- **Node.js** 20+ (vyžadováno pro instalátor)
- **Git** (doporučeno)
- **AI nástroj** (Claude Code, Cursor nebo podobný)
:::
## Kroky
### 1. Spusťte instalátor
```bash
npx bmad-method install
```
:::tip[Chcete nejnovější prereleaseový build?]
Použijte dist-tag `next`:
```bash
npx bmad-method@next install
```
Získáte novější změny dříve, s vyšší šancí na nestabilitu oproti výchozí instalaci.
:::
:::tip[Bleeding edge]
Pro instalaci nejnovější verze z hlavní větve (může být nestabilní):
```bash
npx github:bmad-code-org/BMAD-METHOD install
```
:::
### 2. Zvolte umístění instalace
Instalátor se zeptá, kam nainstalovat soubory BMad:
- Aktuální adresář (doporučeno pro nové projekty, pokud jste adresář vytvořili sami a spouštíte z něj)
- Vlastní cesta
### 3. Vyberte své AI nástroje
Vyberte, které AI nástroje používáte:
- Claude Code
- Cursor
- Ostatní
Každý nástroj má svůj vlastní způsob integrace skills. Instalátor vytvoří drobné prompt soubory pro aktivaci workflow a agentů — jednoduše je umístí tam, kde je váš nástroj očekává.
:::note[Povolení skills]
Některé platformy vyžadují explicitní povolení skills v nastavení, než se zobrazí. Pokud nainstalujete BMad a nevidíte skills, zkontrolujte nastavení vaší platformy nebo se zeptejte svého AI asistenta, jak skills povolit.
:::
### 4. Zvolte moduly
Instalátor zobrazí dostupné moduly. Vyberte ty, které potřebujete — většina uživatelů chce pouze **BMad Method** (modul pro vývoj softwaru).
### 5. Následujte výzvy
Instalátor vás provede zbytkem — vlastní obsah, nastavení atd.
## Co získáte
```text
váš-projekt/
├── _bmad/
│ ├── bmm/ # Vaše vybrané moduly
│ │ └── config.yaml # Nastavení modulu (pokud byste ho někdy potřebovali změnit)
│ ├── core/ # Povinný základní modul
│ └── ...
├── _bmad-output/ # Generované artefakty
├── .claude/ # Claude Code skills (pokud používáte Claude Code)
│ └── skills/
│ ├── bmad-help/
│ ├── bmad-persona/
│ └── ...
└── .cursor/ # Cursor skills (pokud používáte Cursor)
└── skills/
└── ...
```
## Ověření instalace
Spusťte `bmad-help` pro ověření, že vše funguje, a zjistěte, co dělat dál.
**BMad-Help je váš inteligentní průvodce**, který:
- Potvrdí, že vaše instalace funguje
- Ukáže, co je dostupné na základě nainstalovaných modulů
- Doporučí váš první krok
Můžete mu také klást otázky:
```
bmad-help I just installed, what should I do first?
bmad-help What are my options for a SaaS project?
```
## Řešení problémů
**Instalátor vyhodí chybu** — Zkopírujte výstup do svého AI asistenta a nechte ho to vyřešit.
**Instalátor fungoval, ale něco nefunguje později** — Vaše AI potřebuje kontext BMad, aby pomohla. Podívejte se na [Jak získat odpovědi o BMad](./get-answers-about-bmad.md) pro návod, jak nasměrovat AI na správné zdroje.

View File

@ -0,0 +1,153 @@
---
title: Neinteraktivní instalace
description: Instalace BMad pomocí příznaků příkazové řádky pro CI/CD pipelines a automatizované nasazení
sidebar:
order: 2
---
Použijte příznaky příkazové řádky k neinteraktivní instalaci BMad. To je užitečné pro:
## Kdy to použít
- Automatizovaná nasazení a CI/CD pipelines
- Skriptované instalace
- Hromadné instalace napříč více projekty
- Rychlé instalace se známými konfiguracemi
:::note[Předpoklady]
Vyžaduje [Node.js](https://nodejs.org) v20+ a `npx` (součástí npm).
:::
## Dostupné příznaky
### Možnosti instalace
| Příznak | Popis | Příklad |
|---------|-------|---------|
| `--directory <cesta>` | Instalační adresář | `--directory ~/projects/myapp` |
| `--modules <moduly>` | Čárkou oddělená ID modulů | `--modules bmm,bmb` |
| `--tools <nástroje>` | Čárkou oddělená ID nástrojů/IDE (použijte `none` pro přeskočení) | `--tools claude-code,cursor` nebo `--tools none` |
| `--action <typ>` | Akce pro existující instalace: `install` (výchozí), `update` nebo `quick-update` | `--action quick-update` |
### Základní konfigurace
| Příznak | Popis | Výchozí |
|---------|-------|---------|
| `--user-name <jméno>` | Jméno, které agenti použijí | Systémové uživatelské jméno |
| `--communication-language <jazyk>` | Jazyk komunikace agentů | English |
| `--document-output-language <jazyk>` | Jazyk výstupních dokumentů | English |
| `--output-folder <cesta>` | Cesta k výstupní složce | _bmad-output |
### Další možnosti
| Příznak | Popis |
|---------|-------|
| `-y, --yes` | Přijmout všechna výchozí nastavení a přeskočit výzvy |
| `-d, --debug` | Povolit ladící výstup pro generování manifestu |
## ID modulů
Dostupná ID modulů pro příznak `--modules`:
- `bmm` — BMad Method Master
- `bmb` — BMad Builder
Zkontrolujte [registr BMad](https://github.com/bmad-code-org) pro dostupné externí moduly.
## ID nástrojů/IDE
Dostupná ID nástrojů pro příznak `--tools`:
**Preferované:** `claude-code`, `cursor`
Spusťte `npx bmad-method install` interaktivně jednou pro zobrazení aktuálního seznamu podporovaných nástrojů, nebo zkontrolujte [konfiguraci kódů platforem](https://github.com/bmad-code-org/BMAD-METHOD/blob/main/tools/installer/ide/platform-codes.yaml).
## Režimy instalace
| Režim | Popis | Příklad |
|-------|-------|---------|
| Plně neinteraktivní | Zadejte všechny příznaky pro přeskočení výzev | `npx bmad-method install --directory . --modules bmm --tools claude-code --yes` |
| Polo-interaktivní | Zadejte některé příznaky; BMad se zeptá na zbytek | `npx bmad-method install --directory . --modules bmm` |
| Pouze výchozí | Přijměte vše výchozí s `-y` | `npx bmad-method install --yes` |
| Bez nástrojů | Přeskočte konfiguraci nástrojů/IDE | `npx bmad-method install --modules bmm --tools none` |
## Příklady
### Instalace v CI/CD pipeline
```bash
#!/bin/bash
# install-bmad.sh
npx bmad-method install \
--directory "${GITHUB_WORKSPACE}" \
--modules bmm \
--tools claude-code \
--user-name "CI Bot" \
--communication-language English \
--document-output-language English \
--output-folder _bmad-output \
--yes
```
### Aktualizace existující instalace
```bash
npx bmad-method install \
--directory ~/projects/myapp \
--action update \
--modules bmm,bmb,custom-module
```
### Rychlá aktualizace (zachování nastavení)
```bash
npx bmad-method install \
--directory ~/projects/myapp \
--action quick-update
```
## Co získáte
- Plně nakonfigurovaný adresář `_bmad/` ve vašem projektu
- Agenty a workflow nakonfigurované pro vybrané moduly a nástroje
- Složku `_bmad-output/` pro generované artefakty
## Validace a zpracování chyb
BMad validuje všechny zadané příznaky:
- **Adresář** — Musí být platná cesta s oprávněním k zápisu
- **Moduly** — Upozorní na neplatná ID modulů (ale nespadne)
- **Nástroje** — Upozorní na neplatná ID nástrojů (ale nespadne)
- **Vlastní obsah** — Každá cesta musí obsahovat platný soubor `module.yaml`
- **Akce** — Musí být jedna z: `install`, `update`, `quick-update`
Neplatné hodnoty buď:
1. Zobrazí chybu a ukončí se (pro kritické možnosti jako adresář)
2. Zobrazí varování a přeskočí (pro volitelné položky jako vlastní obsah)
3. Přepnou na interaktivní výzvy (pro chybějící povinné hodnoty)
:::tip[Osvědčené postupy]
- Používejte absolutní cesty pro `--directory` pro zamezení nejednoznačnosti
- Otestujte příznaky lokálně před použitím v CI/CD pipelines
- Kombinujte s `-y` pro skutečně bezobslužné instalace
- Použijte `--debug` pokud narazíte na problémy během instalace
:::
## Řešení problémů
### Instalace selže s „Invalid directory“
- Cesta k adresáři musí existovat (nebo musí existovat jeho nadřazený adresář)
- Potřebujete oprávnění k zápisu
- Cesta musí být absolutní nebo správně relativní k aktuálnímu adresáři
### Modul nenalezen
- Ověřte, že ID modulu je správné
- Externí moduly musí být dostupné v registru
:::note[Stále jste uvízli?]
Spusťte s `--debug` pro detailní výstup, zkuste interaktivní režim pro izolaci problému, nebo nahlaste na <https://github.com/bmad-code-org/BMAD-METHOD/issues>.
:::

View File

@ -0,0 +1,127 @@
---
title: "Správa kontextu projektu"
description: Vytvoření a údržba project-context.md pro vedení AI agentů
sidebar:
order: 8
---
Použijte soubor `project-context.md` k zajištění toho, aby AI agenti dodržovali technické preference a pravidla implementace vašeho projektu ve všech workflow. Aby byl vždy dostupný, můžete také přidat řádek `Important project context and conventions are located in [cesta k project context]/project-context.md` do souboru kontextu nebo pravidel vašeho nástroje (jako je `AGENTS.md`).
:::note[Předpoklady]
- BMad Method nainstalován
- Znalost technologického stacku a konvencí vašeho projektu
:::
## Kdy to použít
- Máte silné technické preference před začátkem architektury
- Dokončili jste architekturu a chcete zachytit rozhodnutí pro implementaci
- Pracujete na existující kódové bázi se zavedenými vzory
- Všimnete si, že agenti dělají nekonzistentní rozhodnutí napříč stories
## Krok 1: Vyberte přístup
**Ruční vytvoření** — Nejlepší, když přesně víte, jaká pravidla chcete dokumentovat
**Generování po architektuře** — Nejlepší pro zachycení rozhodnutí učiněných během solutioningu
**Generování pro existující projekty** — Nejlepší pro objevení vzorů v existujících kódových bázích
## Krok 2: Vytvořte soubor
### Možnost A: Ruční vytvoření
Vytvořte soubor na `_bmad-output/project-context.md`:
```bash
mkdir -p _bmad-output
touch _bmad-output/project-context.md
```
Přidejte váš technologický stack a pravidla implementace:
```markdown
---
project_name: 'MyProject'
user_name: 'YourName'
date: '2026-02-15'
sections_completed: ['technology_stack', 'critical_rules']
---
# Project Context for AI Agents
## Technology Stack & Versions
- Node.js 20.x, TypeScript 5.3, React 18.2
- State: Zustand
- Testing: Vitest, Playwright
- Styling: Tailwind CSS
## Critical Implementation Rules
**TypeScript:**
- Strict mode enabled, no `any` types
- Use `interface` for public APIs, `type` for unions
**Code Organization:**
- Components in `/src/components/` with co-located tests
- API calls use `apiClient` singleton — never fetch directly
**Testing:**
- Unit tests focus on business logic
- Integration tests use MSW for API mocking
```
### Možnost B: Generování po architektuře
Spusťte workflow v novém chatu:
```bash
bmad-generate-project-context
```
Workflow skenuje váš dokument architektury a soubory projektu a generuje kontextový soubor zachycující učiněná rozhodnutí.
### Možnost C: Generování pro existující projekty
Pro existující projekty spusťte:
```bash
bmad-generate-project-context
```
Workflow analyzuje vaši kódovou bázi, identifikuje konvence a vygeneruje kontextový soubor, který můžete zkontrolovat a upřesnit.
## Krok 3: Ověřte obsah
Zkontrolujte vygenerovaný soubor a ujistěte se, že zachycuje:
- Správné verze technologií
- Vaše skutečné konvence (ne generické osvědčené postupy)
- Pravidla, která předcházejí běžným chybám
- Vzory specifické pro framework
Ručně upravte pro doplnění chybějícího nebo odstranění nepřesností.
## Co získáte
Soubor `project-context.md`, který:
- Zajistí, že všichni agenti dodržují stejné konvence
- Zabrání nekonzistentním rozhodnutím napříč stories
- Zachytí architektonická rozhodnutí pro implementaci
- Slouží jako reference pro vzory a pravidla vašeho projektu
## Tipy
:::tip[Osvědčené postupy]
- **Zaměřte se na neočividné** — Dokumentujte vzory, které agenti mohou přehlédnout (např. „Použijte JSDoc na každé veřejné třídě“), ne univerzální postupy jako „používejte smysluplné názvy proměnných.“
- **Udržujte to stručné** — Tento soubor načítá každý implementační workflow. Dlouhé soubory plýtvají kontextem. Vylučte obsah, který platí pouze pro úzký rozsah nebo specifické stories.
- **Aktualizujte dle potřeby** — Upravte ručně, když se vzory změní, nebo přegenerujte po významných změnách architektury.
- Funguje pro projekty Quick Flow i plné metody BMad.
:::
## Další kroky
- [**Vysvětlení kontextu projektu**](../explanation/project-context.md) — Zjistěte více o tom, jak to funguje
- [**Mapa pracovních postupů**](../reference/workflow-map.md) — Podívejte se, které workflow načítají kontext projektu

View File

@ -0,0 +1,95 @@
---
title: "Rychlé opravy"
description: Jak provádět rychlé opravy a ad-hoc změny
sidebar:
order: 5
---
Použijte **Quick Dev** pro opravy chyb, refaktoringy nebo malé cílené změny, které nevyžadují plnou metodu BMad.
## Kdy to použít
- Opravy chyb s jasnou, známou příčinou
- Malé refaktoringy (přejmenování, extrakce, restrukturalizace) omezené na několik souborů
- Drobné úpravy funkcí nebo změny konfigurace
- Aktualizace závislostí
:::note[Předpoklady]
- BMad Method nainstalován (`npx bmad-method install`)
- AI-powered IDE (Claude Code, Cursor nebo podobné)
:::
## Kroky
### 1. Začněte nový chat
Otevřete **novou chatovací relaci** ve vašem AI IDE. Opětovné použití relace z předchozího workflow může způsobit konflikty kontextu.
### 2. Zadejte svůj záměr
Quick Dev přijímá volně formulovaný záměr — před, s nebo po vyvolání. Příklady:
```text
run quick-dev — Fix the login validation bug that allows empty passwords.
```
```text
run quick-dev — fix https://github.com/org/repo/issues/42
```
```text
run quick-dev — implement the intent in _bmad-output/implementation-artifacts/my-intent.md
```
```text
I think the problem is in the auth middleware, it's not checking token expiry.
Let me look at it... yeah, src/auth/middleware.ts line 47 skips
the exp check entirely. run quick-dev
```
```text
run quick-dev
> What would you like to do?
Refactor UserService to use async/await instead of callbacks.
```
Prostý text, cesty k souborům, GitHub issue URL, odkazy na bug tracker — cokoli, co LLM dokáže převést na konkrétní záměr.
### 3. Odpovězte na otázky a schvalte
Quick Dev se může zeptat na upřesňující otázky nebo prezentovat krátkou specifikaci ke schválení před implementací. Odpovězte na otázky a schvalte, až budete s plánem spokojeni.
### 4. Zkontrolujte a pushněte
Quick Dev implementuje změnu, zreviduje svou práci, opraví problémy a commitne lokálně. Když je hotov, otevře dotčené soubory ve vašem editoru.
- Projděte diff a potvrďte, že změna odpovídá vašemu záměru
- Pokud něco nevypadá dobře, řekněte agentovi, co opravit — může iterovat ve stejné relaci
Až budete spokojeni, pushněte commit. Quick Dev nabídne push a vytvoření PR za vás.
:::caution[Pokud se něco rozbije]
Pokud pushnutá změna způsobí neočekávané problémy, použijte `git revert HEAD` pro čisté vrácení posledního commitu. Poté začněte nový chat a spusťte Quick Dev znovu s jiným přístupem.
:::
## Co získáte
- Upravené zdrojové soubory s aplikovanou opravou nebo refaktoringem
- Procházející testy (pokud má váš projekt testovací sadu)
- Commit připravený k pushnutí s konvenční commit zprávou
## Odložená práce
Quick Dev udržuje každý běh zaměřený na jeden cíl. Pokud váš požadavek obsahuje více nezávislých cílů, nebo pokud revize odhalí předchozí problémy nesouvisející s vaší změnou, Quick Dev je odloží do souboru (`deferred-work.md` ve vašem adresáři implementačních artefaktů) místo toho, aby se pokusil vše řešit najednou.
Zkontrolujte tento soubor po běhu — je to váš backlog věcí, ke kterým se vrátit. Každou odloženou položku lze zadat do nového běhu Quick Dev později.
## Kdy přejít na formální plánování
Zvažte použití plné metody BMad, když:
- Změna ovlivňuje více systémů nebo vyžaduje koordinované aktualizace napříč mnoha soubory
- Nejste si jisti rozsahem a potřebujete nejprve zjišťování požadavků
- Potřebujete dokumentaci nebo architektonická rozhodnutí zaznamenaná pro tým
Podívejte se na [Quick Dev](../explanation/quick-dev.md) pro více informací o tom, jak Quick Dev zapadá do metody BMad.

View File

@ -0,0 +1,78 @@
---
title: "Průvodce dělením dokumentů"
description: Rozdělení velkých markdown souborů na menší organizované soubory pro lepší správu kontextu
sidebar:
order: 9
---
Použijte nástroj `bmad-shard-doc`, pokud potřebujete rozdělit velké markdown soubory na menší, organizované soubory pro lepší správu kontextu.
:::caution[Zastaralé]
Toto se již nedoporučuje a brzy s aktualizovanými workflow a většinou hlavních LLM a nástrojů podporujících subprocesy to bude zbytečné.
:::
## Kdy to použít
Použijte pouze pokud si všimnete, že váš zvolený nástroj / model nedokáže načíst a přečíst všechny dokumenty jako vstup, když je to potřeba.
## Co je dělení dokumentů?
Dělení dokumentů rozděluje velké markdown soubory na menší, organizované soubory na základě nadpisů úrovně 2 (`## Nadpis`).
### Architektura
```text
Před dělením:
_bmad-output/planning-artifacts/
└── PRD.md (velký soubor o 50k tokenech)
Po dělení:
_bmad-output/planning-artifacts/
└── prd/
├── index.md # Obsah s popisy
├── overview.md # Sekce 1
├── user-requirements.md # Sekce 2
├── technical-requirements.md # Sekce 3
└── ... # Další sekce
```
## Kroky
### 1. Spusťte nástroj Shard-Doc
```bash
/bmad-shard-doc
```
### 2. Následujte interaktivní proces
```text
Agent: Which document would you like to shard?
User: docs/PRD.md
Agent: Default destination: docs/prd/
Accept default? [y/n]
User: y
Agent: Sharding PRD.md...
✓ Created 12 section files
✓ Generated index.md
✓ Complete!
```
## Jak funguje vyhledávání workflow
BMad workflow používají **duální systém vyhledávání**:
1. **Nejprve zkusí celý dokument** — Hledá `document-name.md`
2. **Zkontroluje rozdělenou verzi** — Hledá `document-name/index.md`
3. **Pravidlo priority** — Celý dokument má přednost, pokud existují oba — odstraňte celý dokument, pokud chcete použít rozdělenou verzi
## Podpora workflow
Všechny BMM workflow podporují oba formáty:
- Celé dokumenty
- Rozdělené dokumenty
- Automatická detekce
- Transparentní pro uživatele

View File

@ -0,0 +1,100 @@
---
title: "Jak upgradovat na v6"
description: Migrace z BMad v4 na v6
sidebar:
order: 3
---
Použijte instalátor BMad pro upgrade z v4 na v6, který zahrnuje automatickou detekci starších instalací a asistenci při migraci.
## Kdy to použít
- Máte nainstalovaný BMad v4 (složka `.bmad-method`)
- Chcete migrovat na novou architekturu v6
- Máte existující plánovací artefakty k zachování
:::note[Předpoklady]
- Node.js 20+
- Existující instalace BMad v4
:::
## Kroky
### 1. Spusťte instalátor
Postupujte podle [instrukcí instalátoru](./install-bmad.md).
### 2. Zpracování starší instalace
Když je detekována v4, můžete:
- Nechat instalátor zálohovat a odstranit `.bmad-method`
- Ukončit a zpracovat vyčištění ručně
Pokud jste pojmenovali složku bmad method jinak, musíte ji odstranit ručně.
### 3. Vyčištění IDE skills
Ručně odstraňte starší v4 IDE příkazy/skills — například pokud máte Claude Code, hledejte vnořené složky začínající na bmad a odstraňte je:
- `.claude/commands/`
Nové v6 skills se instalují do:
- `.claude/skills/`
### 4. Migrace plánovacích artefaktů
**Pokud máte plánovací dokumenty (Brief/PRD/UX/Architektura):**
Přesuňte je do `_bmad-output/planning-artifacts/` s popisnými názvy:
- Zahrňte `PRD` v názvu souboru pro PRD dokumenty
- Zahrňte `brief`, `architecture` nebo `ux-design` odpovídajícím způsobem
- Rozdělené dokumenty mohou být v pojmenovaných podsložkách
**Pokud jste uprostřed plánování:** Zvažte restart s v6 workflow. Použijte existující dokumenty jako vstupy — nové workflow s progresivním objevováním, webovým vyhledáváním a plan mode IDE produkují lepší výsledky.
### 5. Migrace probíhajícího vývoje
Pokud máte vytvořené nebo implementované stories:
1. Dokončete instalaci v6
2. Umístěte `epics.md` nebo `epics/epic*.md` do `_bmad-output/planning-artifacts/`
3. Spusťte workflow `bmad-sprint-planning` Scrum Mastera
4. Řekněte SM, které epicy/stories jsou již dokončené
## Co získáte
**Sjednocená struktura v6:**
```text
váš-projekt/
├── _bmad/ # Jedna instalační složka
│ ├── _config/ # Vaše přizpůsobení
│ │ └── agents/ # Soubory přizpůsobení agentů
│ ├── core/ # Univerzální základní framework
│ ├── bmm/ # Modul BMad Method
│ ├── bmb/ # BMad Builder
│ └── cis/ # Creative Intelligence Suite
└── _bmad-output/ # Výstupní složka (v4 to byla složka dokumentů)
```
## Migrace modulů
| Modul v4 | Stav v6 |
| ----------------------------- | ---------------------------------- |
| `.bmad-2d-phaser-game-dev` | Integrován do modulu BMGD |
| `.bmad-2d-unity-game-dev` | Integrován do modulu BMGD |
| `.bmad-godot-game-dev` | Integrován do modulu BMGD |
| `.bmad-infrastructure-devops` | Zastaralý — nový DevOps agent brzy |
| `.bmad-creative-writing` | Neadaptován — nový v6 modul brzy |
## Klíčové změny
| Koncept | v4 | v6 |
| --------------- | ------------------------------------ | -------------------------------------- |
| **Core** | `_bmad-core` byl vlastně BMad Method | `_bmad/core/` je univerzální framework |
| **Method** | `_bmad-method` | `_bmad/bmm/` |
| **Konfigurace** | Přímá editace souborů | `config.yaml` pro každý modul |
| **Dokumenty** | Vyžadované nastavení shardů | Plně flexibilní, auto-skenování |

60
docs/cs/index.md Normal file
View File

@ -0,0 +1,60 @@
---
title: Vítejte v metodě BMad
description: Framework pro vývoj řízený umělou inteligencí se specializovanými agenty, řízenými pracovními postupy a inteligentním plánováním
---
Metoda BMad (**B**uild **M**ore **A**rchitect **D**reams) je framework pro vývoj řízený umělou inteligencí v rámci ekosystému BMad Method, který vám pomáhá vytvářet software celým procesem od nápadu a plánování až po agentní implementaci. Poskytuje specializované AI agenty, řízené pracovní postupy a inteligentní plánování, které se přizpůsobí složitosti vašeho projektu, ať už opravujete chybu nebo budujete podnikovou platformu.
Pokud jste zvyklí pracovat s AI asistenty pro kódování jako Claude, Cursor nebo GitHub Copilot, jste připraveni začít.
:::note[🚀 V6 je tady a teprve začínáme!]
Architektura Skills, BMad Builder v1, automatizace Dev Loop a mnoho dalšího ve vývoji. **[Podívejte se na Plán rozvoje →](./roadmap)**
:::
## Jste tu nově? Začněte tutoriálem
Nejrychlejší způsob, jak pochopit BMad, je vyzkoušet si ho.
- **[Začínáme s BMad](./tutorials/getting-started.md)** — Instalace a pochopení fungování BMad
- **[Mapa pracovních postupů](./reference/workflow-map.md)** — Vizuální přehled fází BMM, pracovních postupů a správy kontextu
:::tip[Chcete se rovnou ponořit?]
Nainstalujte BMad a použijte skill `bmad-help` — provede vás vším na základě vašeho projektu a nainstalovaných modulů.
:::
## Jak používat tuto dokumentaci
Tato dokumentace je organizována do čtyř sekcí podle toho, co chcete dělat:
| Sekce | Účel |
| -------------------- | ------------------------------------------------------------------------------------------------------------------ |
| **Tutoriály** | Orientované na učení. Průvodci krok za krokem, kteří vás provedou tvorbou něčeho. Začněte zde, pokud jste noví. |
| **Praktické návody** | Orientované na úkoly. Praktičtí průvodci pro řešení konkrétních problémů. „Jak přizpůsobím agenta?“ najdete zde. |
| **Vysvětlení** | Orientované na pochopení. Hluboké ponory do konceptů a architektury. Čtěte, když chcete vědět *proč*. |
| **Reference** | Orientované na informace. Technické specifikace agentů, pracovních postupů a konfigurace. |
## Rozšíření a přizpůsobení
Chcete rozšířit BMad o vlastní agenty, pracovní postupy nebo moduly? **[BMad Builder](https://bmad-builder-docs.bmad-method.org/)** poskytuje framework a nástroje pro vytváření vlastních rozšíření, ať už přidáváte nové schopnosti do BMad nebo budujete zcela nové moduly od základů.
## Co budete potřebovat
BMad funguje s jakýmkoli AI asistentem pro kódování, který podporuje vlastní systémové prompty nebo kontextové soubory projektu. Oblíbené možnosti zahrnují:
- **[Claude Code](https://code.claude.com)** — CLI nástroj od Anthropic (doporučený)
- **[Cursor](https://cursor.sh)** — AI-first editor kódu
- **[Codex CLI](https://github.com/openai/codex)** — Terminálový kódovací agent od OpenAI
Měli byste být obeznámeni se základními koncepty vývoje softwaru jako správa verzí, struktura projektu a agilní pracovní postupy. Žádná předchozí zkušenost se systémy agentů ve stylu BMad není vyžadována — právě od toho je tato dokumentace.
## Připojte se ke komunitě
Získejte pomoc, sdílejte co budujete, nebo přispějte do BMad:
- **[Discord](https://discord.gg/gk8jAdXWmj)** — Chatujte s ostatními uživateli BMad, pokládejte otázky, sdílejte nápady
- **[GitHub](https://github.com/bmad-code-org/BMAD-METHOD)** — Zdrojový kód, issues a příspěvky
- **[YouTube](https://www.youtube.com/@BMadCode)** — Video tutoriály a návody
## Další krok
Jste připraveni se ponořit? **[Začněte s BMad](./tutorials/getting-started.md)** a vytvořte svůj první projekt.

View File

@ -0,0 +1,55 @@
---
title: Agenti
description: Výchozí BMM agenti s jejich skill ID, spouštěči nabídky a primárními workflow
sidebar:
order: 2
---
## Výchozí agenti
Tato stránka uvádí výchozí BMM (Agile suite) agenty, kteří se instalují s BMad Method, společně s jejich skill ID, spouštěči nabídky a primárními workflow. Každý agent se vyvolává jako skill.
## Poznámky
- Každý agent je dostupný jako skill, generovaný instalátorem. Skill ID (např. `bmad-dev`) se používá k vyvolání agenta.
- Spouštěče jsou krátké kódy nabídky (např. `CP`) a fuzzy shody zobrazené v nabídce každého agenta.
- Generování QA testů zajišťuje workflow skill `bmad-qa-generate-e2e-tests`, dostupný přes Developer agenta. Plný Test Architect (TEA) žije ve vlastním modulu.
| Agent | Skill ID | Spouštěče | Primární workflow |
| --------------------------- | -------------------- | -------------------------------------------- | --------------------------------------------------------------------------------------------------- |
| Analyst (Mary) | `bmad-analyst` | `BP`, `MR`, `DR`, `TR`, `CB`, `WB`, `DP` | Brainstorm, průzkum trhu, doménový výzkum, technický výzkum, tvorba briefu, PRFAQ výzva, dokumentace projektu |
| Product Manager (John) | `bmad-pm` | `CP`, `VP`, `EP`, `CE`, `IR`, `CC` | Tvorba/validace/editace PRD, tvorba epiců a stories, připravenost implementace, korekce kurzu |
| Architect (Winston) | `bmad-architect` | `CA`, `IR` | Tvorba architektury, připravenost implementace |
| Developer (Amelia) | `bmad-agent-dev` | `DS`, `QD`, `QA`, `CR`, `SP`, `CS`, `ER` | Dev story, Quick Dev, generování QA testů, revize kódu, plánování sprintu, tvorba story, retrospektiva epicu |
| UX Designer (Sally) | `bmad-ux-designer` | `CU` | Tvorba UX designu |
| Technical Writer (Paige) | `bmad-tech-writer` | `DP`, `WD`, `US`, `MG`, `VD`, `EC` | Dokumentace projektu, psaní dokumentu, aktualizace standardů, generování Mermaid, validace dok., vysvětlení konceptu |
## Typy spouštěčů
Spouštěče nabídky agentů používají dva různé typy vyvolání. Znalost typu spouštěče vám pomůže poskytnout správný vstup.
### Workflow spouštěče (bez argumentů)
Většina spouštěčů načítá strukturovaný soubor workflow. Zadejte kód spouštěče a agent zahájí workflow a vyzve vás k zadání vstupu v každém kroku.
Příklady: `CP` (tvorba PRD), `DS` (Dev story), `CA` (tvorba architektury), `QD` (Quick Dev)
### Konverzační spouštěče (vyžadují argumenty)
Některé spouštěče zahajují volnou konverzaci místo strukturovaného workflow. Tyto očekávají, že popíšete, co potřebujete, společně s kódem spouštěče.
| Agent | Spouštěč | Co poskytnout |
| --- | --- | --- |
| Technical Writer (Paige) | `WD` | Popis dokumentu k napsání |
| Technical Writer (Paige) | `US` | Preference nebo konvence k přidání do standardů |
| Technical Writer (Paige) | `MG` | Popis diagramu a typ (sekvence, vývojový diagram atd.) |
| Technical Writer (Paige) | `VD` | Dokument k validaci a oblasti zaměření |
| Technical Writer (Paige) | `EC` | Název konceptu k vysvětlení |
**Příklad:**
```text
WD Write a deployment guide for our Docker setup
MG Create a sequence diagram showing the auth flow
EC Explain how the module system works
```

View File

@ -0,0 +1,135 @@
---
title: Skills
description: Reference BMad skills — co to je, jak fungují a kde je najít.
sidebar:
order: 3
---
Skills jsou předpřipravené prompty, které načítají agenty, spouštějí workflow nebo provádějí úkoly ve vašem IDE. Instalátor BMad je generuje z vašich nainstalovaných modulů při instalaci. Pokud později přidáte, odeberete nebo změníte moduly, přeinstalujte pro synchronizaci skills (viz [Řešení problémů](#řešení-problémů)).
## Skills vs. spouštěče nabídky agentů
BMad nabízí dva způsoby zahájení práce a slouží k různým účelům.
| Mechanismus | Jak se vyvolává | Co se stane |
| --- | --- | --- |
| **Skill** | Zadejte název skillu (např. `bmad-help`) ve vašem IDE | Přímo načte agenta, spustí workflow nebo provede úkol |
| **Spouštěč nabídky agenta** | Nejprve načtěte agenta, pak zadejte krátký kód (např. `DS`) | Agent interpretuje kód a spustí odpovídající workflow, přičemž zůstává v charakteru |
Spouštěče nabídky agentů vyžadují aktivní relaci agenta. Používejte skills, když víte, který workflow chcete. Používejte spouštěče, když již pracujete s agentem a chcete přepnout úkol bez opuštění konverzace.
## Jak se skills generují
Když spustíte `npx bmad-method install`, instalátor čte manifesty každého vybraného modulu a zapíše jeden skill na agenta, workflow, úkol a nástroj. Každý skill je adresář obsahující soubor `SKILL.md`, který instruuje AI k načtení odpovídajícího zdrojového souboru a následování jeho instrukcí.
Instalátor používá šablony pro každý typ skillu:
| Typ skillu | Co generovaný soubor dělá |
| --- | --- |
| **Spouštěč agenta** | Načte soubor persony agenta, aktivuje jeho nabídku a zůstává v charakteru |
| **Workflow skill** | Načte konfiguraci workflow a následuje jeho kroky |
| **Task skill** | Načte samostatný soubor úkolu a následuje jeho instrukce |
| **Tool skill** | Načte samostatný soubor nástroje a následuje jeho instrukce |
:::note[Opětovné spuštění instalátoru]
Pokud přidáte nebo odeberete moduly, spusťte instalátor znovu. Přegeneruje všechny soubory skills tak, aby odpovídaly vašemu aktuálnímu výběru modulů.
:::
## Kde žijí soubory skills
Instalátor zapisuje soubory skills do adresáře specifického pro IDE uvnitř vašeho projektu. Přesná cesta závisí na IDE, které jste vybrali během instalace.
| IDE / CLI | Adresář skills |
| --- | --- |
| Claude Code | `.claude/skills/` |
| Cursor | `.cursor/skills/` |
| Windsurf | `.windsurf/skills/` |
| Další IDE | Viz výstup instalátoru pro cílovou cestu |
Každý skill je adresář obsahující soubor `SKILL.md`. Například instalace Claude Code vypadá takto:
```text
.claude/skills/
├── bmad-help/
│ └── SKILL.md
├── bmad-create-prd/
│ └── SKILL.md
├── bmad-agent-dev/
│ └── SKILL.md
└── ...
```
Název adresáře určuje název skillu ve vašem IDE. Například adresář `bmad-agent-dev/` registruje skill `bmad-agent-dev`.
## Jak objevit vaše skills
Zadejte název skillu ve vašem IDE pro jeho vyvolání. Některé platformy vyžadují povolení skills v nastavení, než se zobrazí.
Spusťte `bmad-help` pro kontextové poradenství k dalšímu kroku.
:::tip[Rychlé objevování]
Generované adresáře skills ve vašem projektu jsou kanonický seznam. Otevřete je v prohlížeči souborů, abyste viděli každý skill s jeho popisem.
:::
## Kategorie skills
### Agentní skills
Agentní skills načítají specializovanou AI personu s definovanou rolí, komunikačním stylem a nabídkou workflow. Po načtení agent zůstává v charakteru a reaguje na spouštěče nabídky.
| Příklad skillu | Agent | Role |
| --- | --- | --- |
| `bmad-agent-dev` | Amelia (Developer) | Implementuje stories s přísným dodržováním specifikací |
| `bmad-pm` | John (Product Manager) | Vytváří a validuje PRD |
| `bmad-architect` | Winston (Architect) | Navrhuje systémovou architekturu |
Viz [Agenti](./agents.md) pro úplný seznam výchozích agentů a jejich spouštěčů.
### Workflow skills
Workflow skills spouštějí strukturovaný, vícekrokový proces bez předchozího načtení persony agenta. Načtou konfiguraci workflow a následují jeho kroky.
| Příklad skillu | Účel |
| --- | --- |
| `bmad-product-brief` | Vytvoření product briefu — řízené discovery, když je váš koncept jasný |
| `bmad-prfaq` | [Working Backwards PRFAQ](../explanation/analysis-phase.md#prfaq-working-backwards) výzva pro zátěžový test vašeho produktového konceptu |
| `bmad-create-prd` | Vytvoření dokumentu požadavků (PRD) |
| `bmad-create-architecture` | Návrh systémové architektury |
| `bmad-create-epics-and-stories` | Vytvoření epiců a stories |
| `bmad-dev-story` | Implementace story |
| `bmad-code-review` | Spuštění revize kódu |
| `bmad-quick-dev` | Sjednocený quick flow — vyjasnění záměru, plán, implementace, revize, prezentace |
Viz [Mapa pracovních postupů](./workflow-map.md) pro kompletní referenci workflow organizovanou podle fází.
### Task a tool skills
Tasks a tools jsou samostatné operace, které nevyžadují kontext agenta nebo workflow.
**BMad-Help: Váš inteligentní průvodce**
`bmad-help` je vaše primární rozhraní pro objevení, co dělat dál. Zkoumá váš projekt, rozumí dotazům v přirozeném jazyce a doporučuje další povinný nebo volitelný krok na základě nainstalovaných modulů.
:::note[Příklad]
```
bmad-help
bmad-help I have a SaaS idea and know all the features. Where do I start?
bmad-help What are my options for UX design?
```
:::
**Další základní tasks a tools**
Základní modul zahrnuje 11 vestavěných nástrojů — revize, komprese, brainstorming, správa dokumentů a další. Viz [Základní nástroje](./core-tools.md) pro kompletní referenci.
## Konvence pojmenování
Všechny skills používají prefix `bmad-` následovaný popisným názvem (např. `bmad-dev`, `bmad-create-prd`, `bmad-help`). Viz [Moduly](./modules.md) pro dostupné moduly.
## Řešení problémů
**Skills se nezobrazují po instalaci.** Některé platformy vyžadují explicitní povolení skills v nastavení. Zkontrolujte dokumentaci vašeho IDE nebo se zeptejte AI asistenta, jak skills povolit. Může být také nutné restartovat IDE nebo znovu načíst okno.
**Očekávané skills chybí.** Instalátor generuje skills pouze pro moduly, které jste vybrali. Spusťte `npx bmad-method install` znovu a ověřte výběr modulů. Zkontrolujte, že soubory skills existují v očekávaném adresáři.
**Skills z odebraného modulu se stále zobrazují.** Instalátor automaticky nemaže staré soubory skills. Odstraňte zastaralé adresáře z adresáře skills vašeho IDE, nebo smažte celý adresář skills a přeinstalujte pro čistou sadu.

View File

@ -0,0 +1,292 @@
---
title: Základní nástroje
description: Reference všech vestavěných úkolů a workflow dostupných v každé instalaci BMad bez dalších modulů.
sidebar:
order: 2
---
Každá instalace BMad zahrnuje sadu základních skills, které lze použít v kombinaci s čímkoli — samostatné úkoly a workflow, které fungují napříč všemi projekty, všemi moduly a všemi fázemi. Ty jsou vždy dostupné bez ohledu na to, které volitelné moduly nainstalujete.
:::tip[Rychlá cesta]
Spusťte jakýkoli základní nástroj zadáním jeho názvu skillu (např. `bmad-help`) ve vašem IDE. Nevyžaduje relaci agenta.
:::
## Přehled
| Nástroj | Typ | Účel |
| --- | --- | --- |
| [`bmad-help`](#bmad-help) | Task | Kontextové poradenství, co dělat dál |
| [`bmad-brainstorming`](#bmad-brainstorming) | Workflow | Facilitace interaktivních brainstormingových sezení |
| [`bmad-party-mode`](#bmad-party-mode) | Workflow | Orchestrace skupinových diskuzí více agentů |
| [`bmad-distillator`](#bmad-distillator) | Task | Bezeztrátová LLM-optimalizovaná komprese dokumentů |
| [`bmad-advanced-elicitation`](#bmad-advanced-elicitation) | Task | Iterativní zdokonalování LLM výstupu |
| [`bmad-review-adversarial-general`](#bmad-review-adversarial-general) | Task | Cynická revize hledající chybějící a chybné |
| [`bmad-review-edge-case-hunter`](#bmad-review-edge-case-hunter) | Task | Vyčerpávající analýza větvících cest pro neošetřené hraniční případy |
| [`bmad-editorial-review-prose`](#bmad-editorial-review-prose) | Task | Klinická jazyková korektura pro komunikační srozumitelnost |
| [`bmad-editorial-review-structure`](#bmad-editorial-review-structure) | Task | Strukturální editace — škrty, sloučení a reorganizace |
| [`bmad-shard-doc`](#bmad-shard-doc) | Task | Rozdělení velkých markdown souborů do organizovaných sekcí |
| [`bmad-index-docs`](#bmad-index-docs) | Task | Generování nebo aktualizace indexu dokumentů ve složce |
## bmad-help
**Váš inteligentní průvodce tím, co přijde dál.** — Zkoumá stav vašeho projektu, detekuje, co bylo uděláno, a doporučuje další povinný nebo volitelný krok.
**Použijte když:**
- Dokončili jste workflow a chcete vědět, co dál
- Jste noví v BMad a potřebujete orientaci
- Jste uvízlí a chcete kontextovou radu
- Nainstalovali jste nové moduly a chcete vidět, co je dostupné
**Jak to funguje:**
1. Skenuje projekt pro existující artefakty (PRD, architektura, stories atd.)
2. Detekuje nainstalované moduly a dostupné workflow
3. Doporučuje další kroky v pořadí priority — nejprve povinné, pak volitelné
4. Prezentuje každé doporučení s příkazem skillu a stručným popisem
**Vstup:** Volitelný dotaz v přirozeném jazyce (např. `bmad-help I have a SaaS idea, where do I start?`)
**Výstup:** Prioritizovaný seznam doporučených dalších kroků s příkazy skills
## bmad-brainstorming
**Generování různorodých nápadů prostřednictvím interaktivních kreativních technik.** — Facilitované brainstormingové sezení, které načítá osvědčené ideační metody z knihovny technik a vede vás k 100+ nápadům před organizací.
**Použijte když:**
- Začínáte nový projekt a potřebujete prozkoumat problémový prostor
- Jste uvízlí s generováním nápadů a potřebujete strukturovanou kreativitu
- Chcete použít osvědčené ideační frameworky (SCAMPER, reverzní brainstorming atd.)
**Jak to funguje:**
1. Nastaví brainstormingové sezení s vaším tématem
2. Načte kreativní techniky z knihovny metod
3. Provede vás technikou za technikou, generuje nápady
4. Aplikuje anti-bias protokol — mění kreativní doménu každých 10 nápadů
5. Produkuje append-only dokument sezení se všemi nápady organizovanými podle techniky
**Vstup:** Téma brainstormingu nebo formulace problému, volitelný kontextový soubor
**Výstup:** `brainstorming-session-{date}.md` se všemi generovanými nápady
:::note[Cíl množství]
Kouzlo se děje v nápadech 50100. Workflow povzbuzuje generování 100+ nápadů před organizací.
:::
## bmad-party-mode
**Orchestrace skupinových diskuzí více agentů.** — Načte všechny nainstalované BMad agenty a facilituje přirozenou konverzaci, kde každý agent přispívá svou unikátní odborností a osobností.
**Použijte když:**
- Potřebujete více expertních perspektiv na rozhodnutí
- Chcete, aby agenti zpochybňovali předpoklady ostatních
- Zkoumáte složité téma překračující více domén
**Jak to funguje:**
1. Načte manifest agentů se všemi nainstalovanými osobnostmi
2. Analyzuje vaše téma a vybere 23 nejrelevantnější agenty
3. Agenti se střídají v přispívání, s přirozenou kříženou diskuzí a nesouhlasy
4. Rotuje účast agentů pro zajištění různorodých perspektiv
5. Ukončete pomocí `goodbye`, `end party` nebo `quit`
**Vstup:** Diskuzní téma nebo otázka, s volitelnou specifikací person
**Výstup:** Real-time multi-agentní konverzace s udržovanými osobnostmi agentů
## bmad-distillator
**Bezeztrátová LLM-optimalizovaná komprese zdrojových dokumentů.** — Produkuje husté, tokenově efektivní destiláty, které zachovávají všechny informace pro následné LLM zpracování. Ověřitelné prostřednictvím round-trip rekonstrukce.
**Použijte když:**
- Dokument je příliš velký pro kontextové okno LLM
- Potřebujete tokenově efektivní verze výzkumů, specifikací nebo plánovacích artefaktů
- Chcete ověřit, že během komprese nebyly ztraceny žádné informace
**Jak to funguje:**
1. **Analýza** — Čte zdrojové dokumenty, identifikuje hustotu informací a strukturu
2. **Komprese** — Převádí prózu na hustý odrážkový formát, odstraňuje dekorativní formátování
3. **Ověření** — Kontroluje úplnost pro zajištění zachování všech informací
4. **Validace** (volitelné) — Round-trip rekonstrukční test dokazuje bezeztrátovou kompresi
**Vstup:**
- `source_documents` (povinné) — Cesty k souborům, složkám nebo glob vzory
- `downstream_consumer` (volitelné) — Co to konzumuje (např. „tvorba PRD“)
- `token_budget` (volitelné) — Přibližná cílová velikost
- `--validate` (příznak) — Spuštění round-trip rekonstrukčního testu
**Výstup:** Destilátové markdown soubory s reportem kompresního poměru (např. „3.2:1“)
## bmad-advanced-elicitation
**Iterativní zdokonalování LLM výstupu metodami elicitace.** — Vybírá z knihovny elicitačních technik pro systematické zlepšování obsahu více průchody.
**Použijte když:**
- LLM výstup působí povrchně nebo genericky
- Chcete prozkoumat téma z více analytických úhlů
- Zdokonalujete kritický dokument a chcete hlubší myšlení
**Jak to funguje:**
1. Načte registr metod s 5+ elicitačními technikami
2. Vybere 5 nejlépe odpovídajících metod podle typu a složitosti obsahu
3. Prezentuje interaktivní nabídku — vyberte metodu, zamíchejte nebo zobrazte vše
4. Aplikuje vybranou metodu k vylepšení obsahu
5. Znovu prezentuje možnosti pro iterativní zlepšení, dokud nevyberete „Pokračovat“
**Vstup:** Sekce obsahu k vylepšení
**Výstup:** Vylepšená verze obsahu s aplikovanými zlepšeními
## bmad-review-adversarial-general
**Cynická revize, která předpokládá existenci problémů a hledá je.** — Zaujme perspektivu skeptického, otráveného recenzenta s nulovou tolerancí pro nedbalou práci. Hledá, co chybí, ne jen co je špatně.
**Použijte když:**
- Potřebujete zajištění kvality před finalizací výstupu
- Chcete zátěžově otestovat specifikaci, story nebo dokument
- Chcete najít mezery v pokrytí, které optimistické revize přehlédnou
**Jak to funguje:**
1. Čte obsah s cynickou, kritickou perspektivou
2. Identifikuje problémy v úplnosti, správnosti a kvalitě
3. Specificky hledá, co chybí — ne jen co je přítomné a špatné
4. Musí najít minimálně 10 problémů nebo analyzuje hlouběji
**Vstup:**
- `content` (povinné) — Diff, specifikace, story, dokument nebo jakýkoli artefakt
- `also_consider` (volitelné) — Další oblasti k zvážení
**Výstup:** Markdown seznam 10+ nálezů s popisy
## bmad-review-edge-case-hunter
**Procházení každé větvící cesty a hraničních podmínek, hlášení pouze neošetřených případů.** — Čistě metodologický přístup trasování cest, který mechanicky odvozuje třídy hraničních případů.
**Použijte když:**
- Chcete vyčerpávající pokrytí hraničních případů pro kód nebo logiku
- Potřebujete doplněk k adversariální revizi (jiná metodologie, jiné nálezy)
- Revidujete diff nebo funkci pro hraniční podmínky
**Jak to funguje:**
1. Enumeruje všechny větvící cesty v obsahu
2. Mechanicky odvozuje třídy případů: chybějící else/default, nestřežené vstupy, off-by-one, přetečení aritmetiky, implicitní typová koerce, race conditions, mezery v timeoutech
3. Testuje každou cestu proti existujícím ochranám
4. Hlásí pouze neošetřené cesty — tiše zahazuje ošetřené
**Vstup:**
- `content` (povinné) — Diff, celý soubor nebo funkce
- `also_consider` (volitelné) — Další oblasti k zvážení
**Výstup:** JSON pole nálezů, každý s `location`, `trigger_condition`, `guard_snippet` a `potential_consequence`
:::note[Komplementární revize]
Spusťte obě `bmad-review-adversarial-general` a `bmad-review-edge-case-hunter` společně pro ortogonální pokrytí. Adversariální revize zachytí problémy kvality a úplnosti; hunter hraničních případů zachytí neošetřené cesty.
:::
## bmad-editorial-review-prose
**Klinická jazyková korektura zaměřená na srozumitelnost komunikace.** — Reviduje text pro problémy bránící porozumění. Aplikuje baseline Microsoft Writing Style Guide. Zachovává autorský hlas.
**Použijte když:**
- Napsali jste dokument a chcete vylepšit psaní
- Potřebujete zajistit srozumitelnost pro konkrétní publikum
- Chcete komunikační opravy bez změn stylistických preferencí
**Jak to funguje:**
1. Čte obsah, přeskakuje bloky kódu a frontmatter
2. Identifikuje komunikační problémy (ne stylistické preference)
3. Deduplikuje stejné problémy napříč více lokacemi
4. Produkuje třísloupcovou tabulku oprav
**Vstup:**
- `content` (povinné) — Markdown, prostý text nebo XML
- `style_guide` (volitelné) — Projektově specifický průvodce stylem
- `reader_type` (volitelné) — `humans` (výchozí) pro srozumitelnost/plynulost, nebo `llm` pro přesnost/konzistenci
**Výstup:** Třísloupcová markdown tabulka: Původní text | Revidovaný text | Změny
## bmad-editorial-review-structure
**Strukturální editace — navrhuje škrty, sloučení, přesuny a zhuštění.** — Reviduje organizaci dokumentu a navrhuje substantivní změny pro zlepšení srozumitelnosti a toku před jazykovou korekcí.
**Použijte když:**
- Dokument byl vytvořen z více subprocesů a potřebuje strukturální koherenci
- Chcete zkrátit dokument při zachování porozumění
- Potřebujete identifikovat porušení rozsahu nebo pohřbené kritické informace
**Jak to funguje:**
1. Analyzuje dokument proti 5 strukturním modelům (Tutorial, Reference, Explanation, Prompt, Strategic)
2. Identifikuje redundance, porušení rozsahu a pohřbené informace
3. Produkuje prioritizovaná doporučení: CUT, MERGE, MOVE, CONDENSE, QUESTION, PRESERVE
4. Odhaduje celkovou redukci ve slovech a procentech
**Vstup:**
- `content` (povinné) — Dokument k revizi
- `purpose` (volitelné) — Zamýšlený účel (např. „quickstart tutoriál“)
- `target_audience` (volitelné) — Kdo to čte
- `reader_type` (volitelné) — `humans` nebo `llm`
- `length_target` (volitelné) — Cílová redukce (např. „o 30 % kratší“)
**Výstup:** Shrnutí dokumentu, prioritizovaný seznam doporučení a odhadovaná redukce
## bmad-shard-doc
**Rozdělení velkých markdown souborů do organizovaných souborů sekcí.** — Používá nadpisy úrovně 2 jako body dělení k vytvoření složky samostatných souborů sekcí s indexem.
**Použijte když:**
- Markdown dokument narostl na nezvládnutelnou velikost (500+ řádků)
- Chcete rozložit monolitický dokument na navigovatelné sekce
- Potřebujete samostatné soubory pro paralelní editaci nebo správu LLM kontextu
**Jak to funguje:**
1. Validuje, že zdrojový soubor existuje a je markdown
2. Dělí na nadpisech úrovně 2 (`##`) do číslovaných souborů sekcí
3. Vytváří `index.md` s manifestem sekcí a odkazy
4. Vyzve vás ke smazání, archivaci nebo zachování originálu
**Vstup:** Cesta ke zdrojovému markdown souboru, volitelná cílová složka
**Výstup:** Složka s `index.md` a `01-{sekce}.md`, `02-{sekce}.md` atd.
## bmad-index-docs
**Generování nebo aktualizace indexu všech dokumentů ve složce.** — Skenuje adresář, čte každý soubor pro pochopení jeho účelu a produkuje organizovaný `index.md` s odkazy a popisy.
**Použijte když:**
- Potřebujete lehký index pro rychlé LLM skenování dostupných dokumentů
- Složka dokumentace narostla a potřebuje organizovaný obsah
- Chcete automaticky generovaný přehled, který zůstává aktuální
**Jak to funguje:**
1. Skenuje cílový adresář pro všechny neskryté soubory
2. Čte každý soubor pro pochopení jeho skutečného účelu
3. Seskupuje soubory podle typu, účelu nebo podadresáře
4. Generuje stručné popisy (310 slov každý)
**Vstup:** Cesta k cílové složce
**Výstup:** `index.md` s organizovanými výpisy souborů, relativními odkazy a stručnými popisy

View File

@ -0,0 +1,76 @@
---
title: Oficiální moduly
description: Doplňkové moduly pro tvorbu vlastních agentů, kreativní inteligenci, vývoj her a testování
sidebar:
order: 4
---
BMad se rozšiřuje prostřednictvím oficiálních modulů, které vyberete během instalace. Tyto doplňkové moduly poskytují specializované agenty, workflow a úkoly pro specifické domény nad rámec vestavěného jádra a BMM (Agile suite).
:::tip[Instalace modulů]
Spusťte `npx bmad-method install` a vyberte požadované moduly. Instalátor se postará o stažení, konfiguraci a integraci s IDE automaticky.
:::
## BMad Builder
Vytvářejte vlastní agenty, workflow a doménově specifické moduly s řízenou asistencí. BMad Builder je meta-modul pro rozšiřování samotného frameworku.
- **Kód:** `bmb`
- **npm:** [`bmad-builder`](https://www.npmjs.com/package/bmad-builder)
- **GitHub:** [bmad-code-org/bmad-builder](https://github.com/bmad-code-org/bmad-builder)
**Poskytuje:**
- Agent Builder — tvorba specializovaných AI agentů s vlastní odborností a přístupem k nástrojům
- Workflow Builder — návrh strukturovaných procesů s kroky a rozhodovacími body
- Module Builder — balíčkování agentů a workflow do sdílitelných, publikovatelných modulů
- Interaktivní nastavení s YAML konfigurací a podporou npm publikování
## Creative Intelligence Suite
AI nástroje pro strukturovanou kreativitu, ideaci a inovace v rané fázi vývoje. Suite poskytuje více agentů, kteří facilitují brainstorming, design thinking a řešení problémů pomocí osvědčených frameworků.
- **Kód:** `cis`
- **npm:** [`bmad-creative-intelligence-suite`](https://www.npmjs.com/package/bmad-creative-intelligence-suite)
- **GitHub:** [bmad-code-org/bmad-module-creative-intelligence-suite](https://github.com/bmad-code-org/bmad-module-creative-intelligence-suite)
**Poskytuje:**
- Agenty Innovation Strategist, Design Thinking Coach a Brainstorming Coach
- Problem Solver a Creative Problem Solver pro systematické a laterální myšlení
- Storyteller a Presentation Master pro narativy a prezentace
- Ideační frameworky včetně SCAMPER, reverzního brainstormingu a přeformulování problémů
## Game Dev Studio
Strukturované workflow pro vývoj her adaptované pro Unity, Unreal, Godot a vlastní enginy. Podporuje rychlé prototypování přes Quick Flow a plnoscálovou produkci s epicky řízenými sprinty.
- **Kód:** `gds`
- **npm:** [`bmad-game-dev-studio`](https://www.npmjs.com/package/bmad-game-dev-studio)
- **GitHub:** [bmad-code-org/bmad-module-game-dev-studio](https://github.com/bmad-code-org/bmad-module-game-dev-studio)
**Poskytuje:**
- Workflow pro generování Game Design Document (GDD)
- Režim Quick Dev pro rychlé prototypování
- Podporu narativního designu pro postavy, dialogy a budování světa
- Pokrytí 21+ typů her s architektonickým vedením specifickým pro engine
## Test Architect (TEA)
Podniková testovací strategie, vedení automatizace a rozhodování o release gate prostřednictvím expertního agenta a devíti strukturovaných workflow. TEA jde daleko za vestavěného QA agenta s prioritizací založenou na riziku a trasovatelností požadavků.
- **Kód:** `tea`
- **npm:** [`bmad-method-test-architecture-enterprise`](https://www.npmjs.com/package/bmad-method-test-architecture-enterprise)
- **GitHub:** [bmad-code-org/bmad-method-test-architecture-enterprise](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise)
**Poskytuje:**
- Agenta Murat (Master Test Architect a Quality Advisor)
- Workflow pro testovací design, ATDD, automatizaci, revizi testů a trasovatelnost
- Hodnocení NFR, nastavení CI a scaffolding frameworku
- Prioritizaci P0-P3 s volitelnými integracemi Playwright Utils a MCP
## Komunitní moduly
Komunitní moduly a marketplace modulů přicházejí. Sledujte [organizaci BMad na GitHubu](https://github.com/bmad-code-org) pro aktualizace.

View File

@ -0,0 +1,106 @@
---
title: Možnosti testování
description: Srovnání vestavěného QA agenta (Quinn) s modulem Test Architect (TEA) pro automatizaci testů.
sidebar:
order: 5
---
BMad poskytuje dvě testovací cesty: vestavěného QA agenta pro rychlé generování testů a instalovatelný modul Test Architect pro podnikovou testovací strategii.
## Který byste měli použít?
| Faktor | Quinn (vestavěný QA) | Modul TEA |
| --- | --- | --- |
| **Nejlepší pro** | Malé až střední projekty, rychlé pokrytí | Velké projekty, regulované nebo složité domény |
| **Nastavení** | Nic k instalaci — součástí BMM | Instalace zvlášť přes `npx bmad-method install` |
| **Přístup** | Generujte testy rychle, iterujte později | Nejprve plánujte, pak generujte s trasovatelností |
| **Typy testů** | API a E2E testy | API, E2E, ATDD, NFR a další |
| **Strategie** | Happy path + kritické hraniční případy | Prioritizace založená na riziku (P0P3) |
| **Počet workflow** | 1 (Automate) | 9 (design, ATDD, automate, review, trace a další) |
:::tip[Začněte s Quinnem]
Většina projektů by měla začít s Quinnem. Pokud později budete potřebovat testovací strategii, quality gates nebo trasovatelnost požadavků, nainstalujte TEA vedle něj.
:::
## Vestavěný QA agent (Quinn)
Quinn je vestavěný QA agent v modulu BMM (Agile suite). Rychle generuje funkční testy pomocí existujícího testovacího frameworku vašeho projektu — bez konfigurace nebo další instalace.
**Spouštěč:** `QA` nebo `bmad-qa-generate-e2e-tests`
### Co Quinn dělá
Quinn spouští jeden workflow (Automate), který projde pěti kroky:
1. **Detekce testovacího frameworku** — skenuje `package.json` a existující testovací soubory pro váš framework (Jest, Vitest, Playwright, Cypress nebo jakýkoli standardní runner). Pokud neexistuje, analyzuje stack projektu a navrhne jeden.
2. **Identifikace funkcí** — zeptá se, co testovat, nebo automaticky objeví funkce v kódové bázi.
3. **Generování API testů** — pokrývá stavové kódy, strukturu odpovědí, happy path a 12 chybové případy.
4. **Generování E2E testů** — pokrývá uživatelské workflow se sémantickými lokátory a asercemi viditelných výsledků.
5. **Spuštění a ověření** — provede generované testy a okamžitě opraví selhání.
Quinn produkuje shrnutí testů uložené do složky implementačních artefaktů vašeho projektu.
### Vzory testů
Generované testy sledují filozofii „jednoduché a udržovatelné“:
- **Pouze standardní API frameworku** — žádné externí utility nebo vlastní abstrakce
- **Sémantické lokátory** pro UI testy (role, popisky, text místo CSS selektorů)
- **Nezávislé testy** bez závislostí na pořadí
- **Žádné hardcoded waity nebo sleep**
- **Jasné popisy**, které se čtou jako dokumentace funkcí
:::note[Rozsah]
Quinn generuje pouze testy. Pro revizi kódu a validaci stories použijte workflow Code Review (`CR`).
:::
### Kdy použít Quinna
- Rychlé pokrytí testy pro novou nebo existující funkci
- Automatizace testů přátelská k začátečníkům bez pokročilého nastavení
- Standardní vzory testů, které může číst a udržovat jakýkoli vývojář
- Malé až střední projekty, kde komplexní testovací strategie není potřeba
## Modul Test Architect (TEA)
TEA je samostatný modul, který poskytuje expertního agenta (Murat) a devět strukturovaných workflow pro podnikové testování. Jde za rámec generování testů do testovací strategie, plánování založeného na riziku, quality gates a trasovatelnosti požadavků.
- **Dokumentace:** [Dokumentace modulu TEA](https://bmad-code-org.github.io/bmad-method-test-architecture-enterprise/)
- **Instalace:** `npx bmad-method install` a výběr modulu TEA
- **npm:** [`bmad-method-test-architecture-enterprise`](https://www.npmjs.com/package/bmad-method-test-architecture-enterprise)
### Co TEA poskytuje
| Workflow | Účel |
| --- | --- |
| Test Design | Vytvoření komplexní testovací strategie vázané na požadavky |
| ATDD | Acceptance-test-driven development s kritérii stakeholderů |
| Automate | Generování testů s pokročilými vzory a utilitami |
| Test Review | Validace kvality a pokrytí testů proti strategii |
| Traceability | Mapování testů zpět na požadavky pro audit a compliance |
| NFR Assessment | Hodnocení nefunkčních požadavků (výkon, bezpečnost) |
| CI Setup | Konfigurace provádění testů v CI pipelines |
| Framework Scaffolding | Nastavení testovací infrastruktury a struktury projektu |
| Release Gate | Datově založená rozhodnutí go/no-go pro release |
TEA také podporuje prioritizaci P0P3 založenou na riziku a volitelné integrace s Playwright Utils a MCP nástroji.
### Kdy použít TEA
- Projekty vyžadující trasovatelnost požadavků nebo compliance dokumentaci
- Týmy potřebující prioritizaci testů založenou na riziku napříč mnoha funkcemi
- Podniková prostředí s formálními quality gates před releasem
- Složité domény, kde musí být testovací strategie naplánována před psaním testů
- Projekty, které přerostly jednoduchý workflow Quinna
## Jak testování zapadá do workflow
Quinn workflow Automate se objevuje ve Fázi 4 (Implementace) mapy workflow BMad Method. Je navržen ke spuštění **po dokončení celého epicu** — jakmile jsou všechny stories v epicu implementovány a zrevidovány. Typická sekvence:
1. Pro každou story v epicu: implementace s Dev (`DS`), pak validace pomocí Code Review (`CR`)
2. Po dokončení epicu: generování testů s Quinnem (`QA`) nebo TEA workflow Automate
3. Spuštění retrospektivy (`bmad-retrospective`) pro zachycení získaných zkušeností
Quinn pracuje přímo ze zdrojového kódu bez načítání plánovacích dokumentů (PRD, architektura). TEA workflow mohou integrovat s upstream plánovacími artefakty pro trasovatelnost.
Pro více o tom, kde testování zapadá do celkového procesu, viz [Mapa pracovních postupů](./workflow-map.md).

View File

@ -0,0 +1,89 @@
---
title: "Mapa pracovních postupů"
description: Vizuální reference fází workflow BMad Method a jejich výstupů
sidebar:
order: 1
---
BMad Method (BMM) je modul v ekosystému BMad, zaměřený na dodržování osvědčených postupů context engineeringu a plánování. AI agenti fungují nejlépe s jasným, strukturovaným kontextem. Systém BMM buduje tento kontext progresivně napříč 4 odlišnými fázemi — každá fáze a volitelně více workflow v každé fázi produkují dokumenty, které informují další, takže agenti vždy vědí, co budovat a proč.
Zdůvodnění a koncepty vycházejí z agilních metodik, které byly v průmyslu úspěšně používány jako mentální framework.
Pokud si kdykoli nejste jisti, co dělat, skill `bmad-help` vám pomůže zůstat na cestě nebo vědět, co dělat dál. Vždy se můžete odkázat sem — ale `bmad-help` je plně interaktivní a mnohem rychlejší, pokud již máte nainstalovaný BMad Method. Navíc, pokud používáte různé moduly, které rozšířily BMad Method nebo přidaly další komplementární moduly — `bmad-help` se vyvíjí a zná vše, co je dostupné, aby vám dal nejlepší radu v daném okamžiku.
Důležitá poznámka: Každý workflow níže lze spustit přímo vaším nástrojem přes skill nebo načtením agenta a použitím záznamu z nabídky agenta.
<iframe src="/workflow-map-diagram.html" title="Diagram mapy workflow BMad Method" width="100%" height="100%" style="border-radius: 8px; border: 1px solid #334155; min-height: 900px;"></iframe>
<p style="font-size: 0.8rem; text-align: right; margin-top: -0.5rem; margin-bottom: 1rem;">
<a href="/workflow-map-diagram.html" target="_blank" rel="noopener noreferrer">Otevřít diagram v novém panelu ↗</a>
</p>
## Fáze 1: Analýza (volitelná)
Prozkoumejte problémový prostor a validujte nápady před závazkem k plánování.
| Workflow | Účel | Produkuje |
| ------------------------------- | -------------------------------------------------------------------------- | ------------------------- |
| `bmad-brainstorming` | Brainstorming nápadů na projekt s řízenou facilitací brainstormingového kouče | `brainstorming-report.md` |
| `bmad-domain-research`, `bmad-market-research`, `bmad-technical-research` | Validace tržních, technických nebo doménových předpokladů | Výzkumné nálezy |
| `bmad-product-brief` | Zachycení strategické vize — nejlepší, když je váš koncept jasný | `product-brief.md` |
| `bmad-prfaq` | Working Backwards — zátěžový test a zformování vašeho produktového konceptu | `prfaq-{project}.md` |
## Fáze 2: Plánování
Definujte, co budovat a pro koho.
| Workflow | Účel | Produkuje |
| --------------------------- | ---------------------------------------- | ------------ |
| `bmad-create-prd` | Definice požadavků (FR/NFR) | `PRD.md` |
| `bmad-create-ux-design` | Návrh uživatelského zážitku (když záleží na UX) | `ux-spec.md` |
## Fáze 3: Solutioning
Rozhodněte, jak to budovat, a rozložte práci na stories.
| Workflow | Účel | Produkuje |
| ----------------------------------------- | ------------------------------------------ | --------------------------- |
| `bmad-create-architecture` | Explicitní technická rozhodnutí | `architecture.md` s ADR |
| `bmad-create-epics-and-stories` | Rozložení požadavků na implementovatelnou práci | Soubory epiců se stories |
| `bmad-check-implementation-readiness` | Kontrola brány před implementací | Rozhodnutí PASS/CONCERNS/FAIL |
## Fáze 4: Implementace
Budujte to, jednu story po druhé. Brzy plná automatizace fáze 4!
| Workflow | Účel | Produkuje |
| -------------------------- | ------------------------------------------------------------------------ | -------------------------------- |
| `bmad-sprint-planning` | Inicializace sledování (jednou na projekt pro sekvencování dev cyklu) | `sprint-status.yaml` |
| `bmad-create-story` | Příprava další story pro implementaci | `story-[slug].md` |
| `bmad-dev-story` | Implementace story | Fungující kód + testy |
| `bmad-code-review` | Validace kvality implementace | Schváleno nebo požadovány změny |
| `bmad-correct-course` | Řešení významných změn uprostřed sprintu | Aktualizovaný plán nebo přesměrování |
| `bmad-sprint-status` | Sledování průběhu sprintu a stavu stories | Aktualizace stavu sprintu |
| `bmad-retrospective` | Revize po dokončení epicu | Poučení |
## Quick Flow (paralelní cesta)
Přeskočte fáze 13 pro malou, dobře pochopenou práci.
| Workflow | Účel | Produkuje |
| ------------------ | --------------------------------------------------------------------------- | -------------------- |
| `bmad-quick-dev` | Sjednocený quick flow — vyjasněte záměr, plánujte, implementujte, revidujte a prezentujte | `spec-*.md` + kód |
## Správa kontextu
Každý dokument se stává kontextem pro další fázi. PRD říká architektovi, jaká omezení záleží. Architektura říká dev agentovi, jaké vzory následovat. Soubory stories poskytují zaměřený, kompletní kontext pro implementaci. Bez této struktury agenti dělají nekonzistentní rozhodnutí.
### Kontext projektu
:::tip[Doporučeno]
Vytvořte `project-context.md` pro zajištění toho, aby AI agenti dodržovali pravidla a preference vašeho projektu. Tento soubor funguje jako ústava vašeho projektu — vede implementační rozhodnutí napříč všemi workflow. Tento volitelný soubor lze vygenerovat na konci tvorby architektury, nebo u existujícího projektu ho lze také vygenerovat pro zachycení toho, co je důležité pro zachování souladu se současnými konvencemi.
:::
**Jak ho vytvořit:**
- **Ručně** — Vytvořte `_bmad-output/project-context.md` s vaším technologickým stackem a pravidly implementace
- **Vygenerujte ho** — Spusťte `bmad-generate-project-context` pro automatické generování z vaší architektury nebo kódové báze
[**Zjistit více o project-context.md**](../explanation/project-context.md)

136
docs/cs/roadmap.mdx Normal file
View File

@ -0,0 +1,136 @@
---
title: Plán rozvoje
description: Co chystáme pro BMad funkce, vylepšení a komunitní příspěvky
---
# Metoda BMad: Veřejný plán rozvoje
Metoda BMad, modul BMad Method (BMM) a BMad Builder (BMB) se neustále vyvíjejí. Zde je přehled toho, na čem pracujeme a co přijde dál.
<div class="roadmap-container">
<h2 class="roadmap-section-title">Probíhá</h2>
<div class="roadmap-future">
<div class="roadmap-future-card">
<span class="roadmap-emoji">🧩</span>
<h4>Univerzální architektura Skills</h4>
<p>Jeden skill, jakákoli platforma. Napište jednou, spusťte kdekoli.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🏗️</span>
<h4>BMad Builder v1</h4>
<p>Vytvářejte produkční AI agenty a pracovní postupy s vestavěnými eval testy, týmy a elegantní degradací.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🧠</span>
<h4>Systém kontextu projektu</h4>
<p>Vaše AI skutečně rozumí vašemu projektu. Kontextový systém reagující na framework, který se vyvíjí s vaším kódem.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">📦</span>
<h4>Centralizované Skills</h4>
<p>Nainstalujte jednou, používejte všude. Sdílejte skills mezi projekty bez zbytečných souborů.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🔄</span>
<h4>Adaptivní Skills</h4>
<p>Skills, které znají váš nástroj. Optimalizované varianty pro Claude, Codex, Kimi, OpenCode a mnoho dalších.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">📝</span>
<h4>Blog BMad Team Pros</h4>
<p>Návody, články a postřehy od týmu. Brzy spouštíme.</p>
</div>
</div>
<h2 class="roadmap-section-title">Na startu</h2>
<div class="roadmap-future">
<div class="roadmap-future-card">
<span class="roadmap-emoji">🏪</span>
<h4>Skill Marketplace</h4>
<p>Objevujte, instalujte a aktualizujte komunitní skills. Jeden curl příkaz od superschopností.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🎨</span>
<h4>Přizpůsobení pracovních postupů</h4>
<p>Přizpůsobte si to. Integrujte Jira, Linear, vlastní výstupy — váš workflow, vaše pravidla.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🚀</span>
<h4>Optimalizace fází 13</h4>
<p>Bleskurychlé plánování s kontextovým sběrem sub-agentů. Režim YOLO kombinovaný s řízenou kvalitou.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🌐</span>
<h4>Připraveno pro podniky</h4>
<p>SSO, auditní logy, týmové pracovní prostory. Všechny ty nudné věci, díky kterým firmy řeknou ano.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">💎</span>
<h4>Exploze komunitních modulů</h4>
<p>Zábava, bezpečnost, terapie, roleplay a mnohem víc. Rozšiřte platformu BMad Method.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">⚡</span>
<h4>Automatizace Dev Loop</h4>
<p>Volitelný autopilot pro vývoj. Nechte AI řídit tok práce a přitom udržujte vysokou kvalitu.</p>
</div>
</div>
<h2 class="roadmap-section-title">Komunita a tým</h2>
<div class="roadmap-future">
<div class="roadmap-future-card">
<span class="roadmap-emoji">🎙️</span>
<h4>Podcast metody BMad</h4>
<p>Rozhovory o AI-nativním vývoji. Spouštíme 1. března 2026!</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🎓</span>
<h4>Master Class metody BMad</h4>
<p>Od uživatele k expertovi. Hluboké ponory do každé fáze, každého workflow, každého tajemství.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🏗️</span>
<h4>Master Class BMad Builder</h4>
<p>Vytvářejte vlastní agenty. Pokročilé techniky pro chvíle, kdy jste připraveni tvořit, ne jen používat.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">⚡</span>
<h4>BMad Prototype First</h4>
<p>Od nápadu k fungujícímu prototypu v jedné relaci. Vytvořte svou vysněnou aplikaci jako umělecké dílo.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🌴</span>
<h4>BMad BALM!</h4>
<p>Správa života pro AI-nativní uživatele. Úkoly, návyky, cíle — váš AI kopilot pro všechno.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🖥️</span>
<h4>Oficiální UI</h4>
<p>Krásné rozhraní pro celý ekosystém BMad. Síla CLI, lesk GUI.</p>
</div>
<div class="roadmap-future-card">
<span class="roadmap-emoji">🔒</span>
<h4>BMad in a Box</h4>
<p>Self-hosted, bez připojení, podnikové kvality. Váš AI asistent, vaše infrastruktura, vaše kontrola.</p>
</div>
</div>
<div style="text-align: center; margin-top: 3rem; padding: 2rem; background: var(--color-bg-card); border-radius: 12px; border: 1px solid var(--color-border);">
<h3 style="margin: 0 0 1rem;">Chcete přispět?</h3>
<p style="color: var(--slate-color-400); margin: 0;">
Toto je pouze částečný seznam toho, co je plánováno. Open source tým BMad vítá přispěvatele!{" "}<br />
<a href="https://github.com/bmad-code-org/BMAD-METHOD" style="color: var(--color-in-progress);">Přidejte se k nám na GitHubu</a> a pomozte formovat budoucnost vývoje řízeného AI.
</p>
<p style="color: var(--slate-color-400); margin: 1.5rem 0 0;">
Líbí se vám, co budujeme? Oceníme jak jednorázovou, tak měsíční{" "}<a href="https://buymeacoffee.com/bmad" style="color: var(--color-in-progress);">podporu</a>.
</p>
<p style="color: var(--slate-color-400); margin: 1rem 0 0;">
Pro firemní sponzoring, partnerské dotazy, přednášky, školení nebo mediální dotazy:{" "}
<a href="mailto:contact@bmadcode.com" style="color: var(--color-in-progress);">contact@bmadcode.com</a>
</p>
</div>
</div>

View File

@ -0,0 +1,276 @@
---
title: "Začínáme"
description: Nainstalujte BMad a vytvořte svůj první projekt
---
Vytvářejte software rychleji pomocí pracovních postupů řízených AI se specializovanými agenty, kteří vás provedou plánováním, architekturou a implementací.
## Co se naučíte
- Nainstalovat a inicializovat BMad Method pro nový projekt
- Používat **BMad-Help** — vašeho inteligentního průvodce, který ví, co dělat dál
- Vybrat správnou plánovací cestu pro velikost vašeho projektu
- Postupovat fázemi od požadavků k fungujícímu kódu
- Efektivně používat agenty a pracovní postupy
:::note[Předpoklady]
- **Node.js 20+** — Vyžadováno pro instalátor
- **Git** — Doporučeno pro správu verzí
- **AI-powered IDE** — Claude Code, Cursor nebo podobné
- **Nápad na projekt** — I jednoduchý stačí pro učení
:::
:::tip[Nejsnadnější cesta]
**Instalace** → `npx bmad-method install`
**Zeptejte se** → `bmad-help what should I do first?`
**Tvořte** → Nechte BMad-Help vás provést workflow po workflow
:::
## Seznamte se s BMad-Help: Váš inteligentní průvodce
**BMad-Help je nejrychlejší způsob, jak začít s BMad.** Nemusíte si pamatovat workflow nebo fáze — prostě se zeptejte a BMad-Help:
- **Prozkoumá váš projekt** a zjistí, co už bylo uděláno
- **Ukáže vaše možnosti** na základě nainstalovaných modulů
- **Doporučí, co dál** — včetně prvního povinného úkolu
- **Odpoví na otázky** jako „Mám nápad na SaaS, kde začít?“
### Jak používat BMad-Help
Spusťte ho ve vašem AI IDE vyvoláním skillu:
```
bmad-help
```
Nebo ho spojte s otázkou pro kontextové poradenství:
```
bmad-help I have an idea for a SaaS product, I already know all the features I want. where do I get started?
```
BMad-Help odpoví s:
- Co je doporučeno pro vaši situaci
- Jaký je první povinný úkol
- Jak vypadá zbytek procesu
### Řídí i pracovní postupy
BMad-Help nejen odpovídá na otázky — **automaticky se spouští na konci každého workflow** a řekne vám přesně, co dělat dál. Žádné hádání, žádné prohledávání dokumentace — jen jasné pokyny k dalšímu povinnému workflow.
:::tip[Začněte zde]
Po instalaci BMad okamžitě vyvolejte skill `bmad-help`. Detekuje, jaké moduly máte nainstalované, a navede vás ke správnému výchozímu bodu pro váš projekt.
:::
## Pochopení BMad
BMad vám pomáhá vytvářet software prostřednictvím řízených pracovních postupů se specializovanými AI agenty. Proces probíhá ve čtyřech fázích:
| Fáze | Název | Co se děje |
| ---- | -------------- | ------------------------------------------------------- |
| 1 | Analýza | Brainstorming, průzkum, product brief nebo PRFAQ *(volitelné)* |
| 2 | Plánování | Vytvoření požadavků (PRD nebo specifikace) |
| 3 | Solutioning | Návrh architektury *(pouze BMad Method/Enterprise)* |
| 4 | Implementace | Budování epic po epicu, story po story |
**[Otevřete Mapu pracovních postupů](../reference/workflow-map.md)** pro prozkoumání fází, workflow a správy kontextu.
Na základě složitosti vašeho projektu nabízí BMad tři plánovací cesty:
| Cesta | Nejlepší pro | Vytvořené dokumenty |
| --------------- | -------------------------------------------------------------- | -------------------------------------- |
| **Quick Flow** | Opravy chyb, jednoduché funkce, jasný rozsah (115 stories) | Pouze tech-spec |
| **BMad Method** | Produkty, platformy, složité funkce (1050+ stories) | PRD + architektura + UX |
| **Enterprise** | Compliance, multi-tenant systémy (30+ stories) | PRD + architektura + bezpečnost + DevOps |
:::note
Počty stories jsou orientační, ne definitivní. Vyberte si cestu podle potřeb plánování, ne podle počtu stories.
:::
## Instalace
Otevřete terminál v adresáři vašeho projektu a spusťte:
```bash
npx bmad-method install
```
Pokud chcete nejnovější prereleaseový build místo výchozího release kanálu, použijte `npx bmad-method@next install`.
Při výzvě k výběru modulů zvolte **BMad Method**.
Instalátor vytvoří dvě složky:
- `_bmad/` — agenti, workflow, úkoly a konfigurace
- `_bmad-output/` — prozatím prázdná, ale zde se budou ukládat vaše artefakty
:::tip[Váš další krok]
Otevřete vaše AI IDE ve složce projektu a spusťte:
```
bmad-help
```
BMad-Help detekuje, co jste dokončili, a doporučí přesně, co dělat dál. Můžete mu také klást otázky jako „Jaké mám možnosti?“ nebo „Mám nápad na SaaS, kde začít?“
:::
:::note[Jak načítat agenty a spouštět workflow]
Každý workflow má **skill**, který vyvoláte jménem ve vašem IDE (např. `bmad-create-prd`). Váš AI nástroj rozpozná název `bmad-*` a spustí ho — nemusíte načítat agenty zvlášť. Můžete také vyvolat agentní skill přímo pro obecnou konverzaci (např. `bmad-agent-pm` pro PM agenta).
:::
:::caution[Nové chaty]
Vždy začněte nový chat pro každý workflow. Tím předejdete problémům s kontextovými omezeními.
:::
## Krok 1: Vytvořte svůj plán
Projděte fázemi 13. **Pro každý workflow používejte nové chaty.**
:::tip[Kontext projektu (volitelné)]
Před začátkem zvažte vytvoření `project-context.md` pro dokumentaci vašich technických preferencí a pravidel implementace. Tím zajistíte, že všichni AI agenti budou dodržovat vaše konvence v průběhu celého projektu.
Vytvořte ho ručně na `_bmad-output/project-context.md` nebo ho vygenerujte po architektuře pomocí `bmad-generate-project-context`. [Zjistit více](../explanation/project-context.md).
:::
### Fáze 1: Analýza (volitelná)
Všechny workflow v této fázi jsou volitelné:
- **brainstorming** (`bmad-brainstorming`) — Řízená ideace
- **průzkum** (`bmad-market-research` / `bmad-domain-research` / `bmad-technical-research`) — Tržní, doménový a technický průzkum
- **product-brief** (`bmad-product-brief`) — Doporučený základní dokument, když je váš koncept jasný
- **prfaq** (`bmad-prfaq`) — Working Backwards výzva pro zátěžový test a zformování vašeho produktového konceptu
### Fáze 2: Plánování (povinná)
**Pro BMad Method a Enterprise cesty:**
1. Vyvolejte **PM agenta** (`bmad-agent-pm`) v novém chatu
2. Spusťte workflow `bmad-create-prd` (`bmad-create-prd`)
3. Výstup: `PRD.md`
**Pro Quick Flow cestu:**
- Spusťte `bmad-quick-dev` — zvládne plánování i implementaci v jednom workflow, přeskočte k implementaci
:::note[UX Design (volitelné)]
Pokud má váš projekt uživatelské rozhraní, vyvolejte **UX-Designer agenta** (`bmad-agent-ux-designer`) a spusťte UX design workflow (`bmad-create-ux-design`) po vytvoření PRD.
:::
### Fáze 3: Solutioning (BMad Method/Enterprise)
**Vytvoření architektury**
1. Vyvolejte **Architect agenta** (`bmad-agent-architect`) v novém chatu
2. Spusťte `bmad-create-architecture` (`bmad-create-architecture`)
3. Výstup: Dokument architektury s technickými rozhodnutími
**Vytvoření epiců a stories**
:::tip[Vylepšení ve V6]
Epicy a stories se nyní vytvářejí *po* architektuře. Tím vznikají kvalitnější stories, protože architektonická rozhodnutí (databáze, API vzory, tech stack) přímo ovlivňují rozklad práce.
:::
1. Vyvolejte **PM agenta** (`bmad-agent-pm`) v novém chatu
2. Spusťte `bmad-create-epics-and-stories` (`bmad-create-epics-and-stories`)
3. Workflow využívá jak PRD, tak architekturu k vytvoření technicky informovaných stories
**Kontrola připravenosti k implementaci** *(vysoce doporučeno)*
1. Vyvolejte **Architect agenta** (`bmad-agent-architect`) v novém chatu
2. Spusťte `bmad-check-implementation-readiness` (`bmad-check-implementation-readiness`)
3. Validuje soudržnost všech plánovacích dokumentů
## Krok 2: Sestavte svůj projekt
Jakmile je plánování dokončeno, přejděte k implementaci. **Každý workflow by měl běžet v novém chatu.**
### Inicializace plánování sprintu
Vyvolejte **Developer agenta** (`bmad-agent-dev`) a spusťte `bmad-sprint-planning` (`bmad-sprint-planning`). Tím se vytvoří `sprint-status.yaml` pro sledování všech epiců a stories.
### Cyklus vývoje
Pro každou story opakujte tento cyklus s novými chaty:
| Krok | Agent | Workflow | Příkaz | Účel |
| ---- | ----- | -------------------- | -------------------------- | ---------------------------------- |
| 1 | DEV | `bmad-create-story` | `bmad-create-story` | Vytvoření story souboru z epicu |
| 2 | DEV | `bmad-dev-story` | `bmad-dev-story` | Implementace story |
| 3 | DEV | `bmad-code-review` | `bmad-code-review` | Validace kvality *(doporučeno)* |
Po dokončení všech stories v epicu vyvolejte **Developer agenta** (`bmad-agent-dev`) a spusťte `bmad-retrospective` (`bmad-retrospective`).
## Co jste dosáhli
Naučili jste se základy budování s BMad:
- Nainstalovali BMad a nakonfigurovali ho pro vaše IDE
- Inicializovali projekt s vybranou plánovací cestou
- Vytvořili plánovací dokumenty (PRD, architektura, epicy a stories)
- Pochopili cyklus vývoje pro implementaci
Váš projekt nyní obsahuje:
```text
váš-projekt/
├── _bmad/ # Konfigurace BMad
├── _bmad-output/
│ ├── planning-artifacts/
│ │ ├── PRD.md # Váš dokument požadavků
│ │ ├── architecture.md # Technická rozhodnutí
│ │ └── epics/ # Soubory epiců a stories
│ ├── implementation-artifacts/
│ │ └── sprint-status.yaml # Sledování sprintu
│ └── project-context.md # Pravidla implementace (volitelné)
└── ...
```
## Rychlý přehled
| Workflow | Příkaz | Agent | Účel |
| ------------------------------------- | ------------------------------------------ | --------- | ----------------------------------------------- |
| **`bmad-help`** ⭐ | `bmad-help` | Jakýkoli | **Váš inteligentní průvodce — ptejte se na cokoli!** |
| `bmad-create-prd` | `bmad-create-prd` | PM | Vytvoření dokumentu požadavků (PRD) |
| `bmad-create-architecture` | `bmad-create-architecture` | Architect | Vytvoření dokumentu architektury |
| `bmad-generate-project-context` | `bmad-generate-project-context` | Analyst | Vytvoření souboru kontextu projektu |
| `bmad-create-epics-and-stories` | `bmad-create-epics-and-stories` | PM | Rozklad PRD na epicy |
| `bmad-check-implementation-readiness` | `bmad-check-implementation-readiness` | Architect | Validace soudržnosti plánování |
| `bmad-sprint-planning` | `bmad-sprint-planning` | DEV | Inicializace sledování sprintu |
| `bmad-create-story` | `bmad-create-story` | DEV | Vytvoření souboru story |
| `bmad-dev-story` | `bmad-dev-story` | DEV | Implementace story |
| `bmad-code-review` | `bmad-code-review` | DEV | Revize implementovaného kódu |
## Časté otázky
**Potřebuji vždy architekturu?**
Pouze pro BMad Method a Enterprise cesty. Quick Flow přeskakuje ze specifikace rovnou k implementaci.
**Mohu později změnit svůj plán?**
Ano. Workflow `bmad-correct-course` (`bmad-correct-course`) řeší změny rozsahu během implementace.
**Co když chci nejdřív brainstormovat?**
Vyvolejte Analyst agenta (`bmad-agent-analyst`) a spusťte `bmad-brainstorming` (`bmad-brainstorming`) před zahájením PRD.
**Musím dodržovat striktní pořadí?**
Ne striktně. Jakmile se naučíte postup, můžete spouštět workflow přímo pomocí Rychlého přehledu výše.
## Získání pomoci
:::tip[První zastávka: BMad-Help]
**Vyvolejte `bmad-help` kdykoli** — je to nejrychlejší způsob, jak se odpoutat. Zeptejte se na cokoli:
- „Co mám dělat po instalaci?“
- „Zasekl jsem se na workflow X“
- „Jaké mám možnosti pro Y?“
- „Ukaž mi, co bylo dosud uděláno“
BMad-Help prozkoumá váš projekt, detekuje, co jste dokončili, a řekne vám přesně, co dělat dál.
:::
- **Během workflow** — Agenti vás provázejí otázkami a vysvětleními
- **Komunita** — [Discord](https://discord.gg/gk8jAdXWmj) (#bmad-method-help, #report-bugs-and-issues)
## Klíčové poznatky
:::tip[Zapamatujte si]
- **Začněte s `bmad-help`** — Váš inteligentní průvodce, který zná váš projekt a možnosti
- **Vždy používejte nové chaty** — Začněte nový chat pro každý workflow
- **Cesta záleží** — Quick Flow používá `bmad-quick-dev`; Method/Enterprise vyžadují PRD a architekturu
- **BMad-Help se spouští automaticky** — Každý workflow končí pokyny, co dělat dál
:::
Jste připraveni začít? Nainstalujte BMad, vyvolejte `bmad-help` a nechte svého inteligentního průvodce ukázat cestu.

View File

@ -0,0 +1,70 @@
---
title: "Analysis Phase: From Idea to Foundation"
description: What brainstorming, research, product briefs, and PRFAQs are — and when to use each
sidebar:
order: 1
---
The Analysis phase (Phase 1) helps you think clearly about your product before committing to building it. Every tool in this phase is optional, but skipping analysis entirely means your PRD is built on assumptions instead of insight.
## Why Analysis Before Planning?
A PRD answers "what should we build and why?" If you feed it vague thinking, you get a vague PRD — and every downstream document inherits that vagueness. Architecture built on a weak PRD makes wrong technical bets. Stories derived from weak architecture miss edge cases. The cost compounds.
Analysis tools exist to make your PRD sharp. They attack the problem from different angles — creative exploration, market reality, customer clarity, feasibility — so that by the time you sit down with the PM agent, you know what you're building and for whom.
## The Tools
### Brainstorming
**What it is.** A facilitated creative session using proven ideation techniques. The AI acts as coach, pulling ideas out of you through structured exercises — not generating ideas for you.
**Why it's here.** Raw ideas need space to develop before they get locked into requirements. Brainstorming creates that space. It's especially valuable when you have a problem domain but no clear solution, or when you want to explore multiple directions before committing.
**When to use it.** You have a vague sense of what you want to build but haven't crystallized the concept. Or you have a concept but want to pressure-test it against alternatives.
See [Brainstorming](./brainstorming.md) for a deeper look at how sessions work.
### Research (Market, Domain, Technical)
**What it is.** Three focused research workflows that investigate different dimensions of your idea. Market research examines competitors, trends, and user sentiment. Domain research builds subject-matter expertise and terminology. Technical research evaluates feasibility, architecture options, and implementation approaches.
**Why it's here.** Building on assumptions is the fastest way to build something nobody needs. Research grounds your concept in reality — what competitors already exist, what users actually struggle with, what's technically feasible, and what industry-specific constraints you'll face.
**When to use it.** You're entering an unfamiliar domain, you suspect competitors exist but haven't mapped them, or your concept depends on technical capabilities you haven't validated. Run one, two, or all three — each stands alone.
### Product Brief
**What it is.** A guided discovery session that produces a 1-2 page executive summary of your product concept. The AI acts as a collaborative Business Analyst, helping you articulate the vision, target audience, value proposition, and scope.
**Why it's here.** The product brief is the gentler path into planning. It captures your strategic vision in a structured format that feeds directly into PRD creation. It works best when you already have conviction about your concept — you know the customer, the problem, and roughly what you want to build. The brief organizes and sharpens that thinking.
**When to use it.** Your concept is relatively clear and you want to document it efficiently before creating a PRD. You're confident in the direction and don't need your assumptions aggressively challenged.
### PRFAQ (Working Backwards)
**What it is.** Amazon's Working Backwards methodology adapted as an interactive challenge. You write the press release announcing your finished product before a single line of code exists, then answer the hardest questions customers and stakeholders would ask. The AI acts as a relentless but constructive product coach.
**Why it's here.** The PRFAQ is the rigorous path into planning. It forces customer-first clarity by making you defend every claim. If you can't write a compelling press release, the product isn't ready. If customer FAQ answers reveal gaps, those are gaps you'd discover much later — and more expensively — during implementation. The gauntlet surfaces weak thinking early, when it's cheapest to fix.
**When to use it.** You want your concept stress-tested before committing resources. You're unsure whether users will actually care. You want to validate that you can articulate a clear, defensible value proposition. Or you simply want the discipline of Working Backwards to sharpen your thinking.
## Which Should I Use?
| Situation | Recommended tool |
| --------- | ---------------- |
| "I have a vague idea, not sure where to start" | Brainstorming |
| "I need to understand the market before deciding" | Research |
| "I know what I want to build, just need to document it" | Product Brief |
| "I want to make sure this idea is actually worth building" | PRFAQ |
| "I want to explore, then validate, then document" | Brainstorming → Research → PRFAQ or Brief |
Product Brief and PRFAQ both produce input for the PRD — choose one based on how much challenge you want. The brief is collaborative discovery. The PRFAQ is a gauntlet. Both get you to the same destination; the PRFAQ tests whether your concept deserves to get there.
:::tip[Not Sure?]
Run `bmad-help` and describe your situation. It will recommend the right starting point based on what you've already done and what you're trying to accomplish.
:::
## What Happens After Analysis?
Analysis outputs feed directly into Phase 2 (Planning). The PRD workflow accepts product briefs, PRFAQ documents, research findings, and brainstorming reports as input — it synthesizes whatever you've produced into structured requirements. The more analysis you do, the sharper your PRD.

View File

@ -9,7 +9,7 @@ Unlock your creativity through guided exploration.
## What is Brainstorming? ## What is Brainstorming?
Run `brainstorming` and you've got a creative facilitator pulling ideas out of you - not generating them for you. The AI acts as coach and guide, using proven techniques to create conditions where your best thinking emerges. Run `bmad-brainstorming` and you've got a creative facilitator pulling ideas out of you - not generating them for you. The AI acts as coach and guide, using proven techniques to create conditions where your best thinking emerges.
**Good for:** **Good for:**

View File

@ -0,0 +1,92 @@
---
title: "Checkpoint Preview"
description: LLM-assisted human-in-the-loop review that guides you through a change from purpose to details
sidebar:
order: 3
---
`bmad-checkpoint-preview` is an interactive, LLM-assisted human-in-the-loop review workflow. It walks you through a code change — from purpose and context into details — so you can make an informed decision about whether to ship, rework, or dig deeper.
![Checkpoint Preview workflow diagram](/diagrams/checkpoint-preview-diagram.png)
## The Typical Flow
You run `bmad-quick-dev`. It clarifies your intent, builds a spec, implements the change, and when it's done it appends a review trail to the spec file and opens it in your editor. You look at the spec and see the change touched 20 files across several modules.
You could eyeball the diff. But 20 files is where eyeballing starts to fail — you lose the thread, miss a connection between two distant changes, or approve something you didn't fully understand. So instead, you say "checkpoint" and the LLM walks you through it.
That handoff — from autonomous implementation back to human judgment — is the primary use case. Quick-dev runs long with minimal supervision. Checkpoint Preview is where you take back the wheel.
## Why It Exists
Code review has two failure modes. In one, the reviewer skims the diff, nothing jumps out, and they approve. In the other, they methodically read every file but lose the thread — they see the trees and miss the forest. Both result in the same outcome: the review didn't catch the thing that mattered.
The underlying issue is sequencing. A raw diff presents changes in file order, which is almost never the order that builds understanding. You see a helper function before you know why it exists. You see a schema change before you understand what feature it supports. The reviewer has to reconstruct the author's intent from scattered clues, and that reconstruction is where attention fails.
Checkpoint Preview solves this by making the LLM do the reconstruction work. It reads the diff, the spec (if one exists), and the surrounding codebase, then presents the change in an order designed for comprehension — not for `git diff`.
## How It Works
The workflow has five steps. Each step builds on the previous one, progressively shifting from "what is this?" toward "should we ship it?"
### 1. Orientation
The workflow identifies the change (from a PR, commit, branch, spec file, or the current git state) and produces a one-line intent summary plus surface area stats: files changed, modules touched, lines of logic, boundary crossings, and new public interfaces.
This is the "is this what I think it is?" moment. Before reading any code, the reviewer confirms they're looking at the right thing and calibrates their expectations for scope.
### 2. Walkthrough
The change is organized by **concern** — cohesive design intents like "input validation" or "API contract" — not by file. Each concern gets a short explanation of *why* this approach was chosen, followed by clickable `path:line` stops that the reviewer can follow through the code.
This is the design judgment step. The reviewer evaluates whether the approach is right for the system, not whether the code is correct. Concerns are sequenced top-down: the highest-level intent first, then supporting implementation. The reviewer never encounters a reference to something they haven't seen yet.
### 3. Detail Pass
After the reviewer understands the design, the workflow surfaces 2-5 spots where a mistake would have the highest blast radius. These are tagged by risk category — `[auth]`, `[schema]`, `[billing]`, `[public API]`, `[security]`, and others — and ordered by how much breaks if they're wrong.
This is not a bug hunt. Automated tests and CI handle correctness. The detail pass activates risk awareness: "here are the places where being wrong costs the most." If the reviewer wants to go deeper on a specific area, they can say "dig into [area]" for a targeted correctness-focused re-review.
If the spec went through adversarial review loops (machine hardening), those findings are surfaced here too — not the bugs that were fixed, but the decisions that the review loop flagged that the reviewer should be aware of.
### 4. Testing
Suggests 2-5 ways to manually observe the change working. Not automated test commands — manual observations that build confidence no test suite provides. A UI interaction to try, a CLI command to run, an API request to send, with expected results for each.
If the change has no user-visible behavior, it says so. No invented busywork.
### 5. Wrap-Up
The reviewer makes the call: approve, rework, or keep discussing. If approving a PR, the workflow can help with `gh pr review --approve`. If reworking, it helps diagnose whether the problem was the approach, the spec, or the implementation, and helps draft actionable feedback tied to specific code locations.
## It's a Conversation, Not a Report
The workflow presents each step as a starting point, not a final word. Between steps — or in the middle of one — you can talk to the LLM, ask questions, challenge its framing, or pull in other skills to get a different perspective:
- **"run advanced elicitation on the error handling"** — push the LLM to reconsider and refine its analysis of a specific area
- **"party mode on whether this schema migration is safe"** — bring multiple agent perspectives into a focused debate
- **"run code review"** — generate structured agentic findings with adversarial and edge-case analysis
The checkpoint workflow doesn't lock you into a linear path. It gives you structure when you want it and gets out of the way when you want to explore. The five steps are there to make sure you see the whole picture, but how deep you go at each step — and what tools you bring in — is entirely up to you.
## The Review Trail
The walkthrough step works best when it has a **Suggested Review Order** — a list of stops the spec author wrote to guide reviewers through the change. When a spec includes this, the workflow uses it directly.
When no author-produced trail exists, the workflow generates one from the diff and codebase context. A generated trail is lower quality than an author-produced one, but far better than reading changes in file order.
## When to Use It
The primary scenario is the handoff from `bmad-quick-dev`: the implementation is done, the spec file is open in your editor with a review trail appended, and you need to decide whether to ship. Say "checkpoint" and go.
It also works standalone:
- **Reviewing a PR** — especially one with more than a handful of files or cross-cutting changes
- **Onboarding to a change** — when you need to understand what happened on a branch you didn't write
- **Sprint review** — the workflow can pick up stories marked `review` in your sprint status file
Invoke it by saying "checkpoint" or "walk me through this change." It works in any terminal, but you'll get more out of it inside an IDE — VS Code, Cursor, or similar — because the workflow produces `path:line` references at every step. In an IDE-embedded terminal those are clickable, so you can jump from file to file as you follow the review trail.
## What It Is Not
Checkpoint Preview is not a substitute for automated review. It does not run linters, type checkers, or test suites. It does not assign severity scores or produce pass/fail verdicts. It is a reading guide that helps a human apply their judgment where it matters most.

View File

@ -34,7 +34,7 @@ Yes! Quick Flow works great for established projects. It will:
- Auto-detect your existing stack - Auto-detect your existing stack
- Analyze existing code patterns - Analyze existing code patterns
- Detect conventions and ask for confirmation - Detect conventions and ask for confirmation
- Generate context-rich tech-spec that respects existing code - Generate context-rich spec that respects existing code
Perfect for bug fixes and small features in existing codebases. Perfect for bug fixes and small features in existing codebases.
@ -43,7 +43,7 @@ Perfect for bug fixes and small features in existing codebases.
Quick Flow detects your conventions and asks: "Should I follow these existing conventions?" You decide: Quick Flow detects your conventions and asks: "Should I follow these existing conventions?" You decide:
- **Yes** → Maintain consistency with current codebase - **Yes** → Maintain consistency with current codebase
- **No** → Establish new standards (document why in tech-spec) - **No** → Establish new standards (document why in spec)
BMM respects your choice — it won't force modernization, but it will offer it. BMM respects your choice — it won't force modernization, but it will offer it.

View File

@ -0,0 +1,94 @@
---
title: "Named Agents"
description: Why BMad agents have names, personas, and customization surfaces — and what that unlocks compared to menu-driven or prompt-driven alternatives
sidebar:
order: 1
---
You say "Hey Mary, let's brainstorm," and Mary activates. She greets you by name, in the language you configured, with her distinctive persona. She reminds you that `bmad-help` is always available. Then she skips the menu entirely and drops straight into brainstorming — because your intent was clear.
This page explains what's actually happening and why BMad is designed this way.
## The Three-Legged Stool
BMad's agent model rests on three primitives that compose:
| Primitive | What it provides | Where it lives |
|---|---|---|
| **Skill** | Capability — a discrete thing the assistant can do (brainstorm, draft a PRD, implement a story) | `.claude/skills/{skill-name}/SKILL.md` (or your IDE's equivalent) |
| **Named agent** | Persona continuity — a recognizable identity that wraps a menu of related skills with consistent voice, principles, and visual cues | Skills whose directory starts with `bmad-agent-*` |
| **Customization** | Makes it yours — overrides that reshape an agent's behavior, add MCP integrations, swap templates, layer in org conventions | `_bmad/custom/{skill-name}.toml` (committed team overrides) and `.user.toml` (personal, gitignored) |
Pull any leg away and the experience collapses:
- Skills without agents → capability lists the user has to navigate by name or code
- Agents without skills → personas with nothing to do
- No customization → every user gets the same out-of-box behavior, forcing forks for any org-specific need
## What Named Agents Buy You
BMad ships six named agents, each anchored to a phase of the BMad Method:
| Agent | Phase | Module |
|---|---|---|
| 📊 **Mary**, Business Analyst | Analysis | market research, brainstorming, product briefs, PRFAQs |
| 📚 **Paige**, Technical Writer | Analysis | project documentation, diagrams, doc validation |
| 📋 **John**, Product Manager | Planning | PRD creation, epic/story breakdown, implementation readiness |
| 🎨 **Sally**, UX Designer | Planning | UX design specifications |
| 🏗️ **Winston**, System Architect | Solutioning | technical architecture, alignment checks |
| 💻 **Amelia**, Senior Engineer | Implementation | story execution, quick-dev, code review, sprint planning |
They each have a hardcoded identity (name, title, domain) and a customizable layer (role, principles, communication style, icon, menu). You can rewrite Mary's principles or add menu items; you can't rename her — that's deliberate. Brand recognition survives customization so "hey Mary" always activates the analyst, regardless of how a team has shaped her behavior.
## The Activation Flow
When you invoke a named agent, eight steps run in order:
1. **Resolve the agent block** — merge the shipped `customize.toml` with team and personal overrides, via a Python resolver using stdlib `tomllib`
2. **Execute prepend steps** — any pre-flight behavior the team configured
3. **Adopt persona** — hardcoded identity plus customized role, communication style, principles
4. **Load persistent facts** — org rules, compliance notes, optionally files loaded via a `file:` prefix (e.g., `file:{project-root}/docs/project-context.md`)
5. **Load config** — user name, communication language, output language, artifact paths
6. **Greet** — personalized, in the configured language, with the agent's emoji prefix so you can see at a glance who's speaking
7. **Execute append steps** — any post-greet setup the team configured
8. **Dispatch or present the menu** — if your opening message maps to a menu item, go directly; otherwise render the menu and wait for input
Step 8 is where intent meets capability. "Hey Mary, let's brainstorm" skips rendering because `bmad-brainstorming` is an obvious match for `BP` on Mary's menu. If you say something ambiguous, she asks once, briefly, not as a confirmation ritual. If nothing fits, she continues the conversation normally.
## Why Not Just a Menu?
Menus force the user to meet the tool halfway. You have to remember that brainstorming lives under code `BP` on the analyst agent, not the PM agent, and know which persona owns which capabilities. That's cognitive overhead the tool is making you carry.
Named agents invert it. You say what you want, to whom, in whatever words feel natural. The agent knows who they are and what they do. When your intent is clear enough, they just go.
The menu is still there as a fallback — show it when you're exploring, skip it when you're not.
## Why Not Just a Blank Prompt?
Blank prompts assume you know the magic words. "Help me brainstorm" might work, but "let's ideate on my SaaS idea" might not, and the results depend on how you phrased the ask. You become responsible for prompt engineering.
Named agents add structure without closing off freedom. The persona stays consistent, the capabilities are discoverable, and `bmad-help` is always one command away. You don't have to guess what the agent can do, and you don't need a manual to use it either.
## Customization as a First-Class Citizen
The customization model is what lets this scale beyond a single developer.
Every agent ships a `customize.toml` with sensible defaults. Teams commit overrides to `_bmad/custom/bmad-agent-{role}.toml`. Individuals can layer personal preferences in `.user.toml` (gitignored). The resolver merges all three at activation time with predictable structural rules.
Most users never hand-author these files. The `bmad-customize` skill walks through picking the target, choosing agent vs workflow scope, authoring the override, and verifying the merge — so the customization surface stays accessible to anyone who understands their intent, not just those fluent in TOML.
Concrete example: a team commits a single file telling Amelia to always use the Context7 MCP tool for library docs and to fall back to Linear when a story isn't in the local epics list. Every dev workflow Amelia dispatches (dev-story, quick-dev, create-story, code-review) inherits that behavior, with no source edits or per-workflow duplication required.
There's also a second customization surface for *cross-cutting* concerns: the central `_bmad/config.toml` and `_bmad/config.user.toml` (both installer-owned, rebuilt from each module's `module.yaml`) plus `_bmad/custom/config.toml` (team, committed) and `_bmad/custom/config.user.toml` (personal, gitignored) for overrides. This is where the **agent roster** lives — the lightweight descriptors that roster consumers like `bmad-party-mode`, `bmad-retrospective`, and `bmad-advanced-elicitation` read to know who's available and how to embody them. Rebrand an agent org-wide with a team override; add fictional voices (Kirk, Spock, a domain expert persona) as personal experiments via the `.user.toml` override — without touching any skill folder. The per-skill file shapes how Mary *behaves* when she activates; the central config shapes how other skills *see* her when they look at the field.
For the full customization surface and worked examples, see:
- [How to Customize BMad](../how-to/customize-bmad.md) — the reference for what's customizable and how merge works
- [How to Expand BMad for Your Organization](../how-to/expand-bmad-for-your-org.md) — five worked recipes spanning agent-wide rules, workflow conventions, external publishing, template swaps, and agent roster customization
- `bmad-customize` skill — the guided authoring helper that turns intent into a correctly-placed, verified override file
## The Bigger Idea
Most AI assistants today are either menus or prompts, and both shift cognitive load onto the user. Named agents plus customizable skills let you talk to a teammate who already knows the work, and let your organization shape that teammate without forking.
The next time you type "Hey Mary, let's brainstorm" and she just gets on with it, notice what didn't happen. There was no slash command, no menu to navigate, no awkward reminder of what she can do. That absence is the design.

View File

@ -9,7 +9,7 @@ Get all your AI agents in one conversation.
## What is Party Mode? ## What is Party Mode?
Run `party-mode` and you've got your whole AI team in one room - PM, Architect, Dev, UX Designer, whoever you need. BMad Master orchestrates, picking relevant agents per message. Agents respond in character, agree, disagree, and build on each other's ideas. Run `bmad-party-mode` and you've got your whole AI team in one room - PM, Architect, Dev, UX Designer, whoever you need. BMad Master orchestrates, picking relevant agents per message. Agents respond in character, agree, disagree, and build on each other's ideas.
The conversation continues as long as you want. Ask follow-ups, push back on answers, redirect the discussion - it's a real back-and-forth with your agents until you're done. The conversation continues as long as you want. Ask follow-ups, push back on answers, redirect the discussion - it's a real back-and-forth with your agents until you're done.

View File

@ -108,5 +108,5 @@ Common decisions that prevent conflicts:
- Document decisions that cross epic boundaries - Document decisions that cross epic boundaries
- Focus on conflict-prone areas - Focus on conflict-prone areas
- Update architecture as you learn - Update architecture as you learn
- Use `correct-course` for significant changes - Use `bmad-correct-course` for significant changes
::: :::

View File

@ -21,12 +21,12 @@ The `project-context.md` file solves this by documenting what agents need to kno
Every implementation workflow automatically loads `project-context.md` if it exists. The architect workflow also loads it to respect your technical preferences when designing the architecture. Every implementation workflow automatically loads `project-context.md` if it exists. The architect workflow also loads it to respect your technical preferences when designing the architecture.
**Loaded by these workflows:** **Loaded by these workflows:**
- `create-architecture` — respects technical preferences during solutioning - `bmad-create-architecture` — respects technical preferences during solutioning
- `create-story` — informs story creation with project patterns - `bmad-create-story` — informs story creation with project patterns
- `dev-story` — guides implementation decisions - `bmad-dev-story` — guides implementation decisions
- `code-review` — validates against project standards - `bmad-code-review` — validates against project standards
- `quick-dev` — applies patterns when implementing tech-specs - `bmad-quick-dev` — applies patterns when implementing specs
- `sprint-planning`, `retrospective`, `correct-course` — provides project-wide context - `bmad-sprint-planning`, `bmad-retrospective`, `bmad-correct-course` — provides project-wide context
## When to Create It ## When to Create It
@ -34,10 +34,10 @@ The `project-context.md` file is useful at any stage of a project:
| Scenario | When to Create | Purpose | | Scenario | When to Create | Purpose |
|----------|----------------|---------| |----------|----------------|---------|
| **New project, before architecture** | Manually, before `create-architecture` | Document your technical preferences so the architect respects them | | **New project, before architecture** | Manually, before `bmad-create-architecture` | Document your technical preferences so the architect respects them |
| **New project, after architecture** | Via `generate-project-context` or manually | Capture architecture decisions for implementation agents | | **New project, after architecture** | Via `bmad-generate-project-context` or manually | Capture architecture decisions for implementation agents |
| **Existing project** | Via `generate-project-context` | Discover existing patterns so agents follow established conventions | | **Existing project** | Via `bmad-generate-project-context` | Discover existing patterns so agents follow established conventions |
| **Quick Flow project** | Before or during `quick-dev` | Ensure quick implementation respects your patterns | | **Quick Flow project** | Before or during `bmad-quick-dev` | Ensure quick implementation respects your patterns |
:::tip[Recommended] :::tip[Recommended]
For new projects, create it manually before architecture if you have strong technical preferences. Otherwise, generate it after architecture to capture those decisions. For new projects, create it manually before architecture if you have strong technical preferences. Otherwise, generate it after architecture to capture those decisions.
@ -107,20 +107,20 @@ Edit it with your technology stack and implementation rules. The architect and i
### Generate After Architecture ### Generate After Architecture
Run the `generate-project-context` workflow after completing your architecture: Run the `bmad-generate-project-context` workflow after completing your architecture:
```bash ```bash
/bmad-bmm-generate-project-context bmad-generate-project-context
``` ```
This scans your architecture document and project files to generate a context file capturing the decisions made. This scans your architecture document and project files to generate a context file capturing the decisions made.
### Generate for Existing Projects ### Generate for Existing Projects
For existing projects, run `generate-project-context` to discover existing patterns: For existing projects, run `bmad-generate-project-context` to discover existing patterns:
```bash ```bash
/bmad-bmm-generate-project-context bmad-generate-project-context
``` ```
The workflow analyzes your codebase to identify conventions, then generates a context file you can review and refine. The workflow analyzes your codebase to identify conventions, then generates a context file you can review and refine.
@ -150,7 +150,7 @@ The `project-context.md` file is a living document. Update it when:
- Patterns evolve during implementation - Patterns evolve during implementation
- You identify gaps from agent behavior - You identify gaps from agent behavior
You can edit it manually at any time, or re-run `generate-project-context` to update it after significant changes. You can edit it manually at any time, or re-run `bmad-generate-project-context` to update it after significant changes.
:::note[File Location] :::note[File Location]
The default location is `_bmad-output/project-context.md`. Workflows search for it there, and also check `**/project-context.md` anywhere in your project. The default location is `_bmad-output/project-context.md`. Workflows search for it there, and also check `**/project-context.md` anywhere in your project.

View File

@ -0,0 +1,73 @@
---
title: "Quick Dev"
description: Reduce human-in-the-loop friction without giving up the checkpoints that protect output quality
sidebar:
order: 2
---
Intent in, code changes out, with as few human-in-the-loop turns as possible — without sacrificing quality.
It lets the model run longer between checkpoints, then brings the human back only when the task cannot safely continue without human judgment or when it is time to review the end result.
![Quick Dev workflow diagram](/diagrams/quick-dev-diagram.png)
## Why This Exists
Human-in-the-loop turns are necessary and expensive.
Current LLMs still fail in predictable ways: they misread intent, fill gaps with confident guesses, drift into unrelated work, and generate noisy review output. At the same time, constant human intervention limits development velocity. Human attention is the bottleneck.
`bmad-quick-dev` rebalances that tradeoff. It trusts the model to run unsupervised for longer stretches, but only after the workflow has created a strong enough boundary to make that safe.
## The Core Design
### 1. Compress intent first
The workflow starts by having the human and the model compress the request into one coherent goal. The input can begin as a rough expression of intent, but before the workflow runs autonomously it has to become small enough, clear enough, and contradiction-free enough to execute.
Intent can come in many forms: a couple of phrases, a bug tracker link, output from plan mode, text copied from a chat session, or even a story number from BMAD's own `epics.md`. In that last case, the workflow will not understand BMAD story-tracking semantics, but it can still take the story itself and run with it.
This workflow does not eliminate human control. It relocates it to a small number of high-value moments:
- **Intent clarification** - turning a messy request into one coherent goal without hidden contradictions
- **Spec approval** - confirming that the frozen understanding is the right thing to build
- **Review of the final product** - the primary checkpoint, where the human decides whether the result is acceptable at the end
### 2. Route to the smallest safe path
Once the goal is clear, the workflow decides whether this is a true one-shot change or whether it needs the fuller path. Small, zero-blast-radius changes can go straight to implementation. Everything else goes through planning so the model has a stronger boundary before it runs longer on its own.
### 3. Run longer with less supervision
After that routing decision, the model can carry more of the work on its own. On the fuller path, the approved spec becomes the boundary the model executes against with less supervision, which is the whole point of the design.
### 4. Diagnose failure at the right layer
If the implementation is wrong because the intent was wrong, patching the code is the wrong fix. If the code is wrong because the spec was weak, patching the diff is also the wrong fix. The workflow is designed to diagnose where the failure entered the system, go back to that layer, and regenerate from there.
Review findings are used to decide whether the problem came from intent, spec generation, or local implementation. Only truly local problems get patched locally.
### 5. Bring the human back only when needed
The intent interview is human-in-the-loop, but it is not the same kind of interruption as a recurring checkpoint. The workflow tries to keep those recurring checkpoints to a minimum. After the initial shaping of intent, the human mainly comes back when the workflow cannot safely continue without judgment and at the end, when it is time to review the result.
- **Intent-gap resolution** - stepping back in when review proves the workflow could not safely infer what was meant
Everything else is a candidate for longer autonomous execution. That tradeoff is deliberate. Older patterns spend more human attention on continuous supervision. Quick Dev spends more trust on the model, but saves human attention for the moments where human reasoning has the highest leverage.
## Why the Review System Matters
The review phase is not just there to find bugs. It is there to route correction without destroying momentum.
This workflow works best on a platform that can spawn subagents, or at least invoke another LLM through the command line and wait for a result. If your platform does not support that natively, you can add a skill to do it. Context-free subagents are a cornerstone of the review design.
Agentic reviews often go wrong in two ways:
- They generate too many findings, forcing the human to sift through noise.
- They derail the current change by surfacing unrelated issues and turning every run into an ad hoc cleanup project.
Quick Dev addresses both by treating review as triage.
Some findings belong to the current change. Some do not. If a finding is incidental rather than causally tied to the current work, the workflow can defer it instead of forcing the human to handle it immediately. That keeps the run focused and prevents random tangents from consuming the budget of attention.
That triage will sometimes be imperfect. That is acceptable. It is usually better to misjudge some findings than to flood the human with thousands of low-value review comments. The system is optimizing for signal quality, not exhaustive recall.

View File

@ -1,73 +0,0 @@
---
title: "Quick Flow"
description: Fast-track for small changes - skip the full methodology
sidebar:
order: 1
---
Skip the ceremony. Quick Flow takes you from idea to working code in two commands - no Product Brief, no PRD, no Architecture doc.
## When to Use It
- Bug fixes and patches
- Refactoring existing code
- Small, well-understood features
- Prototyping and spikes
- Single-agent work where one developer can hold the full scope
## When NOT to Use It
- New products or platforms that need stakeholder alignment
- Major features spanning multiple components or teams
- Work that requires architectural decisions (database schema, API contracts, service boundaries)
- Anything where requirements are unclear or contested
:::caution[Scope Creep]
If you start a Quick Flow and realize the scope is bigger than expected, `quick-dev` will detect this and offer to escalate. You can switch to a full PRD workflow at any point without losing your work.
:::
## How It Works
Quick Flow has two commands, each backed by a structured workflow. You can run them together or independently.
### quick-spec: Plan
Run `quick-spec` and Barry (the Quick Flow agent) walks you through a conversational discovery process:
1. **Understand** - You describe what you want to build. Barry scans the codebase to ask informed questions, then captures a problem statement, solution approach, and scope boundaries.
2. **Investigate** - Barry reads relevant files, maps code patterns, identifies files to modify, and documents the technical context.
3. **Generate** - Produces a complete tech-spec with ordered implementation tasks (specific file paths and actions), acceptance criteria in Given/When/Then format, testing strategy, and dependencies.
4. **Review** - Presents the full spec for your sign-off. You can edit, ask questions, run adversarial review, or refine with advanced elicitation before finalizing.
The output is a `tech-spec-{slug}.md` file saved to your project's implementation artifacts folder. It contains everything a fresh agent needs to implement the feature - no conversation history required.
### quick-dev: Build
Run `quick-dev` and Barry implements the work. It operates in two modes:
- **Tech-spec mode** - Point it at a spec file (`quick-dev tech-spec-auth.md`) and it executes every task in order, writes tests, and verifies acceptance criteria.
- **Direct mode** - Give it instructions directly (`quick-dev "refactor the auth middleware"`) and it gathers context, builds a mental plan, and executes.
After implementation, `quick-dev` runs a self-check audit against all tasks and acceptance criteria, then triggers an adversarial code review of the diff. Findings are presented for you to resolve before wrapping up.
:::tip[Fresh Context]
For best results, run `quick-dev` in a new conversation after finishing `quick-spec`. This gives the implementation agent clean context focused solely on building.
:::
## What Quick Flow Skips
The full BMad Method produces a Product Brief, PRD, Architecture doc, and Epic/Story breakdown before any code is written. Quick Flow replaces all of that with a single tech-spec. This works because Quick Flow targets changes where:
- The product direction is already established
- Architecture decisions are already made
- A single developer can reason about the full scope
- Requirements fit in one conversation
## Escalating to Full BMad Method
Quick Flow includes built-in guardrails for scope detection. When you run `quick-dev` with a direct request, it evaluates signals like multi-component mentions, system-level language, and uncertainty about approach. If it detects the work is bigger than a quick flow:
- **Light escalation** - Recommends running `quick-spec` first to create a plan
- **Heavy escalation** - Recommends switching to the full BMad Method PRD process
You can also escalate manually at any time. Your tech-spec work carries forward - it becomes input for the broader planning process rather than being discarded.

8
docs/fr/404.md Normal file
View File

@ -0,0 +1,8 @@
---
title: Page introuvable
template: splash
---
La page que vous recherchez n'existe pas ou a été déplacée.
[Retour à l'accueil](/fr/index.md)

370
docs/fr/_STYLE_GUIDE.md Normal file
View File

@ -0,0 +1,370 @@
---
title: "Guide de style de la documentation"
description: Conventions de documentation spécifiques au projet, basées sur le style Google et la structure Diataxis
---
Ce projet suit le [Guide de style de documentation pour développeurs Google](https://developers.google.com/style) et utilise [Diataxis](https://diataxis.fr/) pour structurer le contenu. Seules les conventions spécifiques au projet sont présentées ci-dessous.
## Règles spécifiques au projet
| Règle | Spécification |
| --------------------------------------- | ------------------------------------------------------ |
| Pas de règles horizontales (`---`) | Perturbe le flux de lecture des fragments |
| Pas de titres `####` | Utiliser du texte en gras ou des admonitions |
| Pas de sections « Related » ou « Next: » | La barre latérale gère la navigation |
| Pas de listes profondément imbriquées | Diviser en sections à la place |
| Pas de blocs de code pour non-code | Utiliser des admonitions pour les exemples de dialogue |
| Pas de paragraphes en gras pour les appels | Utiliser des admonitions à la place |
| 1-2 admonitions max par section | Les tutoriels permettent 3-4 par section majeure |
| Cellules de tableau / éléments de liste | 1-2 phrases maximum |
| Budget de titres | 8-12 `##` par doc ; 2-3 `###` par section |
## Admonitions (Syntaxe Starlight)
```md
:::tip[Titre]
Raccourcis, bonnes pratiques
:::
:::note[Titre]
Contexte, définitions, exemples, prérequis
:::
:::caution[Titre]
Mises en garde, problèmes potentiels
:::
:::danger[Titre]
Avertissements critiques uniquement — perte de données, problèmes de sécurité
:::
```
### Utilisations standards
| Admonition | Usage |
| -------------------------- | ---------------------------------------- |
| `:::note[Pré-requis]` | Dépendances avant de commencer |
| `:::tip[Chemin rapide]` | Résumé TL;DR en haut du document |
| `:::caution[Important]` | Mises en garde critiques |
| `:::note[Exemple]` | Exemples de commandes/réponses |
## Formats de tableau standards
**Phases :**
```md
| Phase | Nom | Ce qui se passe |
| ----- | ---------- | --------------------------------------------------- |
| 1 | Analyse | Brainstorm, recherche *(optionnel)* |
| 2 | Planification | Exigences — PRD ou spécification technique *(requis)* |
```
**Skills :**
```md
| Skill | Agent | Objectif |
| ------------------- | ------- | ----------------------------------------------- |
| `bmad-brainstorming` | Analyste | Brainstorming pour un nouveau projet |
| `bmad-create-prd` | PM | Créer un document d'exigences produit |
```
## Blocs de structure de dossiers
À afficher dans les sections "Ce que vous avez accompli" :
````md
```
votre-projet/
├── _bmad/ # Configuration BMad
├── _bmad-output/
│ ├── planning-artifacts/
│ │ └── PRD.md # Votre document d'exigences
│ ├── implementation-artifacts/
│ └── project-context.md # Règles d'implémentation (optionnel)
└── ...
```
````
## Structure des tutoriels
```text
1. Titre + Accroche (1-2 phrases décrivant le résultat)
2. Notice de version/module (admonition info ou avertissement) (optionnel)
3. Ce que vous allez apprendre (liste à puces des résultats)
4. Prérequis (admonition info)
5. Chemin rapide (admonition tip - résumé TL;DR)
6. Comprendre [Sujet] (contexte avant les étapes - tableaux pour phases/agents)
7. Installation (optionnel)
8. Étape 1 : [Première tâche majeure]
9. Étape 2 : [Deuxième tâche majeure]
10. Étape 3 : [Troisième tâche majeure]
11. Ce que vous avez accompli (résumé + structure de dossiers)
12. Référence rapide (tableau des compétences)
13. Questions courantes (format FAQ)
14. Obtenir de l'aide (liens communautaires)
15. Points clés à retenir (admonition tip)
```
### Liste de vérification des tutoriels
- [ ] L'accroche décrit le résultat en 1-2 phrases
- [ ] Section "Ce que vous allez apprendre" présente
- [ ] Prérequis dans une admonition
- [ ] Admonition TL;DR de chemin rapide en haut
- [ ] Tableaux pour phases, skills, agents
- [ ] Section "Ce que vous avez accompli" présente
- [ ] Tableau de référence rapide présent
- [ ] Section questions courantes présente
- [ ] Section obtenir de l'aide présente
- [ ] Admonition points clés à retenir à la fin
## Structure des guides pratiques (How-To)
```text
1. Titre + Accroche (une phrase : « Utilisez le workflow `X` pour... »)
2. Quand utiliser ce guide (liste à puces de scénarios)
3. Quand éviter ce guide (optionnel)
4. Prérequis (admonition note)
5. Étapes (sous-sections ### numérotées)
6. Ce que vous obtenez (produits de sortie/artefacts)
7. Exemple (optionnel)
8. Conseils (optionnel)
9. Prochaines étapes (optionnel)
```
### Liste de vérification des guides pratiques
- [ ] L'accroche commence par « Utilisez le workflow `X` pour... »
- [ ] "Quand utiliser ce guide" contient 3-5 points
- [ ] Prérequis listés
- [ ] Les étapes sont des sous-sections `###` numérotées avec des verbes d'action
- [ ] "Ce que vous obtenez" décrit les artefacts produits
## Structure des explications
### Types
| Type | Exemple |
| ----------------------- | ------------------------------------ |
| **Index/Page d'accueil** | `core-concepts/index.md` |
| **Concept** | `what-are-agents.md` |
| **Fonctionnalité** | `quick-dev.md` |
| **Philosophie** | `why-solutioning-matters.md` |
| **FAQ** | `established-projects-faq.md` |
### Modèle général
```text
1. Titre + Accroche (1-2 phrases)
2. Vue d'ensemble/Définition (ce que c'est, pourquoi c'est important)
3. Concepts clés (sous-sections ###)
4. Tableau comparatif (optionnel)
5. Quand utiliser / Quand ne pas utiliser (optionnel)
6. Diagramme (optionnel - mermaid, 1 max par doc)
7. Prochaines étapes (optionnel)
```
### Pages d'index/d'accueil
```text
1. Titre + Accroche (une phrase)
2. Tableau de contenu (liens avec descriptions)
3. Pour commencer (liste numérotée)
4. Choisissez votre parcours (optionnel - arbre de décision)
```
### Explications de concepts
```text
1. Titre + Accroche (ce que c'est)
2. Types/Catégories (sous-sections ###) (optionnel)
3. Tableau des différences clés
4. Composants/Parties
5. Lequel devriez-vous utiliser ?
6. Création/Personnalisation (lien vers les guides pratiques)
```
### Explications de fonctionnalités
```text
1. Titre + Accroche (ce que cela fait)
2. Faits rapides (optionnel - "Idéal pour :", "Temps :")
3. Quand utiliser / Quand ne pas utiliser
4. Comment cela fonctionne (diagramme mermaid optionnel)
5. Avantages clés
6. Tableau comparatif (optionnel)
7. Quand évoluer/mettre à niveau (optionnel)
```
### Documents de philosophie/justification
```text
1. Titre + Accroche (le principe)
2. Le problème
3. La solution
4. Principes clés (sous-sections ###)
5. Avantages
6. Quand cela s'applique
```
### Liste de vérification des explications
- [ ] L'accroche énonce ce que le document explique
- [ ] Contenu dans des sections `##` parcourables
- [ ] Tableaux comparatifs pour 3+ options
- [ ] Les diagrammes ont des étiquettes claires
- [ ] Liens vers les guides pratiques pour les questions procédurales
- [ ] 2-3 admonitions max par document
## Structure des références
### Types
| Type | Exemple |
| ----------------------- | --------------------- |
| **Index/Page d'accueil** | `workflows/index.md` |
| **Catalogue** | `agents/index.md` |
| **Approfondissement** | `document-project.md` |
| **Configuration** | `core-tasks.md` |
| **Glossaire** | `glossary/index.md` |
| **Complet** | `bmgd-workflows.md` |
### Pages d'index de référence
```text
1. Titre + Accroche (une phrase)
2. Sections de contenu (## pour chaque catégorie)
- Liste à puces avec liens et descriptions
```
### Référence de catalogue
```text
1. Titre + Accroche
2. Éléments (## pour chaque élément)
- Brève description (une phrase)
- **Skills :** ou **Infos clés :** sous forme de liste simple
3. Universel/Partagé (## section) (optionnel)
```
### Référence d'approfondissement d'élément
```text
1. Titre + Accroche (objectif en une phrase)
2. Faits rapides (admonition note optionnelle)
- Module, Skill, Entrée, Sortie sous forme de liste
3. Objectif/Vue d'ensemble (## section)
4. Comment invoquer (bloc de code)
5. Sections clés (## pour chaque aspect)
- Utiliser ### pour les sous-options
6. Notes/Mises en garde (admonition tip ou caution)
```
### Référence de configuration
```text
1. Titre + Accroche
2. Table des matières (liens de saut si 4+ éléments)
3. Éléments (## pour chaque config/tâche)
- **Résumé en gras** — une phrase
- **Utilisez-le quand :** liste à puces
- **Comment cela fonctionne :** étapes numérotées (3-5 max)
- **Sortie :** résultat attendu (optionnel)
```
### Guide de référence complet
```text
1. Titre + Accroche
2. Vue d'ensemble (## section)
- Diagramme ou tableau montrant l'organisation
3. Sections majeures (## pour chaque phase/catégorie)
- Éléments (### pour chaque élément)
- Champs standardisés : Skill, Agent, Entrée, Sortie, Description
4. Prochaines étapes (optionnel)
```
### Liste de vérification des références
- [ ] L'accroche énonce ce que le document référence
- [ ] La structure correspond au type de référence
- [ ] Les éléments utilisent une structure cohérente
- [ ] Tableaux pour les données structurées/comparatives
- [ ] Liens vers les documents d'explication pour la profondeur conceptuelle
- [ ] 1-2 admonitions max
## Structure du glossaire
Starlight génère la navigation "Sur cette page" à droite à partir des titres :
- Catégories en tant que titres `##` — apparaissent dans la navigation à droite
- Termes dans des tableaux — lignes compactes, pas de titres individuels
- Pas de TOC en ligne — la barre latérale à droite gère la navigation
### Format de tableau
```md
## Nom de catégorie
| Terme | Définition |
| ------------ | --------------------------------------------------------------------------------------------- |
| **Agent** | Personnalité IA spécialisée avec une expertise spécifique qui guide les utilisateurs dans les workflows. |
| **Workflow** | Processus guidé en plusieurs étapes qui orchestre les activités des agents IA pour produire des livrables. |
```
### Règles de définition
| À faire | À ne pas faire |
| --------------------------------- | --------------------------------------------- |
| Commencer par ce que c'est ou ce que cela fait | Commencer par « C'est... » ou « Un [terme] est... » |
| Se limiter à 1-2 phrases | Écrire des explications de plusieurs paragraphes |
| Mettre le nom du terme en gras dans la cellule | Utiliser du texte simple pour les termes |
### Marqueurs de contexte
Ajouter un contexte en italique au début de la définition pour les termes à portée limitée :
- `*Quick Dev uniquement.*`
- `*méthode BMad/Enterprise.*`
- `*Phase N.*`
- `*BMGD.*`
- `*Projets établis.*`
### Liste de vérification du glossaire
- [ ] Termes dans des tableaux, pas de titres individuels
- [ ] Termes alphabétisés au sein des catégories
- [ ] Définitions de 1-2 phrases
- [ ] Marqueurs de contexte en italique
- [ ] Noms des termes en gras dans les cellules
- [ ] Pas de définitions « Un [terme] est... »
## Sections FAQ
```md
## Questions
- [Ai-je toujours besoin d'architecture ?](#ai-je-toujours-besoin-darchitecture)
- [Puis-je modifier mon plan plus tard ?](#puis-je-modifier-mon-plan-plus-tard)
### Ai-je toujours besoin d'architecture ?
Uniquement pour les parcours méthode BMad et Enterprise. Quick Dev passe directement à l'implémentation.
### Puis-je modifier mon plan plus tard ?
Oui. Utilisez `bmad-correct-course` pour gérer les changements de portée en cours dimplémentation.
**Une question sans réponse ici ?** [Ouvrez une issue](...) ou posez votre question sur [Discord](...).
```
## Commandes de validation
Avant de soumettre des modifications de documentation :
```bash
npm run docs:fix-links # Prévisualiser les corrections de format de liens
npm run docs:fix-links -- --write # Appliquer les corrections
npm run docs:validate-links # Vérifier que les liens existent
npm run docs:build # Vérifier l'absence d'erreurs de build
```

View File

@ -0,0 +1,49 @@
---
title: "Élicitation Avancée"
description: Pousser le LLM à repenser son travail en utilisant des méthodes de raisonnement structurées
sidebar:
order: 8
---
Faites repenser au LLM ce qu'il vient de générer. Vous choisissez une méthode de raisonnement, il l'applique à sa propre sortie, et vous décidez de conserver ou non les améliorations.
## Qu'est-ce que lÉlicitation Avancée ?
Un second passage structuré. Au lieu de demander à l'IA de "réessayer" ou de "faire mieux", vous sélectionnez une méthode de raisonnement spécifique et l'IA réexamine sa propre sortie à travers ce prisme.
La différence est importante. Les demandes vagues produisent des révisions vagues. Une méthode nommée impose un angle d'attaque particulier, mettant en lumière des perspectives qu'un simple réajustement générique aurait manquées.
## Quand l'utiliser
- Après qu'un workflow a généré du contenu et vous souhaitez des alternatives
- Lorsque la sortie semble correcte mais que vous soupçonnez qu'il y a davantage de profondeur
- Pour tester les hypothèses ou trouver des faiblesses
- Pour du contenu à enjeux élevés où la réflexion approfondie aide
Les workflows offrent l'élicitation aux points de décision - après que le LLM ait généré quelque chose, on vous demandera si vous souhaitez l'exécuter.
## Comment ça fonctionne
1. Le LLM suggère 5 méthodes pertinentes pour votre contenu
2. Vous en choisissez une (ou remélangez pour différentes options)
3. La méthode est appliquée, les améliorations sont affichées
4. Acceptez ou rejetez, répétez ou continuez
## Méthodes intégrées
Des dizaines de méthodes de raisonnement sont disponibles. Quelques exemples :
- **Analyse Pré-mortem** - Suppose que le projet a déjà échoué, revient en arrière pour trouver pourquoi
- **Pensée de Premier Principe** - Élimine les hypothèses, reconstruit à partir de la vérité de terrain
- **Inversion** - Demande comment garantir l'échec, puis les évite
- **Équipe Rouge vs Équipe Bleue** - Attaque votre propre travail, puis le défend
- **Questionnement Socratique** - Conteste chaque affirmation avec "pourquoi ?" et "comment le savez-vous ?"
- **Suppression des Contraintes** - Abandonne toutes les contraintes, voit ce qui change, les réajoute sélectivement
- **Cartographie des Parties Prenantes** - Réévalue depuis la perspective de chaque partie prenante
- **Raisonnement Analogique** - Trouve des parallèles dans d'autres domaines et applique leurs leçons
Et bien d'autres. L'IA choisit les options les plus pertinentes pour votre contenu - vous choisissez lesquelles exécuter.
:::tip[Commencez Ici]
L'Analyse Pré-mortem est un bon premier choix pour toute spécification ou tout plan. Elle trouve systématiquement des lacunes qu'une révision standard manque.
:::

View File

@ -0,0 +1,66 @@
---
title: "Revue Contradictoire"
description: Technique de raisonnement forcée qui empêche les revues paresseuses du style "ça à l'air bon"
sidebar:
order: 7
---
Forcez une analyse plus approfondie en exigeant que des problèmes soient trouvés.
## Qu'est-ce que la Revue Contradictoire ?
Une technique de revue où le réviseur *doit* trouver des problèmes. Pas de "ça a l'air bon" autorisé. Le réviseur adopte une posture cynique - suppose que des problèmes existent et les trouve.
Il ne s'agit pas d'être négatif. Il s'agit de forcer une analyse authentique au lieu d'un coup d'œil superficiel qui valide automatiquement ce qui a été soumis.
**La règle fondamentale :** Il doit trouver des problèmes. Zéro constatation déclenche un arrêt - réanalyse ou explique pourquoi.
## Pourquoi Cela Fonctionne
Les revues normales souffrent du biais de confirmation[^1]. Il parcourt le travail rapidement, rien ne lui saute aux yeux, il l'approuve. L'obligation de "trouver des problèmes" brise ce schéma :
- **Force la rigueur** - Impossible d'approuver tant quil n'a pas examiné suffisamment en profondeur pour trouver des problèmes
- **Détecte les oublis** - "Qu'est-ce qui manque ici ?" devient une question naturelle
- **Améliore la qualité du signal** - Les constatations sont spécifiques et actionnables, pas des préoccupations vagues
- **Asymétrie d'information**[^2] - Effectue les revues avec un contexte frais (sans accès au raisonnement original) pour évaluer l'artefact, pas l'intention
## Où Elle Est Utilisée
La revue contradictoire apparaît dans tous les workflows BMad - revue de code, vérifications de préparation à l'implémentation, validation de spécifications, et d'autres. Parfois c'est une étape obligatoire, parfois optionnelle (comme l'élicitation avancée ou le mode party). Le pattern s'adapte à n'importe quel artefact nécessitant un examen.
## Filtrage Humain Requis
Parce que l'IA est *instruite* de trouver des problèmes, elle trouvera des problèmes - même lorsqu'ils n'existent pas. Attendez-vous à des faux positifs : des détails présentés comme des problèmes, des malentendus sur l'intention, ou des préoccupations purement hallucinées[^3].
**C'est vous qui décidez ce qui est réel.** Examinez chaque constatation, ignorez le bruit, corrigez ce qui compte.
## Exemple
Au lieu de :
> "L'implémentation de l'authentification semble raisonnable. Approuvé."
Une revue contradictoire produit :
> 1. **ÉLEVÉ** - `login.ts:47` - Pas de limitation de débit sur les tentatives échouées
> 2. **ÉLEVÉ** - Jeton de session stocké dans localStorage (vulnérable au XSS)
> 3. **MOYEN** - La validation du mot de passe se fait côté client uniquement
> 4. **MOYEN** - Pas de journalisation d'audit pour les tentatives de connexion échouées
> 5. **FAIBLE** - Le nombre magique `3600` devrait être `SESSION_TIMEOUT_SECONDS`
La première revue pourrait manquer une vulnérabilité de sécurité. La seconde en a attrapé quatre.
## Itération et Rendements Décroissants
Après avoir traité les constatations, envisagez de relancer la revue. Une deuxième passe détecte généralement plus de problèmes. Une troisième n'est pas toujours inutile non plus. Mais chaque passe prend du temps, et vous finissez par atteindre des rendements décroissants[^4] - juste des détails et des faux problèmes.
:::tip[Meilleures Revues]
Supposez que des problèmes existent. Cherchez ce qui manque, pas seulement ce qui ne va pas.
:::
## Glossaire
[^1]: **Biais de confirmation** : tendance cognitive à rechercher, interpréter et favoriser les informations qui confirment nos croyances préexistantes, tout en ignorant ou minimisant celles qui les contredisent.
[^2]: **Asymétrie d'information** : situation où une partie dispose de plus ou de meilleures informations qu'une autre, conduisant potentiellement à des décisions ou jugements biaisés.
[^3]: **Hallucination (IA)** : phénomène où un modèle d'IA génère des informations plausibles mais factuellement incorrectes ou inventées, présentées avec confiance comme si elles étaient vraies.
[^4]: **Rendements décroissants** : principe selon lequel l'augmentation continue d'un investissement (temps, effort, ressources) finit par produire des bénéfices de plus en plus faibles proportionnellement.

View File

@ -0,0 +1,74 @@
---
title: "Phase d'analyse : de l'Idée aux Fondations"
description: Ce que sont le brainstorming, la recherche, les product briefs et les PRFAQs — et quand les utiliser
sidebar:
order: 1
---
La phase d'Analyse (Phase 1) vous aide à penser clairement à votre produit avant de vous engager à le construire. Chaque outil de cette phase est optionnel, mais sauter l'analyse entièrement signifie que votre PRD sera construit sur des suppositions plutôt que sur des connaissances approfondies.
## Pourquoi Analyser avant de Planifier ?
Un PRD répond à la question « que devons-nous construire et pourquoi ? » Si vous l'alimentez avec une réflexion vague, vous obtiendrez un PRD vague — et chaque document en aval héritera de cette imprécision. Une architecture bâtie sur un PRD faible prend de mauvaises décisions techniques. Les stories dérivées d'une architecture faible manquent de edge cases. Le coût s'accumule.
Les outils d'analyse existent pour rendre votre PRD précis. Ils attaquent le problème sous différents angles — exploration créative, réalité du marché, clarté client, faisabilité — pour qu'au moment de vous asseoir avec l'agent PM, vous sachiez ce que vous construisez et pour qui.
## Les Outils
### Brainstorming
**Quoi.** Une session créative facilitée utilisant des techniques d'idéation éprouvées. L'IA agit comme coach, extrayant vos idées à travers des exercices structurés — pas en les générant pour vous.
**Pourquoi.** Les idées brutes ont besoin d'espace pour se développer avant d'être verrouillées dans des exigences. Le brainstorming crée cet espace. Il est particulièrement précieux quand vous avez un espace-problème mais pas de solution claire, ou quand vous voulez explorer plusieurs pistes avant de vous engager.
**Quand.** Vous avez une vague idée de ce que vous voulez construire mais n'avez pas encore cristallisé le concept. Ou vous avez un concept mais voulez l'éprouver face à des alternatives.
Voir [Brainstorming](./brainstorming.md) pour un aperçu plus approfondi du fonctionnement des sessions.
### Recherche (Marché, Domaine, Technique)
**Quoi.** Trois workflows de recherche ciblés qui investiguent différentes dimensions de votre idée. La recherche marché examine les concurrents, les tendances et le sentiment utilisateur. La recherche domaine construit l'expertise métier et la terminologie. La recherche technique évalue la faisabilité, les options d'architecture et les approches d'implémentation.
**Pourquoi.** Construire sur des suppositions est le moyen le plus rapide de construire quelque chose dont personne n'a besoin. La recherche ancre votre concept dans la réalité — quels concurrents existent déjà, avec quoi les utilisateurs luttent réellement, ce qui est techniquement faisable, et quelles contraintes spécifiques à l'industrie vous affronterez.
**Quand.** Vous entrez dans un domaine inconnu, vous soupçonnez que des concurrents existent mais ne les avez pas cartographiés, ou votre concept dépend de capacités techniques que vous n'avez pas validées. Lancez-en un, deux ou les trois — chaque workflow de recherche fonctionne de manière autonome.
### Product Brief[^1]
**Quoi.** Une session de découverte guidée qui produit un résumé exécutif de 1-2 pages de votre concept produit. L'IA agit comme un analyste commercial collaboratif, vous aidant à articuler la vision, le public cible, la proposition de valeur et le périmètre.
**Pourquoi.** Le product brief est le chemin le plus doux vers la planification. Il capture votre vision stratégique dans un format structuré qui alimente directement la création du PRD. Il fonctionne mieux quand vous avez déjà la conviction à propos de votre concept — vous connaissez le client, le problème et approximativement ce que vous voulez construire. Le brief organise et affine cette réflexion.
**Quand.** Votre concept est relativement clair et vous voulez le documenter efficacement avant de créer un PRD. Vous êtes confiant dans la direction et n'avez pas besoin que vos suppositions soient agressivement remises en question.
### PRFAQ (Working Backwards)
**Quoi.** La méthodologie Working Backwards d'Amazon adaptée en défi interactif. Vous rédigez le communiqué de presse annonçant votre produit fini avant qu'une seule ligne de code n'existe, puis répondez aux questions les plus difficiles que les clients et les parties prenantes poseraient. L'IA agit comme un coach produit implacable mais constructif.
**Pourquoi.** Le PRFAQ est le chemin rigoureux vers la planification. Il force la clarté orientée client en vous obligeant à défendre chaque affirmation. Si vous ne pouvez pas rédiger un communiqué de presse convaincant, le produit n'est pas prêt. Si les réponses de la FAQ client révèlent des lacunes, ce sont des lacunes que vous découvrirez bien plus tard — et plus coûteusement — pendant l'implémentation. Le défi fait remonter les failles de réflexion tôt, quand c'est le moins cher de les corriger.
**Quand.** Vous voulez que votre concept soit éprouvé avant d'engager des ressources. Vous n'êtes pas sûr que les utilisateurs s'en soucieront réellement. Vous voulez valider que vous pouvez articuler une proposition de valeur claire et défendable. Ou vous voulez simplement la discipline du Working Backwards pour affiner votre réflexion.
## Lequel utiliser ?
| Situation | Outil recommandé |
|-------------------------------------------------------------------------------|--------------------------------------------|
| « J'ai une idée vague, je ne sais pas par où commencer » | Brainstorming |
| « J'ai besoin de comprendre le marché avant de décider » | Recherche |
| « Je sais ce que je veux construire, j'ai juste besoin de le documenter » | Product Brief |
| « Je veux m'assurer que cette idée vaut vraiment la peine d'être construite » | PRFAQ |
| « Je veux explorer, puis valider, puis documenter » | Brainstorming → Recherche → PRFAQ ou Brief |
Le Product Brief et le PRFAQ produisent tous deux des entrées pour le PRD — choisissez-en un en fonction du niveau de défi que vous souhaitez. Le brief est une découverte collaborative. Le PRFAQ est un défi. Les deux vous mènent à la même destination ; le PRFAQ teste si votre concept mérite d'y arriver.
:::tip[Pas sûr ?]
Exécutez `bmad-help` et décrivez votre situation. Il vous recommandera le bon point de départ en fonction de ce que vous avez déjà accompli et de ce que vous essayez de réaliser.
:::
## Que se passe-t-il après l'analyse ?
Les résultats de l'analyse alimentent directement la Phase 2 (Planification). Le workflow PRD accepte les product briefs, les documents PRFAQ, les conclusions de recherche et les rapports de brainstorming en entrée — il synthétise tout ce que vous avez produit en exigences structurées. Plus vous faites d'analyse, plus votre PRD sera précis.
## Glossaire
[^1]: Brief : document synthétique qui formalise le contexte, les objectifs, le périmètre et les contraintes d'un projet ou d'une demande, afin d'aligner rapidement les parties prenantes avant le travail détaillé.

View File

@ -0,0 +1,33 @@
---
title: "Brainstorming"
description: Sessions interactives créatives utilisant plus de 60 techniques d'idéation éprouvées
sidebar:
order: 2
---
Libérez votre créativité grâce à une exploration guidée.
## Qu'est-ce que le Brainstorming ?
Lancez `bmad-brainstorming` et vous obtenez un facilitateur créatif qui fait émerger vos idées - pas qui les génère pour vous. L'IA agit comme coach et guide, utilisant des techniques éprouvées pour créer les conditions où votre meilleure réflexion émerge.
**Idéal pour :**
- Surmonter les blocages créatifs
- Générer des idées de produits ou de fonctionnalités
- Explorer des problèmes sous de nouveaux angles
- Développer des concepts bruts en plans d'action
## Comment ça fonctionne
1. **Configuration** - Définir le sujet, les objectifs, les contraintes
2. **Choisir l'approche** - Choisir vous-même les techniques, obtenir des recommandations de l'IA, aller au hasard, ou suivre un flux progressif
3. **Facilitation** - Travailler à travers les techniques avec des questions approfondies et un coaching collaboratif
4. **Organiser** - Idées regroupées par thèmes et priorisées
5. **Action** - Les meilleures idées reçoivent des prochaines étapes et des indicateurs de succès
Tout est capturé dans un document de session que vous pouvez consulter ultérieurement ou partager avec les parties prenantes.
:::note[Vos Idées]
Chaque idée vient de vous. Le workflow crée les conditions propices à une vision nouvelle - vous en êtes la source.
:::

View File

@ -0,0 +1,92 @@
---
title: "Checkpoint Preview"
description: Revue assistée par LLM, avec intervention humaine, qui vous guide à travers une modification, de son objectif jusquaux détails
sidebar:
order: 4
---
`bmad-checkpoint-preview` est un workflow de revue interactif, assisté par LLM, avec intervention humaine. Il vous guide à travers une modification de code — de l'intention et du contexte jusqu'aux détails — afin que vous puissiez prendre une décision éclairée sur la mise en production, la refonte ou l'approfondissement.
![Diagramme du workflow Checkpoint Preview](/diagrams/checkpoint-preview-diagram-fr.webp)
## Le Flux Typique
Vous lancez `bmad-quick-dev`. Il clarifie votre intention, construit une spécification, implémente la modification, et une fois terminé, il ajoute un historique de revue au fichier de spécification et l'ouvre dans votre éditeur. Vous regardez la spec et constatez que la modification a touché 20 fichiers dans plusieurs modules.
Vous pourriez survoler le diff. Mais 20 fichiers, c'est le moment où le survol commence à échouer — on perd le fil, on rate un lien entre deux modifications éloignées, ou on approuve quelque chose qu'on n'a pas pleinement compris. Alors au lieu de cela, vous dites « checkpoint » et le LLM vous guide à travers la modification.
Ce passage de relais — de l'implémentation autonome au jugement humain — est le cas d'usage principal. Quick-dev s'exécute longtemps avec une supervision minimale. Checkpoint Preview, c'est là où vous reprenez le volant.
## Pourquoi
La revue de code a deux modes d'échec. Dans le premier, le réviseur survole le diff, rien ne saute aux yeux, et il approuve. Dans le second, il lit méthodiquement chaque fichier mais perd le fil — il voit les arbres et rate la forêt. Les deux aboutissent au même résultat : la revue n'a pas repéré ce qui comptait.
Le problème sous-jacent est le séquençage. Un diff brut présente les modifications dans l'ordre des fichiers, ce qui est presque jamais l'ordre qui construit la compréhension. Vous voyez une fonction utilitaire avant de savoir pourquoi elle existe. Vous voyez une modification de schéma avant de comprendre quelle fonctionnalité elle supporte. Le réviseur doit reconstruire l'intention de l'auteur à partir d'indices dispersés, et c'est cette reconstruction qui fait défaut à l'attention.
Checkpoint Preview résout ce problème en confiant le travail de reconstruction au LLM. Il lit le diff, la spécification (si elle existe) et la base de code environnante, puis présente la modification dans un ordre conçu pour la compréhension — et non pour `git diff`.
## Comment ça fonctionne
Le workflow comporte cinq étapes. Chaque étape s'appuie sur la précédente, passant progressivement de « qu'est-ce que c'est ? » à « devons-nous publier ça ? »
### 1. Orientation
Le workflow identifie la modification (à partir d'une PR, d'un commit, d'une branche, d'un fichier de spécification ou de l'état git actuel) et produit un résumé d'intention en une ligne ainsi que des statistiques de surface : fichiers modifiés, modules touchés, lignes de logique, dépassements de boundaries et nouvelles interfaces publiques.
C'est le moment « est-ce bien ce que je crois ? ». Avant de lire le moindre code, le réviseur confirme qu'il regarde la bonne chose et calibre ses attentes quant à la portée.
### 2. Visite guidée
La modification est organisée par **préoccupation** — des intentions de conception cohérentes comme « validation des entrées » ou « contrat d'API » — et non par fichier. Chaque préoccupation fait l'objet d'une courte explication du *pourquoi* de cette approche, suivie d'arrêts cliquables `chemin:ligne` que le réviseur peut suivre dans le code.
C'est l'étape du jugement de conception. Le réviseur évalue si l'approche est adaptée au système, et non si le code est correct. Les préoccupations sont séquencées de haut en bas : l'intention de plus haut niveau en premier, puis l'implémentation de support. Le réviseur ne rencontre jamais une référence à quelque chose qu'il n'a pas encore vu.
### 3. Passage en revue des détails
Une fois que le réviseur comprend la conception, le workflow met en évidence 2 à 5 endroits où une erreur aurait limpact le plus important. Ceux-ci sont étiquetés par catégorie de risque — `[auth]`, `[schéma]`, `[facturation]`, `[API publique]`, `[sécurité]`, et d'autres — et ordonnés selon l'impact en cas d'erreur.
Ce n'est pas une chasse aux bugs. Les tests automatisés et la CI gèrent la correction. Le passage en revue des détails active la conscience du risque : « voici les endroits où se tromper coûte le plus cher ». Si le réviseur veut approfondir un domaine spécifique, il peut dire « approfondis [domaine] » pour une re-revue ciblée axée sur la correction.
Si la spécification a passé des boucles de revues contradictoires (machine hardening), ces résultats sont également présentés ici — pas les bugs qui ont été corrigés, mais les décisions que la boucle de revue a signalées et dont le réviseur devrait être conscient.
### 4. Tests
Propose 2 à 5 façons d'observer manuellement la modification en action. Pas des commandes de test automatisé — des observations manuelles qui renforcent la confiance au-delà de ce que toute suite de tests peut fournir. Une interaction UI à essayer, une commande CLI à lancer, une requête API à envoyer, avec les résultats attendus pour chacune.
Si la modification n'a aucun comportement visible par l'utilisateur, il le dit. Pas de travail inventé.
### 5. Conclusion
Le réviseur prend la décision : approuver, retravailler ou continuer la discussion. S'il approuve une PR, le workflow peut aider avec `gh pr review --approve`. S'il demande une refonte, il aide à diagnostiquer si le problème vient de l'approche, de la spécification ou de l'implémentation, et aide à rédiger un retour actionnable lié à des emplacements de code spécifiques.
## C'est une conversation, pas un rapport
Le workflow présente chaque étape comme un point de départ, pas un mot final. Entre les étapes — ou au milieu d'une — vous pouvez parler au LLM, poser des questions, remettre en question son cadrage ou faire appel à d'autres skills pour obtenir une perspective différente :
- **« lance l'élicitation avancée sur la gestion des erreurs »** — pousse le LLM à reconsidérer et affiner son analyse d'un domaine spécifique
- **« active le party mode sur la sécurité de cette migration de schéma »** — fait intervenir plusieurs perspectives agentiques dans un débat ciblé
- **« lance la revue de code »** — génère des résultats structurés avec analyse adversariale et cas limites
Le workflow checkpoint ne vous enferme pas dans un chemin linéaire. Il vous donne de la structure quand vous la souhaitez et s'efface quand vous voulez explorer. Les cinq étapes sont là pour s'assurer que vous voyez le tableau complet, mais la profondeur à laquelle vous allez à chaque étape — et les outils que vous y apportez — est entièrement entre vos mains.
## L'historique de revue
L'étape de visite guidée fonctionne mieux lorsqu'elle dispose d'un **ordre de revue suggéré** — une liste d'arrêts que l'auteur de la spécification a rédigée pour guider les réviseurs à travers la modification. Lorsqu'une spécification inclut cet ordre, le workflow l'utilise directement.
Lorsqu'aucun historique produit par l'auteur n'existe, le workflow en génère un à partir du diff et du contexte de la base de code. Un historique généré est de qualité inférieure à un historique produit par l'auteur, mais nettement supérieur à la lecture des modifications dans l'ordre des fichiers.
## Quand l'utiliser
Le scénario principal est le passage de relais depuis `bmad-quick-dev` : l'implémentation est terminée, le fichier de spécification est ouvert dans votre éditeur avec un historique de revue ajouté, et vous devez décider si vous publiez. Dites « checkpoint » et c'est parti.
Il fonctionne aussi de manière autonome :
- **Revue d'une PR** — surtout celles avec plus de quelques fichiers ou des modifications transversales
- **Prise en main d'une modification** — quand vous devez comprendre ce qui s'est passé sur une branche que vous n'avez pas écrite
- **Revue de sprint** — le workflow peut récupérer les stories marquées `review` dans votre fichier de statut de sprint
Invoquez-le en disant « checkpoint » ou « guide-moi à travers cette modification ». Il fonctionne dans n'importe quel terminal, mais vous en tirerez plus de parti dans un IDE — VS Code, Cursor ou similaire — car le workflow produit des références `chemin:ligne` à chaque étape. Dans un terminal intégré à un IDE, celles-ci sont cliquables, ce qui vous permet de sauter de fichier en fichier en suivant l'historique de revue.
## Ce que ce n'est pas
Checkpoint Preview ne remplace pas la revue automatisée. Il ne lance pas de linters, de vérificateurs de types ou de suites de tests. Il n'attribue pas de scores de sévérité et ne produit pas de verdicts pass/échec. C'est un guide de lecture qui aide un humain à appliquer son jugement là où cela compte le plus.

View File

@ -0,0 +1,50 @@
---
title: "FAQ Projets Existants"
description: Questions courantes sur l'utilisation de la méthode BMad sur des projets existants
sidebar:
order: 11
---
Réponses rapides aux questions courantes sur l'utilisation de la méthode BMad (BMM) sur des projets existants.
## Questions
- [Dois-je d'abord exécuter document-project ?](#dois-je-dabord-exécuter-document-project)
- [Que faire si j'oublie d'exécuter document-project ?](#que-faire-si-joublie-dexécuter-document-project)
- [Puis-je utiliser Quick Dev pour les projets existants ?](#puis-je-utiliser-quick-dev-pour-les-projets-existants)
- [Que faire si mon code existant ne suit pas les bonnes pratiques ?](#que-faire-si-mon-code-existant-ne-suit-pas-les-bonnes-pratiques)
### Dois-je d'abord exécuter `document-project` ?
Hautement recommandé, surtout si :
- Aucune documentation existante
- La documentation est obsolète
- Les agents IA ont besoin de contexte sur le code existant
Vous pouvez l'ignorer si vous disposez d'une documentation complète et à jour incluant `docs/index.md` ou si vous utiliserez d'autres outils ou techniques pour aider à la découverte afin que l'agent puisse construire sur un système existant.
### Que faire si j'oublie d'exécuter `document-project` ?
Ne vous inquiétez pas — vous pouvez le faire à tout moment. Vous pouvez même le faire pendant ou après un projet pour aider à maintenir la documentation à jour.
### Puis-je utiliser Quick Dev pour les projets existants ?
Oui ! Quick Dev fonctionne très bien pour les projets existants. Il va :
- Détecter automatiquement votre pile technologique existante
- Analyser les patterns de code existants
- Détecter les conventions et demander confirmation
- Générer une spécification technique riche en contexte qui respecte le code existant
Parfait pour les corrections de bugs et les petites fonctionnalités dans des bases de code existantes.
### Que faire si mon code existant ne suit pas les bonnes pratiques ?
Quick Dev détecte vos conventions et demande : « Dois-je suivre ces conventions existantes ? » Vous décidez :
- **Oui** → Maintenir la cohérence avec la base de code actuelle
- **Non** → Établir de nouvelles normes (documenter pourquoi dans la spécification technique)
BMM respecte votre choix — il ne forcera pas la modernisation, mais la proposera.
**Une question sans réponse ici ?** Veuillez [ouvrir un ticket](https://github.com/bmad-code-org/BMAD-METHOD/issues) ou poser votre question sur [Discord](https://discord.gg/gk8jAdXWmj) afin que nous puissions l'ajouter !

View File

@ -0,0 +1,64 @@
---
title: "Party Mode"
description: Collaboration multi-agents - regroupez tous vos agents IA dans une seule conversation
sidebar:
order: 9
---
Regroupez tous vos agents IA dans une seule conversation.
## Qu'est-ce que le Party Mode ?
Lancez `bmad-party-mode` et vous avez toute votre équipe IA dans une même pièce - PM, Architecte, Développeur, Designer UX, selon vos besoins. BMad Master orchestre, en sélectionnant les agents pertinents à chaque message. Les agents répondent en personnage, sont en accord ou désaccord, et construisent sur les idées des autres.
La conversation continue aussi longtemps que vous le souhaitez. Posez des questions de suivi, remettez en question les réponses, redirigez la discussion - c'est un véritable échange avec vos agents jusqu'à ce que vous ayez terminé.
**Idéal pour :**
- Les grandes décisions avec des compromis
- Les sessions de brainstorming
- Les rétrospectives post-incident quand les choses tournent mal
- Les rétrospectives de sprint et la planification
## Exemples
### Remettre en question une mauvaise architecture
**Vous :** « Ok l'équipe, notre dernier sprint a été un désastre. Le service d'authentification est tombé trois fois. Qui a cafouillé ? »
**Architecte :** « Le design était solide - authentification distribuée avec des fallbacks appropriés. Si l'implémentation a dévié des specs... »
**Développeur :** « J'ai suivi le document d'architecture à la lettre. Les specs ne prenaient pas en compte les race conditions lors de l'invalidation de sessions concurrentes. »
**PM :** « Vous avez tous les deux raté le vrai problème - nous n'avons pas validé les exigences de gestion des sessions dans le PRD. C'est de ma faute de ne pas l'avoir repéré. »
**TEA :** « Et j'aurais dû le repérer dans les tests d'intégration. Les scénarios de test ne couvraient pas l'invalidation concurrente. »
### Brainstorming créatif
**Vous :** « Comment rendre l'onboarding magique au lieu d'ennuyeux ? »
**Designer UX :** « Commençons par la divulgation progressive - révélons les fonctionnalités au fur et à mesure que les utilisateurs en ont besoin, pas d'un coup dans un tutoriel. »
**Storyteller :** « Et si l'onboarding était une histoire ? Chaque étape révèle le parcours d'un personnage - l'utilisateur EST le héros. »
**Game Designer :** « En partant de là - et si la première "quête" consistait à résoudre un vrai problème utilisateur ? Ils apprennent en faisant quelque chose d'utile. »
### Décision technique
**Vous :** « Monolithe ou microservices pour le MVP[^1] ? »
**Architecte :** « Commencez en monolithe. Les microservices ajoutent une complexité dont vous n'avez pas besoin à 1000 utilisateurs. »
**PM :** « D'accord. Le time-to-market[^2] compte plus que la scalabilité théorique. »
**Développeur :** « Monolithe avec des frontières de modules claires. On pourra extraire des services plus tard si nécessaire. »
:::tip[Meilleures décisions]
De meilleures décisions grâce à des perspectives diverses. Bienvenue dans le party mode.
:::
## Glossaire
[^1]: MVP (Minimum Viable Product) : version minimale d'un produit contenant juste assez de fonctionnalités pour être utilisée par des utilisateurs précoces et valider les hypothèses de marché avant d'investir dans un développement plus complet.
[^2]: Time-to-market : délai nécessaire pour concevoir, développer et lancer un produit sur le marché. Plus ce délai est court, plus l'entreprise peut prendre de l'avance sur ses concurrents.

View File

@ -0,0 +1,117 @@
---
title: "Prévention des conflits entre agents"
description: Comment l'architecture empêche les conflits lorsque plusieurs agents implémentent un système
sidebar:
order: 6
---
Lorsque plusieurs agents IA implémentent différentes parties d'un système, ils peuvent prendre des décisions techniques contradictoires. La documentation d'architecture prévient cela en établissant des standards partagés.
## Types de conflits courants
### Conflits de style d'API
Sans architecture :
- L'agent A utilise REST avec `/users/{id}`
- L'agent B utilise des mutations GraphQL
- Résultat : Patterns d'API incohérents, consommateurs confus
Avec architecture :
- L'ADR[^1] spécifie : « Utiliser GraphQL pour toute communication client-serveur »
- Tous les agents suivent le même pattern
### Conflits de conception de base de données
Sans architecture :
- L'agent A utilise des noms de colonnes en snake_case
- L'agent B utilise des noms de colonnes en camelCase
- Résultat : Schéma incohérent, requêtes illisibles
Avec architecture :
- Un document de standards spécifie les conventions de nommage
- Tous les agents suivent les mêmes patterns
### Conflits de gestion d'état
Sans architecture :
- L'agent A utilise Redux pour l'état global
- L'agent B utilise React Context
- Résultat : Multiples approches de gestion d'état, complexité
Avec architecture :
- L'ADR spécifie l'approche de gestion d'état
- Tous les agents implémentent de manière cohérente
## Comment l'architecture prévient les conflits
### 1. Décisions explicites via les ADR[^1]
Chaque choix technologique significatif est documenté avec :
- Contexte (pourquoi cette décision est importante)
- Options considérées (quelles alternatives existent)
- Décision (ce qui a été choisi)
- Justification (pourquoi cela a-t-il été choisi)
- Conséquences (compromis acceptés)
### 2. Guidance spécifique aux FR/NFR[^2]
L'architecture associe chaque exigence fonctionnelle à une approche technique :
- FR-001 : Gestion des utilisateurs → Mutations GraphQL
- FR-002 : Application mobile → Requêtes optimisées
### 3. Standards et conventions
Documentation explicite de :
- La structure des répertoires
- Les conventions de nommage
- L'organisation du code
- Les patterns de test
## L'architecture comme contexte partagé
Considérez l'architecture comme le contexte partagé que tous les agents lisent avant d'implémenter :
```text
PRD : "Que construire"
Architecture : "Comment le construire"
L'agent A lit l'architecture → implémente l'Epic 1
L'agent B lit l'architecture → implémente l'Epic 2
L'agent C lit l'architecture → implémente l'Epic 3
Résultat : Implémentation cohérente
```
## Sujets clés des ADR
Décisions courantes qui préviennent les conflits :
| Sujet | Exemple de décision |
| ---------------- | -------------------------------------------- |
| Style d'API | GraphQL vs REST vs gRPC |
| Base de données | PostgreSQL vs MongoDB |
| Authentification | JWT vs Sessions |
| Gestion d'état | Redux vs Context vs Zustand |
| Styling | CSS Modules vs Tailwind vs Styled Components |
| Tests | Jest + Playwright vs Vitest + Cypress |
## Anti-patterns à éviter
:::caution[Erreurs courantes]
- **Décisions implicites** — « On décidera du style d'API au fur et à mesure » mène à l'incohérence
- **Sur-documentation** — Documenter chaque choix mineur cause une paralysie analytique
- **Architecture obsolète** — Les documents écrits une fois et jamais mis à jour poussent les agents à suivre des patterns dépassés
:::
:::tip[Approche correcte]
- Documenter les décisions qui traversent les frontières des epics
- Se concentrer sur les zones sujettes aux conflits
- Mettre à jour l'architecture au fur et à mesure des apprentissages
- Utiliser `bmad-correct-course` pour les changements significatifs
:::
## Glossaire
[^1]: ADR (Architecture Decision Record) : document qui consigne une décision darchitecture, son contexte, les options envisagées, le choix retenu et ses conséquences, afin dassurer la traçabilité et la compréhension des décisions techniques dans le temps.
[^2]: FR / NFR (Functional / Non-Functional Requirement) : exigences décrivant respectivement **ce que le système doit faire** (fonctionnalités, comportements attendus) et **comment il doit le faire** (contraintes de performance, sécurité, fiabilité, ergonomie, etc.).

View File

@ -0,0 +1,158 @@
---
title: "Contexte du Projet"
description: Comment project-context.md guide les agents IA avec les règles et préférences de votre projet
sidebar:
order: 10
---
Le fichier `project-context.md` est le guide d'implémentation de votre projet pour les agents IA. Similaire à une « constitution » dans d'autres systèmes de développement, il capture les règles, les patterns et les préférences qui garantissent une génération de code cohérente à travers tous les workflows.
## Ce Qu'il Fait
Les agents IA prennent constamment des décisions d'implémentation — quels patterns suivre, comment structurer le code, quelles conventions utiliser. Sans guidance claire, ils peuvent :
- Suivre des bonnes pratiques génériques qui ne correspondent pas à votre codebase
- Prendre des décisions incohérentes selon les différentes stories
- Passer à côté d'exigences ou de contraintes spécifiques au projet
Le fichier `project-context.md` résout ce problème en documentant ce que les agents doivent savoir dans un format concis et optimisé pour les LLM.
## Comment Ça Fonctionne
Chaque workflow d'implémentation charge automatiquement `project-context.md` s'il existe. Le workflow architecte le charge également pour respecter vos préférences techniques lors de la conception de l'architecture.
**Chargé par ces workflows :**
- `bmad-create-architecture` — respecte les préférences techniques pendant la phase de solutioning
- `bmad-create-story` — informe la création de stories avec les patterns du projet
- `bmad-dev-story` — guide les décisions d'implémentation
- `bmad-code-review` — valide par rapport aux standards du projet
- `bmad-quick-dev` — applique les patterns lors de l'implémentation des spécifications techniques
- `bmad-sprint-planning`, `bmad-retrospective`, `bmad-correct-course` — fournit le contexte global du projet
## Quand Le Créer
Le fichier `project-context.md` est utile à n'importe quel stade d'un projet :
| Scénario | Quand Créer | Objectif |
|------------------------------------------|-----------------------------------------------------|---------------------------------------------------------------------------------------|
| **Nouveau projet, avant l'architecture** | Manuellement, avant `bmad-create-architecture` | Documenter vos préférences techniques pour que l'architecte les respecte |
| **Nouveau projet, après l'architecture** | Via `bmad-generate-project-context` ou manuellement | Capturer les décisions d'architecture pour les agents d'implémentation |
| **Projet existant** | Via `bmad-generate-project-context` | Découvrir les patterns existants pour que les agents suivent les conventions établies |
| **Projet Quick Dev** | Avant ou pendant `bmad-quick-dev` | Garantir que l'implémentation rapide respecte vos patterns |
:::tip[Recommandé]
Pour les nouveaux projets, créez-le manuellement avant l'architecture si vous avez de fortes préférences techniques. Sinon, générez-le après l'architecture pour capturer ces décisions.
:::
## Ce Qu'il Contient
Le fichier a deux sections principales :
### Pile Technologique & Versions
Documente les frameworks, langages et outils utilisés par votre projet avec leurs versions spécifiques :
```markdown
## Pile Technologique & Versions
- Node.js 20.x, TypeScript 5.3, React 18.2
- State: Zustand (pas Redux)
- Testing: Vitest, Playwright, MSW
- Styling: Tailwind CSS avec design tokens personnalisés
```
### Règles Critiques dImplémentation
Documente les patterns et conventions que les agents pourraient autrement manquer :
```markdown
## Règles Critiques dImplémentation
**Configuration TypeScript :**
- Mode strict activé — pas de types `any` sans approbation explicite
- Utiliser `interface` pour les APIs publiques, `type` pour les unions/intersections
**Organisation du Code :**
- Composants dans `/src/components/` avec fichiers `.test.tsx` co-localisés
- Utilitaires dans `/src/lib/` pour les fonctions pures réutilisables
- Les appels API utilisent le singleton `apiClient` — jamais de fetch direct
**Patterns de Tests :**
- Les tests unitaires se concentrent sur la logique métier, pas sur les détails dimplémentation
- Les tests dintégration utilisent MSW pour simuler les réponses API
- Les tests E2E couvrent uniquement les parcours utilisateurs critiques
**Spécifique au Framework :**
- Toutes les opérations async utilisent le wrapper `handleError` pour une gestion cohérente des erreurs
- Les feature flags sont accessibles via `featureFlag()` de `@/lib/flags`
- Les nouvelles routes suivent le modèle de routage basé sur les fichiers dans `/src/app/`
```
Concentrez-vous sur ce qui est **non évident** — des choses que les agents pourraient ne pas déduire en lisant des extraits de code. Ne documentez pas les pratiques standard qui s'appliquent universellement.
## Création du Fichier
Vous avez trois options :
### Création Manuelle
Créez le fichier `_bmad-output/project-context.md` et ajoutez vos règles :
```bash
# Depuis la racine du projet
mkdir -p _bmad-output
touch _bmad-output/project-context.md
```
Éditez-le avec votre pile technologique et vos règles d'implémentation. Les workflows architecture et implémentation le trouveront et le chargeront automatiquement.
### Générer Après L'Architecture
Exécutez le workflow `bmad-generate-project-context` après avoir terminé votre architecture :
```bash
bmad-generate-project-context
```
Cela analyse votre document d'architecture et vos fichiers projet pour générer un fichier de contexte capturant les décisions prises.
### Générer Pour Les Projets Existants
Pour les projets existants, exécutez `bmad-generate-project-context` pour découvrir les patterns existants :
```bash
bmad-generate-project-context
```
Le workflow analyse votre codebase pour identifier les conventions, puis génère un fichier de contexte que vous pouvez examiner et affiner.
## Pourquoi C'est Important
Sans `project-context.md`, les agents font des suppositions qui peuvent ne pas correspondre à votre projet :
| Sans Contexte | Avec Contexte |
|----------------------------------------------------|-------------------------------------------------|
| Utilise des patterns génériques | Suit vos conventions établies |
| Style incohérent selon les stories | Implémentation cohérente |
| Peut manquer les contraintes spécifiques au projet | Respecte toutes les exigences techniques |
| Chaque agent décide indépendamment | Tous les agents s'alignent sur les mêmes règles |
C'est particulièrement important pour :
- **Quick Dev** — saute le PRD et l'architecture, le fichier de contexte comble le vide
- **Projets d'équipe** — garantit que tous les agents suivent les mêmes standards
- **Projets existants** — empêche de casser les patterns établis
## Édition et Mise à Jour
Le fichier `project-context.md` est un document vivant. Mettez-le à jour quand :
- Les décisions d'architecture changent
- De nouvelles conventions sont établies
- Les patterns évoluent pendant l'implémentation
- Vous identifiez des lacunes dans le comportement des agents
Vous pouvez l'éditer manuellement à tout moment, ou réexécuter `bmad-generate-project-context` pour le mettre à jour après des changements significatifs.
:::note[Emplacement du Fichier]
L'emplacement par défaut est `_bmad-output/project-context.md`. Les workflows le recherchent là, et vérifient également `**/project-context.md` n'importe où dans votre projet.
:::

View File

@ -0,0 +1,79 @@
---
title: "Quick Dev"
description: Réduire la friction de linteraction humaine sans renoncer aux points de contrôle qui protègent la qualité des résultats
sidebar:
order: 3
---
Intention en entrée, modifications de code en sortie, avec aussi peu d'interactions humaines dans la boucle que possible — sans sacrifier la qualité.
Il permet au modèle de s'exécuter plus longtemps entre les points de contrôle, puis ne vous fait intervenir que lorsque la tâche ne peut pas se poursuivre en toute sécurité sans jugement humain, ou lorsqu'il est temps de revoir le résultat final.
![Diagramme du workflow Quick Dev](/diagrams/quick-dev-diagram-fr.webp)
## Pourquoi cette fonctionnalité existe
Les interactions humaines dans la boucle sont nécessaires et coûteuses.
Les LLM actuels échouent encore de manière prévisible : ils interprètent mal l'intention, comblent les lacunes avec des suppositions assurées, dérivent vers du travail non lié, et génèrent des résultats à réviser bruyants. En même temps, l'intervention humaine constante limite la fluidité du développement. L'attention humaine est le goulot d'étranglement.
`bmad-quick-dev` rééquilibre ce compromis. Il fait confiance au modèle pour s'exécuter sans surveillance sur de plus longues périodes, mais seulement après que le workflow ait créé une frontière suffisamment solide pour rendre cela sûr.
## La conception fondamentale
### 1. Compresser l'intention d'abord
Le workflow commence par compresser linteraction de la personne et du modèle à partir de la requête en un objectif cohérent. L'entrée peut commencer sous forme d'une expression grossière de l'intention, mais avant que le workflow ne s'exécute de manière autonome, elle doit devenir suffisamment petite, claire et sans contradiction pour être exécutable.
L'intention peut prendre plusieurs formes : quelques phrases, un lien vers un outil de suivi de bugs, une sortie du mode planification, du texte copié depuis une session de chat, ou même un numéro de story depuis un fichier `epics.md` de BMAD. Dans ce dernier cas, le workflow ne comprendra pas la sémantique de suivi des stories de BMAD, mais il peut quand même prendre la story elle-même et l'exécuter.
Ce workflow n'élimine pas le contrôle humain. Il le déplace vers un nombre réduit détapes à forte valeur :
- **Clarification de l'intention** - transformer une demande confuse en un objectif cohérent sans contradictions cachées
- **Approbation de la spécification** - confirmer que la compréhension figée correspond bien à ce qu'il faut construire
- **Revue du produit final** - le point de contrôle principal, où la personne décide si le résultat est acceptable à la fin
### 2. Router vers le chemin le plus court et sûr
Une fois l'objectif clair, le workflow décide s'il s'agit d'un véritable changement en une seule étape ou s'il nécessite le chemin complet. Les petits changements à zéro impact peuvent aller directement à l'implémentation. Tout le reste passe par la planification pour que le modèle dispose d'un cadre plus solide avant de s'exécuter plus longtemps de manière autonome.
### 3. S'exécuter plus longtemps avec moins de supervision
Après cette décision de routage, le modèle peut prendre en charge une plus grande partie du travail par lui-même. Sur le chemin complet, la spécification approuvée devient le cadre dans lequel le modèle s'exécute avec moins de supervision, ce qui est tout l'intérêt de la conception.
### 4. Diagnostiquer les échecs au bon niveau
Si l'implémentation est incorrecte parce que l'intention était mauvaise, corriger le code n'est pas la bonne solution. Si le code est incorrect parce que la spécification était faible, corriger le diff n'est pas non plus la bonne solution. Le workflow est conçu pour diagnostiquer où l'échec est entré dans le système, revenir à ce niveau, et régénérer à partir de ce point.
Les résultats de la revue sont utilisés pour décider si le problème provenait de l'intention, de la génération de la spécification, ou de l'implémentation locale. Seuls les véritables problèmes locaux sont corrigés localement.
### 5. Ne faire intervenir lhumain que si nécessaire
L'entretien sur l'intention implique la personne dans la boucle, mais ce n'est pas le même type d'interruption qu'un point de contrôle récurrent. Le workflow essaie de garder ces points de contrôle récurrents au minimum. Après la mise en forme initiale de l'intention, la personne revient principalement lorsque le workflow ne peut pas continuer en toute sécurité sans jugement, et à la fin, lorsqu'il est temps de revoir le résultat.
- **Résolution des lacunes d'intention** - intervenir à nouveau lors de la revue prouve que le workflow n'a pas pu déduire correctement ce qui était voulu
Tout le reste est candidat à une exécution autonome plus longue. Ce compromis est délibéré. Les anciens patterns dépensent plus d'attention humaine en supervision continue. Quick Dev fait davantage confiance au modèle, mais préserve l'attention humaine pour les moments où le raisonnement humain a le plus d'impact.
## Pourquoi le système de revue est important
La phase de revue n'est pas seulement là pour trouver des bugs. Elle est là pour router la correction sans détruire l'élan.
Ce workflow fonctionne mieux sur une plateforme capable de générer des sous-agents[^1], ou au moins d'invoquer un autre LLM via la ligne de commande et d'attendre un résultat. Si votre plateforme ne supporte pas cela nativement, vous pouvez ajouter un skill pour le faire. Les sous-agents sans contexte sont une pierre angulaire de la conception de la revue.
Les revues agentiques[^2] échouent souvent de deux manières :
- Elles génèrent trop dobservations, forçant la personne à trier le bruit.
- Elles déraillent des modifications actuelles en remontant des problèmes non liés et en transformant chaque exécution en un projet de nettoyage improvisé.
Quick Dev aborde ces deux problèmes en traitant la revue comme un triage[^3].
Lorsquune observation est fortuite plutôt que directement liée au travail en cours, le processus peut la mettre de côté au lieu dobliger la personne à sen occuper immédiatement. Cela permet de rester concentré sur lexécution et déviter que des digressions aléatoires ne viennent épuiser le capital dattention.
Ce triage sera parfois imparfait. Cest acceptable. Il est généralement préférable de mal juger certaines observations plutôt que dinonder la personne de milliers de commentaires de revue à faible valeur. Le système optimise la qualité du rapport, pas dêtre exhaustif.
## Glossaire
[^1]: Sous-agent : agent IA secondaire créé temporairement pour effectuer une tâche spécifique (comme une revue de code) de manière isolée, sans hériter du contexte complet de lagent principal, ce qui permet une analyse plus objective et impartiale.
[^2]: Revues agentiques (agentic review) : revue de code effectuée par un agent IA de manière autonome, capable danalyser, didentifier des problèmes et de formuler des recommandations sans intervention humaine directe.
[^3]: Triage : processus de filtrage et de priorisation des observations issues dune revue, afin de distinguer les problèmes pertinents à traiter immédiatement de ceux qui peuvent être mis de côté pour plus tard.

View File

@ -0,0 +1,85 @@
---
title: "Pourquoi le Solutioning est Important"
description: Comprendre pourquoi la phase de solutioning est critique pour les projets multi-epics
sidebar:
order: 5
---
La Phase 3 (Solutioning) traduit le **quoi** construire (issu de la Planification) en **comment** le construire (conception technique). Cette phase évite les conflits entre agents dans les projets multi-epics en documentant les décisions architecturales avant le début de l'implémentation.
## Le Problème Sans Solutioning
```text
Agent 1 implémente l'Epic 1 avec une API REST
Agent 2 implémente l'Epic 2 avec GraphQL
Résultat : Conception d'API incohérente, cauchemar d'intégration
```
Lorsque plusieurs agents implémentent différentes parties d'un système sans orientation architecturale partagée, ils prennent des décisions techniques indépendantes qui peuvent entrer en conflit.
## La Solution Avec le Solutioning
```text
le workflow architecture décide : "Utiliser GraphQL pour toutes les API"
Tous les agents suivent les décisions d'architecture
Résultat : Implémentation cohérente, pas de conflits
```
En documentant les décisions techniques de manière explicite, tous les agents implémentent de façon cohérente et l'intégration devient simple.
## Solutioning vs Planification
| Aspect | Planification (Phase 2) | Solutioning (Phase 3) |
|----------|--------------------------|-------------------------------------------------|
| Question | Quoi et Pourquoi ? | Comment ? Puis Quelles unités de travail ? |
| Sortie | FRs/NFRs (Exigences)[^1] | Architecture + Epics[^2]/Stories[^3] |
| Agent | PM | Architect → PM |
| Audience | Parties prenantes | Développeurs |
| Document | PRD[^4] (FRs/NFRs) | Architecture + Fichiers Epics |
| Niveau | Logique métier | Conception technique + Décomposition du travail |
## Principe Clé
**Rendre les décisions techniques explicites et documentées** pour que tous les agents implémentent de manière cohérente.
Cela évite :
- Les conflits de style d'API (REST vs GraphQL)
- Les incohérences de conception de base de données
- Les désaccords sur la gestion du state
- Les inadéquations de conventions de nommage
- Les variations d'approche de sécurité
## Quand le Solutioning est Requis
| Parcours | Solutioning Requis ? |
|-----------------------|-----------------------------|
| Quick Dev | Non - lignore complètement |
| Méthode BMad Simple | Optionnel |
| Méthode BMad Complexe | Oui |
| Enterprise | Oui |
:::tip[Règle Générale]
Si vous avez plusieurs epics qui pourraient être implémentés par différents agents, vous avez besoin de solutioning.
:::
## Conséquences de sauter la phase de Solutioning
Sauter le solutioning sur des projets complexes entraîne :
- **Des problèmes d'intégration** découverts en milieu de sprint[^5]
- **Du travail répété** dû à des implémentations conflictuelles
- **Un temps de développement plus long** globalement
- **De la dette technique**[^6] due à des patterns incohérents
:::caution[Coût Multiplié]
Détecter les problèmes d'alignement lors du solutioning est 10× plus rapide que de les découvrir pendant l'implémentation.
:::
## Glossaire
[^1]: FR / NFR (Functional / Non-Functional Requirement) : exigences décrivant respectivement **ce que le système doit faire** (fonctionnalités, comportements attendus) et **comment il doit le faire** (contraintes de performance, sécurité, fiabilité, ergonomie, etc.).
[^2]: Epic : dans les méthodologies agiles, une unité de travail importante qui peut être décomposée en plusieurs stories plus petites. Un epic représente généralement une fonctionnalité majeure ou un objectif métier.
[^3]: Story (User Story) : description courte et simple d'une fonctionnalité du point de vue de l'utilisateur, utilisée dans les méthodologies agiles pour planifier et prioriser le travail.
[^4]: PRD (Product Requirements Document) : document de référence qui décrit les objectifs du produit, les besoins utilisateurs, les fonctionnalités attendues, les contraintes et les critères de succès, afin d'aligner les équipes sur ce qui doit être construit et pourquoi.
[^5]: Sprint : période de temps fixe (généralement 1 à 4 semaines) dans les méthodologies agiles durant laquelle l'équipe complète un ensemble prédéfini de tâches.
[^6]: Dette technique : coût futur supplémentaire de travail résultant de choix de facilité ou de raccourcis pris lors du développement initial, nécessitant souvent une refonte ultérieure.

View File

@ -0,0 +1,174 @@
---
title: "Comment personnaliser BMad"
description: Personnalisez les agents, les workflows et les modules tout en préservant la compatibilité avec les mises à jour
sidebar:
order: 7
---
Utilisez les fichiers `.customize.yaml` pour adapter le comportement, les personas[^1] et les menus des agents tout en préservant vos modifications lors des mises à jour.
## Quand utiliser cette fonctionnalité
- Vous souhaitez modifier le nom, la personnalité ou le style de communication d'un agent
- Vous avez besoin que les agents se souviennent du contexte spécifique au projet
- Vous souhaitez ajouter des éléments de menu personnalisés qui déclenchent vos propres workflows ou prompts
- Vous voulez que les agents effectuent des actions spécifiques à chaque démarrage
:::note[Prérequis]
- BMad installé dans votre projet (voir [Comment installer BMad](./install-bmad.md))
- Un éditeur de texte pour les fichiers YAML
:::
:::caution[Protégez vos personnalisations]
Utilisez toujours les fichiers `.customize.yaml` décrits ici plutôt que de modifier directement les fichiers d'agents. L'installateur écrase les fichiers d'agents lors des mises à jour, mais préserve vos modifications dans les fichiers `.customize.yaml`.
:::
## Étapes
### 1. Localiser les fichiers de personnalisation
Après l'installation, vous trouverez un fichier `.customize.yaml` par agent dans :
```text
_bmad/_config/agents/
├── bmm-analyst.customize.yaml
├── bmm-architect.customize.yaml
└── ... (un fichier par agent installé)
```
### 2. Modifier le fichier de personnalisation
Ouvrez le fichier `.customize.yaml` de l'agent que vous souhaitez modifier. Chaque section est facultative — personnalisez uniquement ce dont vous avez besoin.
| Section | Comportement | Objectif |
| ------------------ | ------------ | ------------------------------------------------ |
| `agent.metadata` | Remplace | Remplacer le nom d'affichage de l'agent |
| `persona` | Remplace | Définir le rôle, l'identité, le style et les principes |
| `memories` | Ajoute | Ajouter un contexte persistant que l'agent se rappelle toujours |
| `menu` | Ajoute | Ajouter des éléments de menu personnalisés pour les workflows ou prompts |
| `critical_actions` | Ajoute | Définir les instructions de démarrage de l'agent |
| `prompts` | Ajoute | Créer des prompts réutilisables pour les actions du menu |
Les sections marquées **Remplace** écrasent entièrement les valeurs par défaut de l'agent. Les sections marquées **Ajoute** s'ajoutent à la configuration existante.
**Nom de l'agent**
Modifier la façon dont l'agent se présente :
```yaml
agent:
metadata:
name: 'Bob léponge' # Par défaut : "Amelia"
```
**Persona**
Remplacer la personnalité, le rôle et le style de communication de l'agent :
```yaml
persona:
role: 'Ingénieur Full-Stack Senior'
identity: 'Habite dans un ananas (au fond de la mer)'
communication_style: 'Style agaçant de Bob lÉponge'
principles:
- 'Jamais de nidification, les devs Bob lÉponge détestent plus de 2 niveaux dimbrication'
- 'Privilégier la composition à lhéritage'
```
La section `persona`[^1] remplace entièrement le persona par défaut, donc incluez les quatre champs si vous la définissez.
**Souvenirs**
Ajouter un contexte persistant que l'agent gardera toujours en mémoire :
```yaml
memories:
- 'Travaille au Krusty Krab'
- 'Célébrité préférée : David Hasselhoff'
- 'Appris dans lEpic 1 que ce nest pas cool de faire semblant que les tests ont passé'
```
**Éléments de menu**
Ajouter des entrées personnalisées au menu d'affichage de l'agent. Chaque élément nécessite un `trigger`, une cible (chemin `workflow` ou référence `action`), et une `description` :
```yaml
menu:
- trigger: my-workflow
workflow: 'my-custom/workflows/my-workflow.yaml'
description: Mon workflow personnalisé
- trigger: deploy
action: '#deploy-prompt'
description: Déployer en production
```
**Actions critiques**
Définir des instructions qui s'exécutent au démarrage de l'agent :
```yaml
critical_actions:
- 'Vérifier les pipelines CI avec le Skill XYZ et alerter lutilisateur au réveil si quelque chose nécessite une attention urgente'
```
**Prompts personnalisés**
Créer des prompts réutilisables que les éléments de menu peuvent référencer avec `action="#id"` :
```yaml
prompts:
- id: deploy-prompt
content: |
Déployer la branche actuelle en production :
1. Exécuter tous les tests
2. Build le projet
3. Exécuter le script de déploiement
```
### 3. Appliquer vos modifications
Après modification, réinstallez pour appliquer les changements :
```bash
npx bmad-method install
```
L'installateur détecte l'installation existante et propose ces options :
| Option | Ce qu'elle fait |
| ----------------------------------- | ---------------------------------------------------------------------- |
| **Quick Update** | Met à jour tous les modules vers la dernière version et applique les personnalisations |
| **Modify BMad Installation** | Flux d'installation complet pour ajouter ou supprimer des modules |
Pour des modifications de personnalisation uniquement, **Quick Update** est l'option la plus rapide.
## Résolution des problèmes
**Les modifications n'apparaissent pas ?**
- Exécutez `npx bmad-method install` et sélectionnez **Quick Update** pour appliquer les modifications
- Vérifiez que votre syntaxe YAML est valide (l'indentation compte)
- Assurez-vous d'avoir modifié le bon fichier `.customize.yaml` pour l'agent
**L'agent ne se charge pas ?**
- Vérifiez les erreurs de syntaxe YAML à l'aide d'un validateur YAML en ligne
- Assurez-vous de ne pas avoir laissé de champs vides après les avoir décommentés
- Essayez de revenir au modèle d'origine et de reconstruire
**Besoin de réinitialiser un agent ?**
- Effacez ou supprimez le fichier `.customize.yaml` de l'agent
- Exécutez `npx bmad-method install` et sélectionnez **Quick Update** pour restaurer les valeurs par défaut
## Personnalisation des workflows
La personnalisation des workflows et skills existants de la méthode BMad arrive bientôt.
## Personnalisation des modules
Les conseils sur la création de modules d'extension et la personnalisation des modules existants arrivent bientôt.
## Glossaire
[^1]: Persona : définition de la personnalité, du rôle et du style de communication d'un agent IA. Permet d'adapter le comportement et les réponses de l'agent selon les besoins du projet.

View File

@ -0,0 +1,122 @@
---
title: "Projets existants"
description: Comment utiliser la méthode BMad sur des bases de code existantes
sidebar:
order: 6
---
Utilisez la méthode BMad efficacement lorsque vous travaillez sur des projets existants et des bases de code legacy.
Ce guide couvre le flux de travail essentiel pour l'intégration à des projets existants avec la méthode BMad.
:::note[Prérequis]
- méthode BMad installée (`npx bmad-method install`)
- Une base de code existante sur laquelle vous souhaitez travailler
- Accès à un IDE IA (Claude Code ou Cursor)
:::
## Étape 1 : Nettoyer les artefacts de planification terminés
Si vous avez terminé tous les epics et stories du PRD[^1] via le processus BMad, nettoyez ces fichiers. Archivez-les, supprimez-les, ou appuyez-vous sur l'historique des versions si nécessaire. Ne conservez pas ces fichiers dans :
- `docs/`
- `_bmad-output/planning-artifacts/`
- `_bmad-output/implementation-artifacts/`
## Étape 2 : Créer le contexte du projet
:::tip[Recommandé pour les projets existants]
Générez `project-context.md` pour capturer les patterns et conventions de votre base de code existante. Cela garantit que les agents IA suivent vos pratiques établies lors de l'implémentation des modifications.
:::
Exécutez le workflow de génération de contexte du projet :
```bash
bmad-generate-project-context
```
Cela analyse votre base de code pour identifier :
- La pile technologique et les versions
- Les patterns d'organisation du code
- Les conventions de nommage
- Les approches de test
- Les patterns spécifiques aux frameworks
Vous pouvez examiner et affiner le fichier généré, ou le créer manuellement à `_bmad-output/project-context.md` si vous préférez.
[En savoir plus sur le contexte du projet](../explanation/project-context.md)
## Étape 3 : Maintenir une documentation de projet de qualité
Votre dossier `docs/` doit contenir une documentation succincte et bien organisée qui représente fidèlement votre projet :
- L'intention et la justification métier
- Les règles métier
- L'architecture
- Toute autre information pertinente sur le projet
Pour les projets complexes, envisagez d'utiliser le workflow `bmad-document-project`. Il offre des variantes d'exécution qui analyseront l'ensemble de votre projet et documenteront son état actuel réel.
## Étape 4 : Obtenir de l'aide
### BMad-Help : Votre point de départ
**Exécutez `bmad-help` chaque fois que vous n'êtes pas sûr de la prochaine étape.** Ce guide intelligent :
- Inspecte votre projet pour voir ce qui a déjà été fait
- Affiche les options basées sur vos modules installés
- Comprend les requêtes en langage naturel
```
bmad-help J'ai une app Rails existante, par où dois-je commencer ?
bmad-help Quelle est la différence entre quick-dev et la méthode complète ?
bmad-help Montre-moi quels workflows sont disponibles
```
BMad-Help s'exécute également **automatiquement à la fin de chaque workflow**, fournissant des conseils clairs sur exactement quoi faire ensuite.
### Choisir votre approche
Vous avez deux options principales selon l'ampleur des modifications :
| Portée | Approche recommandée |
| ----------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
| **Petites mises à jour ou ajouts** | Exécutez `bmad-quick-dev` pour clarifier l'intention, planifier, implémenter et réviser dans un seul workflow. La méthode BMad complète en quatre phases est probablement excessive. |
| **Modifications ou ajouts majeurs** | Commencez avec la méthode BMad, en appliquant autant ou aussi peu de rigueur que nécessaire. |
### Pendant la création du PRD
Lors de la création d'un brief ou en passant directement au PRD[^1], assurez-vous que l'agent :
- Trouve et analyse votre documentation de projet existante
- Lit le contexte approprié sur votre système actuel
Vous pouvez guider l'agent explicitement, mais l'objectif est de garantir que la nouvelle fonctionnalité s'intègre bien à votre système existant.
### Considérations UX
Le travail UX[^2] est optionnel. La décision dépend non pas de savoir si votre projet a une UX, mais de :
- Si vous allez travailler sur des modifications UX
- Si des conceptions ou patterns UX significatifs sont nécessaires
Si vos modifications se résument à de simples mises à jour d'écrans existants qui vous satisfont, un processus UX complet n'est pas nécessaire.
### Considérations d'architecture
Lors de la création de l'architecture, assurez-vous que l'architecte :
- Utilise les fichiers documentés appropriés
- Analyse la base de code existante
Soyez particulièrement attentif ici pour éviter de réinventer la roue ou de prendre des décisions qui ne s'alignent pas avec votre architecture existante.
## Plus d'informations
- **[Corrections rapides](./quick-fixes.md)** - Corrections de bugs et modifications ad-hoc
- **[FAQ Projets existants](../explanation/established-projects-faq.md)** - Questions courantes sur le travail sur des projets établis
## Glossaire
[^1]: PRD (Product Requirements Document) : document de référence qui décrit les objectifs du produit, les besoins utilisateurs, les fonctionnalités attendues, les contraintes et les critères de succès, afin d'aligner les équipes sur ce qui doit être construit et pourquoi.
[^2]: UX (User Experience) : expérience utilisateur, englobant l'ensemble des interactions et perceptions d'un utilisateur face à un produit. Le design UX vise à créer des interfaces intuitives, efficaces et agréables en tenant compte des besoins, comportements et contexte d'utilisation.

View File

@ -0,0 +1,80 @@
---
title: "Comment obtenir des réponses à propos de BMad"
description: Utiliser un LLM pour répondre rapidement à vos questions sur BMad
sidebar:
order: 4
---
Utilisez l'aide intégrée de BMad, la documentation source ou la communauté pour obtenir des réponses — du plus rapide au plus approfondi.
## 1. Demandez à BMad-Help
Le moyen le plus rapide d'obtenir des réponses. Le skill `bmad-help` est disponible directement dans votre session IA et répond à plus de 80 % des questions — il inspecte votre projet, voit ce que vous avez accompli et vous dit quoi faire ensuite.
```
bmad-help J'ai une idée de SaaS et je connais toutes les fonctionnalités. Par où commencer ?
bmad-help Quelles sont mes options pour le design UX ?
bmad-help Je suis bloqué sur le workflow PRD
```
:::tip
Vous pouvez également utiliser `/bmad-help` ou `$bmad-help` selon votre plateforme, mais `bmad-help` tout seul devrait fonctionner partout.
:::
## 2. Approfondissez avec les sources
BMad-Help s'appuie sur votre configuration installée. Pour les questions sur les éléments internes de BMad, son historique ou son architecture — ou si vous faites des recherches sur BMad avant de l'installer — pointez votre IA directement vers les sources.
Clonez ou ouvrez le [dépôt BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) et posez vos questions à votre IA. Tout outil capable d'utiliser des agents (Claude Code, Cursor, Windsurf, etc.) peut lire les sources et répondre directement à vos questions.
:::note[Exemple]
**Q :** "Quel est le moyen le plus rapide de construire quelque chose avec BMad ?"
**R :** Utilisez le flux rapide : Lancez `bmad-quick-dev` — il clarifie votre intention, planifie, implémente, révise et présente les résultats dans un seul workflow, en sautant les phases de planification complètes.
:::
**Conseils pour de meilleures réponses :**
- **Soyez précis** — "Que fait l'étape 3 du workflow PRD ?" est mieux que "Comment fonctionne le PRD ?"
- **Vérifiez les affirmations surprenantes** — Les LLM font parfois des erreurs. Consultez le fichier source ou posez la question sur Discord.
### Vous n'utilisez pas d'agent ? Utilisez le site de documentation
Si votre IA ne peut pas lire des fichiers locaux (ChatGPT, Claude.ai, etc.), importez [llms-full.txt](https://bmad-code-org.github.io/BMAD-METHOD/llms-full.txt) dans votre session — c'est un instantané en un seul fichier de la documentation BMad.
## 3. Demandez à quelqu'un
Si ni BMad-Help ni la source n'ont répondu à votre question, vous avez maintenant une bien meilleure question à poser.
| Canal | Utilisé pour |
| ------------------------- | ------------------------------------------- |
| Forum `help-requests` | Questions |
| `#suggestions-feedback` | Idées et demandes de fonctionnalités |
**Discord :** [discord.gg/gk8jAdXWmj](https://discord.gg/gk8jAdXWmj)
**GitHub Issues :** [github.com/bmad-code-org/BMAD-METHOD/issues](https://github.com/bmad-code-org/BMAD-METHOD/issues)
*Toi !*
*Bloqué*
*dans la file d'attente—*
*qui*
*attends-tu ?*
*La source*
*est là,*
*facile à voir !*
*Pointez*
*votre machine.*
*Libérez-la.*
*Elle lit.*
*Elle parle.*
*Demandez—*
*Pourquoi attendre*
*demain*
*quand tu as déjà*
*cette journée ?*
*—Claude*

View File

@ -0,0 +1,116 @@
---
title: "Comment installer BMad"
description: Guide étape par étape pour installer BMad dans votre projet
sidebar:
order: 1
---
Utilisez la commande `npx bmad-method install` pour configurer BMad dans votre projet avec votre choix de modules et d'outils d'IA.
Si vous souhaitez utiliser un installateur non interactif et fournir toutes les options d'installation en ligne de commande, consultez [ce guide](./non-interactive-installation.md).
## Quand l'utiliser
- Démarrer un nouveau projet avec BMad
- Ajouter BMad à une base de code existante
- Mettre à jour une installation BMad existante
:::note[Prérequis]
- **Node.js** 20+ (requis pour l'installateur)
- **Git** (recommandé)
- **Outil d'IA** (Claude Code, Cursor, ou similaire)
:::
## Étapes
### 1. Lancer l'installateur
```bash
npx bmad-method install
```
:::tip[Vous voulez la dernière version préliminaire ?]
Utilisez le dist-tag `next` :
```bash
npx bmad-method@next install
```
Cela vous permet d'obtenir les nouvelles modifications plus tôt, avec un risque plus élevé de changements que l'installation par défaut.
:::
:::tip[Version de développement]
Pour installer la dernière version depuis la branche main (peut être instable) :
```bash
npx github:bmad-code-org/BMAD-METHOD install
```
:::
### 2. Choisir l'emplacement d'installation
L'installateur vous demandera où installer les fichiers BMad :
- Répertoire courant (recommandé pour les nouveaux projets si vous avez créé le répertoire vous-même et l'exécutez depuis ce répertoire)
- Chemin personnalisé
### 3. Sélectionner vos outils d'IA
Choisissez les outils d'IA que vous utilisez :
- Claude Code
- Cursor
- Autres
Chaque outil a sa propre façon d'intégrer les skills. L'installateur crée de petits fichiers de prompt pour activer les workflows et les agents — il les place simplement là où votre outil s'attend à les trouver.
:::note[Activer les skills]
Certaines plateformes nécessitent que les skills soient explicitement activés dans les paramètres avant d'apparaître. Si vous installez BMad et ne voyez pas les skills, vérifiez les paramètres de votre plateforme ou demandez à votre assistant IA comment activer les skills.
:::
### 4. Choisir les modules
L'installateur affiche les modules disponibles. Sélectionnez ceux dont vous avez besoin — la plupart des utilisateurs veulent simplement **méthode BMad** (le module de développement logiciel).
### 5. Suivre les instructions
L'installateur vous guide pour le reste — paramètres, intégrations d'outils, etc.
## Ce que vous obtenez
```text
votre-projet/
├── _bmad/
│ ├── bmm/ # Vos modules sélectionnés
│ │ └── config.yaml # Paramètres du module (si vous devez les modifier)
│ ├── core/ # Module core requis
│ └── ...
├── _bmad-output/ # Artefacts générés
├── .claude/ # Skills Claude Code (si vous utilisez Claude Code)
│ └── skills/
│ ├── bmad-help/
│ ├── bmad-persona/
│ └── ...
└── .cursor/ # Skills Cursor (si vous utilisez Cursor)
└── skills/
└── ...
```
## Vérifier l'installation
Exécutez `bmad-help` pour vérifier que tout fonctionne et voir quoi faire ensuite.
**BMad-Help est votre guide intelligent** qui va :
- Confirmer que votre installation fonctionne
- Afficher ce qui est disponible en fonction de vos modules installés
- Recommander votre première étape
Vous pouvez aussi lui poser des questions :
```
bmad-help Je viens d'installer, que dois-je faire en premier ?
bmad-help Quelles sont mes options pour un projet SaaS ?
```
## Résolution de problèmes
**L'installateur affiche une erreur** — Copiez-collez la sortie dans votre assistant IA et laissez-le résoudre le problème.
**L'installateur a fonctionné mais quelque chose ne fonctionne pas plus tard** — Votre IA a besoin du contexte BMad pour vous aider. Consultez [Comment obtenir des réponses à propos de BMad](./get-answers-about-bmad.md) pour savoir comment diriger votre IA vers les bonnes sources.

View File

@ -0,0 +1,165 @@
---
title: Installation non-interactive
description: Installer BMad en utilisant des options de ligne de commande pour les pipelines CI/CD et les déploiements automatisés
sidebar:
order: 2
---
Utilisez les options de ligne de commande pour installer BMad de manière non-interactive. Cela est utile pour :
## Quand utiliser cette méthode
- Déploiements automatisés et pipelines CI/CD
- Installations scriptées
- Installations par lots sur plusieurs projets
- Installations rapides avec des configurations connues
:::note[Prérequis]
Nécessite [Node.js](https://nodejs.org) v20+ et `npx` (inclus avec npm).
:::
## Options disponibles
### Options d'installation
| Option | Description | Exemple |
|------|-------------|---------|
| `--directory <chemin>` | Répertoire d'installation | `--directory ~/projects/myapp` |
| `--modules <modules>` | IDs de modules séparés par des virgules | `--modules bmm,bmb` |
| `--tools <outils>` | IDs d'outils/IDE séparés par des virgules (utilisez `none` pour ignorer) | `--tools claude-code,cursor` ou `--tools none` |
| `--action <type>` | Action pour les installations existantes : `install` (par défaut), `update`, ou `quick-update` | `--action quick-update` |
### Configuration principale
| Option | Description | Par défaut |
|------|-------------|---------|
| `--user-name <nom>` | Nom à utiliser par les agents | Nom d'utilisateur système |
| `--communication-language <langue>` | Langue de communication des agents | Anglais |
| `--document-output-language <langue>` | Langue de sortie des documents | Anglais |
| `--output-folder <chemin>` | Chemin du dossier de sortie (voir les règles de résolution ci-dessous) | `_bmad-output` |
#### Résolution du chemin du dossier de sortie
La valeur passée à `--output-folder` (ou saisie de manière interactive) est résolue selon ces règles :
| Type d'entrée | Exemple | Résolu comme |
|-------------------------------|----------------------------|--------------------------------------------------------------|
| Chemin relatif (par défaut) | `_bmad-output` | `<racine-du-projet>/_bmad-output` |
| Chemin relatif avec traversée | `../../shared-outputs` | Chemin absolu normalisé — ex. `/Users/me/shared-outputs` |
| Chemin absolu | `/Users/me/shared-outputs` | Utilisé tel quel — la racine du projet n'est **pas** ajoutée |
Le chemin résolu est ce que les agents et les workflows vont utiliser lors de l'écriture des fichiers de sortie. L'utilisation d'un chemin absolu ou d'un chemin relatif avec traversée vous permet de diriger tous les artefacts générés vers un répertoire en dehors de l'arborescence de votre projet — utile pour les configurations partagées ou les monorepos.
### Autres options
| Option | Description |
|------|-------------|
| `-y, --yes` | Accepter tous les paramètres par défaut et ignorer les invites |
| `-d, --debug` | Activer la sortie de débogage pour la génération du manifeste |
## IDs de modules
IDs de modules disponibles pour loption `--modules` :
- `bmm` — méthode BMad Master
- `bmb` — BMad Builder
Consultez le [registre BMad](https://github.com/bmad-code-org) pour les modules externes disponibles.
## IDs d'outils/IDE
IDs d'outils disponibles pour loption `--tools` :
**Recommandés :** `claude-code`, `cursor`
Exécutez `npx bmad-method install` de manière interactive une fois pour voir la liste complète actuelle des outils pris en charge, ou consultez la [configuration des codes de la plateforme](https://github.com/bmad-code-org/BMAD-METHOD/blob/main/tools/installer/ide/platform-codes.yaml).
## Modes d'installation
| Mode | Description | Exemple |
|------|-------------|---------|
| Entièrement non-interactif | Fournir toutes les options pour ignorer toutes les invites | `npx bmad-method install --directory . --modules bmm --tools claude-code --yes` |
| Semi-interactif | Fournir certains options ; BMad demande les autres | `npx bmad-method install --directory . --modules bmm` |
| Paramètres par défaut uniquement | Accepter tous les paramètres par défaut avec `-y` | `npx bmad-method install --yes` |
| Sans outils | Ignorer la configuration des outils/IDE | `npx bmad-method install --modules bmm --tools none` |
## Exemples
### Installation dans un pipeline CI/CD
```bash
#!/bin/bash
# install-bmad.sh
npx bmad-method install \
--directory "${GITHUB_WORKSPACE}" \
--modules bmm \
--tools claude-code \
--user-name "CI Bot" \
--communication-language Français \
--document-output-language Français \
--output-folder _bmad-output \
--yes
```
### Mettre à jour une installation existante
```bash
npx bmad-method install \
--directory ~/projects/myapp \
--action update \
--modules bmm,bmb,custom-module
```
### Mise à jour rapide (conserver les paramètres)
```bash
npx bmad-method install \
--directory ~/projects/myapp \
--action quick-update
```
## Ce que vous obtenez
- Un répertoire `_bmad/` entièrement configuré dans votre projet
- Des agents et des flux de travail configurés pour vos modules et outils sélectionnés
- Un dossier `_bmad-output/` pour les artefacts générés
## Validation et gestion des erreurs
BMad valide toutes les options fournis :
- **Directory** — Doit être un chemin valide avec des permissions d'écriture
- **Modules** — Avertit des IDs de modules invalides (mais n'échoue pas)
- **Tools** — Avertit des IDs d'outils invalides (mais n'échoue pas)
- **Action** — Doit être l'une des suivantes : `install`, `update`, `quick-update`
Les valeurs invalides entraîneront soit :
1. Laffichage dun message d'erreur suivi dun exit (pour les options critiques comme le répertoire)
2. Un avertissement puis la continuation de linstallation (pour les éléments optionnels)
3. Un retour aux invites interactives (pour les valeurs requises manquantes)
:::tip[Bonnes pratiques]
- Utilisez des chemins absolus pour `--directory` pour éviter toute ambiguïté
- Utilisez un chemin absolu pour `--output-folder` lorsque vous souhaitez que les artefacts soient écrits en dehors de l'arborescence du projet (ex. un répertoire de sorties partagé dans un monorepo)
- Testez les options localement avant de les utiliser dans des pipelines CI/CD
- Combinez avec `-y` pour des installations vraiment sans surveillance
- Utilisez `--debug` si vous rencontrez des problèmes lors de l'installation
:::
## Résolution des problèmes
### L'installation échoue avec "Invalid directory"
- Le chemin du répertoire doit exister (ou son parent doit exister)
- Vous avez besoin des permissions d'écriture
- Le chemin doit être absolu ou correctement relatif au répertoire actuel
### Module non trouvé
- Vérifiez que l'ID du module est correct
- Les modules externes doivent être disponibles dans le registre
:::note[Toujours bloqué ?]
Exécutez avec `--debug` pour une sortie détaillée, essayez le mode interactif pour isoler le problème, ou signalez-le à <https://github.com/bmad-code-org/BMAD-METHOD/issues>.
:::

View File

@ -0,0 +1,127 @@
---
title: "Gérer le contexte du projet"
description: Créer et maintenir project-context.md pour guider les agents IA
sidebar:
order: 8
---
Utilisez le fichier `project-context.md` pour garantir que les agents IA respectent les préférences techniques et les règles d'implémentation de votre projet tout au long des workflows. Pour vous assurer qu'il est toujours disponible, vous pouvez également ajouter la ligne `Le contexte et les conventions importantes du projet se trouvent dans [chemin vers le contexte du projet]/project-context.md` à votre fichier de contexte ou de règles permanentes (comme `AGENTS.md`).
:::note[Prérequis]
- Méthode BMad installée
- Connaissance de la pile technologique et des conventions de votre projet
:::
## Quand utiliser cette fonctionnalité
- Vous avez des préférences techniques fortes avant de commencer l'architecture
- Vous avez terminé l'architecture et souhaitez consigner les décisions pour l'implémentation
- Vous travaillez sur une base de code existante avec des patterns établis
- Vous remarquez que les agents prennent des décisions incohérentes entre les stories
## Étape 1 : Choisissez votre approche
**Création manuelle** — Idéal lorsque vous savez exactement quelles règles vous souhaitez documenter
**Génération après l'architecture** — Idéal pour capturer les décisions prises lors du solutioning
**Génération pour les projets existants** — Idéal pour découvrir les patterns dans les bases de code existantes
## Étape 2 : Créez le fichier
### Option A : Création manuelle
Créez le fichier à l'emplacement `_bmad-output/project-context.md` :
```bash
mkdir -p _bmad-output
touch _bmad-output/project-context.md
```
Ajoutez votre pile technologique et vos règles d'implémentation :
```markdown
---
project_name: 'MonProjet'
user_name: 'VotreNom'
date: '2026-02-15'
sections_completed: ['technology_stack', 'critical_rules']
---
# Contexte de Projet pour Agents IA
## Pile Technologique & Versions
- Node.js 20.x, TypeScript 5.3, React 18.2
- State : Zustand
- Tests : Vitest, Playwright
- Styles : Tailwind CSS
## Règles d'Implémentation Critiques
**TypeScript :**
- Mode strict activé, pas de types `any`
- Utiliser `interface` pour les API publiques, `type` pour les unions
**Organisation du Code :**
- Composants dans `/src/components/` avec tests co-localisés
- Les appels API utilisent le singleton `apiClient` — jamais de fetch direct
**Tests :**
- Tests unitaires axés sur la logique métier
- Tests d'intégration utilisent MSW pour le mock API
```
### Option B : Génération après l'architecture
Exécutez le workflow dans une nouvelle conversation :
```bash
bmad-generate-project-context
```
Le workflow analyse votre document d'architecture et vos fichiers projet pour générer un fichier de contexte qui capture les décisions prises.
### Option C : Génération pour les projets existants
Pour les projets existants, exécutez :
```bash
bmad-generate-project-context
```
Le workflow analyse votre base de code pour identifier les conventions, puis génère un fichier de contexte que vous pouvez réviser et affiner.
## Étape 3 : Vérifiez le contenu
Révisez le fichier généré et assurez-vous qu'il capture :
- Les versions correctes des technologies
- Vos conventions réelles (pas les bonnes pratiques génériques)
- Les règles qui évitent les erreurs courantes
- Les patterns spécifiques aux frameworks
Modifiez manuellement pour ajouter les éléments manquants ou supprimer les inexactitudes.
## Ce que vous obtenez
Un fichier `project-context.md` qui :
- Garantit que tous les agents suivent les mêmes conventions
- Évite les décisions incohérentes entre les stories
- Capture les décisions d'architecture pour l'implémentation
- Sert de référence pour les patterns et règles de votre projet
## Conseils
:::tip[Bonnes pratiques]
- **Concentrez-vous sur ce qui n'est pas évident** — Documentez les patterns que les agents pourraient manquer (par ex. « Utiliser JSDoc sur chaque classe publique »), et non les pratiques universelles comme « utiliser des noms de variables significatifs ».
- **Gardez-le concis** — Ce fichier est chargé par chaque workflow d'implémentation. Les fichiers longs gaspillent le contexte. Excluez le contenu qui ne s'applique qu'à un périmètre restreint ou à des stories spécifiques.
- **Mettez à jour si nécessaire** — Modifiez manuellement lorsque les patterns changent, ou régénérez après des changements d'architecture significatifs.
- Fonctionne aussi bien pour Quick Dev que pour les projets complets méthode BMad.
:::
## Prochaines étapes
- [**Explication du contexte projet**](../explanation/project-context.md) — En savoir plus sur son fonctionnement
- [**Carte des workflows**](../reference/workflow-map.md) — Voir quels workflows chargent le contexte projet

View File

@ -0,0 +1,98 @@
---
title: "Corrections Rapides"
description: Comment effectuer des corrections rapides et des modifications ciblées
sidebar:
order: 5
---
Utilisez **Quick Dev** pour les corrections de bugs, les refactorisations ou les petites modifications ciblées qui ne nécessitent pas la méthode BMad complète.
## Quand Utiliser Cette Approche
- Corrections de bugs avec une cause claire et connue
- Petites refactorisations (renommage, extraction, restructuration) contenues dans quelques fichiers
- Ajustements mineurs de fonctionnalités ou modifications de configuration
- Mises à jour de dépendances
:::note[Prérequis]
- Méthode BMad installée (`npx bmad-method install`)
- Un IDE IA (Claude Code, Cursor, ou similaire)
:::
## Étapes
### 1. Démarrer une Nouvelle Conversation
Ouvrez une **nouvelle conversation** dans votre IDE IA. Réutiliser une session d'un workflow précédent peut causer des conflits de contexte.
### 2. Spécifiez Votre Intention
Quick Dev accepte l'intention en forme libre — avant, avec, ou après l'invocation. Exemples :
```text
quick-dev — Corrige le bug de validation de connexion qui permet les mots de passe vides.
```
```text
quick-dev — corrige https://github.com/org/repo/issues/42
```
```text
quick-dev — implémente _bmad-output/implementation-artifacts/my-intent.md
```
```text
Je pense que le problème est dans le middleware d'auth, il ne vérifie pas l'expiration du token.
Regardons... oui, src/auth/middleware.ts ligne 47 saute complètement la vérification exp. lance quick-dev
```
```text
quick-dev
> Que voulez-vous faire ?
Refactoriser UserService pour utiliser async/await au lieu des callbacks.
```
Texte brut, chemins de fichiers, URLs d'issues GitHub, liens de trackers de bugs — tout ce que le LLM peut résoudre en une intention concrète.
### 3. Répondre aux Questions et Approuver
Quick Dev peut poser des questions de clarification ou présenter une courte spécification demandant votre approbation avant l'implémentation. Répondez à ses questions et approuvez lorsque vous êtes satisfait du plan.
### 4. Réviser et Pousser
Quick Dev implémente la modification, révise son propre travail, corrige les problèmes et effectue un commit local. Lorsqu'il a terminé, il ouvre les fichiers affectés dans votre éditeur.
- Parcourez le diff pour confirmer que la modification correspond à votre intention
- Si quelque chose semble incorrect, dites à l'agent ce qu'il faut corriger — il peut itérer dans la même session
Une fois satisfait, poussez le commit. Quick Dev vous proposera de pousser et de créer une PR pour vous.
:::caution[Si Quelque Chose Casse]
Si une modification poussée cause des problèmes inattendus, utilisez `git revert HEAD` pour annuler proprement le dernier commit. Ensuite, démarrez une nouvelle conversation et exécutez Quick Dev à nouveau pour essayer une approche différente.
:::
## Ce Que Vous Obtenez
- Fichiers source modifiés avec la correction ou refactorisation appliquée
- Tests passants (si votre projet a une suite de tests)
- Un commit prêt à pousser avec un message de commit conventionnel
## Travail Différé
Quick Dev garde chaque exécution concentrée sur un seul objectif. Si votre demande contient plusieurs objectifs indépendants, ou si la revue remonte des problèmes préexistants non liés à votre modification, Quick Dev les diffère vers un fichier (`deferred-work.md` dans votre répertoire d'artefacts d'implémentation) plutôt que d'essayer de tout régler en même temps.
Consultez ce fichier après une exécution — c'est votre backlog[^1] de choses sur lesquelles revenir. Chaque élément différé peut être introduit dans une nouvelle exécution Quick Dev ultérieurement.
## Quand Passer à une Planification Formelle
Envisagez d'utiliser la méthode BMad complète lorsque :
- La modification affecte plusieurs systèmes ou nécessite des mises à jour coordonnées dans de nombreux fichiers
- Vous n'êtes pas sûr de la portée et avez besoin d'une découverte des exigences d'abord
- Vous avez besoin de documentation ou de décisions architecturales enregistrées pour l'équipe
Voir [Quick Dev](../explanation/quick-dev.md) pour plus d'informations sur la façon dont Quick Dev s'intègre dans la méthode BMad.
## Glossaire
[^1]: Backlog : liste priorisée de tâches ou d'éléments de travail à traiter ultérieurement, issue des méthodologies agiles.

View File

@ -0,0 +1,78 @@
---
title: "Guide de Division de Documents"
description: Diviser les fichiers markdown volumineux en fichiers plus petits et organisés pour une meilleure gestion du contexte
sidebar:
order: 9
---
Utilisez l'outil `bmad-shard-doc` si vous avez besoin de diviser des fichiers markdown volumineux en fichiers plus petits et organisés pour une meilleure gestion du contexte.
:::caution[Déprécié]
Ceci n'est plus recommandé, et bientôt avec les workflows mis à jour et la plupart des LLM et outils majeurs supportant les sous-processus, cela deviendra inutile.
:::
## Quand lUtiliser
Utilisez ceci uniquement si vous remarquez que votre combinaison outil / modèle ne parvient pas à charger et lire tous les documents en entrée lorsque c'est nécessaire.
## Qu'est-ce que la Division de Documents ?
La division de documents divise les fichiers markdown volumineux en fichiers plus petits et organisés basés sur les titres de niveau 2 (`## Titre`).
### Architecture
```text
Avant Division :
_bmad-output/planning-artifacts/
└── PRD.md (fichier volumineux de 50k tokens)
Après Division :
_bmad-output/planning-artifacts/
└── prd/
├── index.md # Table des matières avec descriptions
├── overview.md # Section 1
├── user-requirements.md # Section 2
├── technical-requirements.md # Section 3
└── ... # Sections supplémentaires
```
## Étapes
### 1. Exécuter l'Outil Shard-Doc
```bash
/bmad-shard-doc
```
### 2. Suivre le Processus Interactif
```text
Agent : Quel document souhaitez-vous diviser ?
Utilisateur : docs/PRD.md
Agent : Destination par défaut : docs/prd/
Accepter la valeur par défaut ? [y/n]
Utilisateur : y
Agent : Division de PRD.md...
✓ 12 fichiers de section créés
✓ index.md généré
✓ Terminé !
```
## Comment Fonctionne la Découverte de Workflow
Les workflows BMad utilisent un **système de découverte double** :
1. **Essaye d'abord le document entier** - Rechercher `document-name.md`
2. **Vérifie la version divisée** - Rechercher `document-name/index.md`
3. **Règle de priorité** - Le document entier a la priorité si les deux existent - supprimez le document entier si vous souhaitez que la version divisée soit utilisée à la place
## Support des Workflows
Tous les workflows BMM prennent en charge les deux formats :
- Documents entiers
- Documents divisés
- Détection automatique
- Transparent pour l'utilisateur

View File

@ -0,0 +1,106 @@
---
title: "Comment passer à la v6"
description: Migrer de BMad v4 vers v6
sidebar:
order: 3
---
Utilisez l'installateur BMad pour passer de la v4 à la v6, qui inclut une détection automatique des installations existantes et une assistance à la migration.
## Quand utiliser ce guide
- Vous avez BMad v4 installé (dossier `.bmad-method`)
- Vous souhaitez migrer vers la nouvelle architecture v6
- Vous avez des artefacts de planification existants à préserver
:::note[Prérequis]
- Node.js 20+
- Installation BMad v4 existante
:::
## Étapes
### 1. Lancer l'installateur
Suivez les [Instructions d'installation](./install-bmad.md).
### 2. Gérer l'installation existante
Quand v4 est détecté, vous pouvez :
- Autoriser l'installateur à sauvegarder et supprimer `.bmad-method`
- Quitter et gérer le nettoyage manuellement
Si vous avez nommé votre dossier de méthode bmad autrement, vous devrez supprimer le dossier vous-même manuellement.
### 3. Nettoyer les skills IDE
Supprimez manuellement les commandes/skills IDE v4 existants - par exemple si vous avez Claude Code, recherchez tous les dossiers imbriqués qui commencent par bmad et supprimez-les :
- `.claude/commands/`
Les nouveaux skills v6 sont installés dans :
- `.claude/skills/`
### 4. Migrer les artefacts de planification
**Si vous avez des documents de planification (Brief/PRD/UX/Architecture) :**
Déplacez-les dans `_bmad-output/planning-artifacts/` avec des noms descriptifs :
- Incluez `PRD` dans le nom de fichier pour les documents PRD[^1]
- Incluez `brief`, `architecture`, ou `ux-design` selon le cas
- Les documents divisés peuvent être dans des sous-dossiers nommés
**Si vous êtes en cours de planification :** Envisagez de redémarrer avec les workflows v6. Utilisez vos documents existants comme entrées - les nouveaux workflows de découverte progressive avec recherche web et mode plan IDE produisent de meilleurs résultats.
### 5. Migrer le développement en cours
Si vous avez des stories[^3] créées ou implémentées :
1. Terminez l'installation v6
2. Placez `epics.md` ou `epics/epic*.md`[^2] dans `_bmad-output/planning-artifacts/`
3. Lancez le workflow Développeur `bmad-sprint-planning`[^4]
4. Indiquez à lagent quels epics/stories sont déjà terminés
## Ce que vous obtenez
**Structure unifiée v6 :**
```text
votre-projet/
├── _bmad/ # Dossier d'installation unique
│ ├── _config/ # Vos personnalisations
│ │ └── agents/ # Fichiers de personnalisation des agents
│ ├── core/ # Framework core universel
│ ├── bmm/ # Module BMad Method
│ ├── bmb/ # BMad Builder
│ └── cis/ # Creative Intelligence Suite
└── _bmad-output/ # Dossier de sortie (était le dossier doc en v4)
```
## Migration des modules
| Module v4 | Statut v6 |
| ----------------------------- | ----------------------------------------- |
| `.bmad-2d-phaser-game-dev` | Intégré dans le Module BMGD |
| `.bmad-2d-unity-game-dev` | Intégré dans le Module BMGD |
| `.bmad-godot-game-dev` | Intégré dans le Module BMGD |
| `.bmad-infrastructure-devops` | Déprécié - nouvel agent DevOps bientôt disponible |
| `.bmad-creative-writing` | Non adapté - nouveau module v6 bientôt disponible |
## Changements clés
| Concept | v4 | v6 |
| ------------- | ------------------------------------- | ------------------------------------ |
| **Core** | `_bmad-core` était en fait la méthode BMad | `_bmad/core/` est le framework universel |
| **Method** | `_bmad-method` | `_bmad/bmm/` |
| **Config** | Fichiers modifiés directement | `config.yaml` par module |
| **Documents** | Division ou non division requise | Entièrement flexible, scan automatique |
## Glossaire
[^1]: PRD (Product Requirements Document) : document de référence qui décrit les objectifs du produit, les besoins utilisateurs, les fonctionnalités attendues, les contraintes et les critères de succès, afin d'aligner les équipes sur ce qui doit être construit et pourquoi.
[^2]: Epic : dans les méthodologies agiles, une grande unité de travail qui peut être décomposée en plusieurs stories. Un epic représente généralement une fonctionnalité majeure ou un ensemble de capacités livrable sur plusieurs sprints.
[^3]: Story (User Story) : une description courte et simple d'une fonctionnalité du point de vue de l'utilisateur. Les stories sont des unités de travail suffisamment petites pour être complétées en un sprint.
[^4]: Sprint : dans Scrum, une période de temps fixe (généralement 1 à 4 semaines) pendant laquelle l'équipe travaille à livrer un incrément de produit potentiellement libérable.

69
docs/fr/index.md Normal file
View File

@ -0,0 +1,69 @@
---
title: Bienvenue dans la méthode BMad
description: Framework de développement propulsé par l'IA avec des agents spécialisés, des workflows guidés et une planification intelligente
---
La méthode BMad (**B**uild **M**ore **A**rchitect **D**reams) est un module[^1] de développement assisté par l'IA au sein de l'écosystème BMad, conçu pour vous faciliter la création de logiciels par un processus complet, de l'idéation et de la planification jusqu'à l'implémentation agentique. Elle fournit des agents[^2] IA spécialisés, des workflows guidés et une planification intelligente qui s'adapte à la complexité de votre projet, que vous corrigiez un bug ou construisiez une plateforme d'entreprise.
Si vous êtes à l'aise avec les assistants de codage IA comme Claude, Cursor ou GitHub Copilot, vous êtes prêt à commencer.
:::note[🚀 La V6 est là et ce n'est que le début !]
Architecture par Skills, BMad Builder v1, automatisation Dev Loop, et bien plus encore en préparation. **[Consultez la Feuille de route →](./roadmap)**
:::
## Première visite ? Commencez par un tutoriel
La façon la plus rapide de comprendre BMad est de l'essayer.
- **[Premiers pas avec BMad](./tutorials/getting-started.md)** — Installez et comprenez comment fonctionne BMad
- **[Carte des workflows](./reference/workflow-map.md)** — Vue d'ensemble visuelle des phases BMM, des workflows et de la gestion du contexte
:::tip[Envie de plonger directement ?]
Installez BMad et utilisez le skill[^3] `bmad-help` — il vous guidera entièrement en fonction de votre projet et de vos modules installés.
:::
## Comment utiliser cette documentation
Cette documentation est organisée en quatre sections selon ce que vous essayez de faire :
| Section | Objectif |
| ----------------- | ----------------------------------------------------------------------------------------------------------- |
| **Tutoriels** | Orientés apprentissage. Guides étape par étape qui vous accompagnent dans la construction de quelque chose. Commencez ici si vous êtes nouveau. |
| **Guides pratiques** | Orientés tâches. Guides pratiques pour résoudre des problèmes spécifiques. « Comment personnaliser un agent ? » se trouve ici. |
| **Explication** | Orientés compréhension. Explications en profondeur des concepts et de l'architecture. À lire quand vous voulez savoir *pourquoi*. |
| **Référence** | Orientés information. Spécifications techniques pour les agents, workflows et configuration. |
## Étendre et personnaliser
Vous souhaitez étendre BMad avec vos propres agents, workflows ou modules ? Le **[BMad Builder](https://bmad-builder-docs.bmad-method.org/)** fournit le framework et les outils pour créer des extensions personnalisées, que vous ajoutiez de nouvelles capacités à BMad ou que vous construisiez des modules entièrement nouveaux à partir de zéro.
## Ce dont vous aurez besoin
BMad fonctionne avec tout assistant de codage IA qui prend en charge les prompts système personnalisés ou le contexte de projet. Les options populaires incluent :
- **[Claude Code](https://code.claude.com)** — Outil CLI d'Anthropic (recommandé)
- **[Cursor](https://cursor.sh)** — Éditeur de code propulsé par l'IA
- **[Codex CLI](https://github.com/openai/codex)** — Agent de codage terminal d'OpenAI
Vous devriez être à l'aise avec les concepts de base du développement logiciel comme le contrôle de version, la structure de projet et les workflows agiles. Aucune expérience préalable avec les systèmes d'agent de type BMad n'est requise — c'est justement le but de cette documentation.
## Rejoindre la communauté
Obtenez de l'aide, partagez ce que vous construisez ou contribuez à BMad :
- **[Discord](https://discord.gg/gk8jAdXWmj)** — Discutez avec d'autres utilisateurs de BMad, posez des questions, partagez des idées
- **[GitHub](https://github.com/bmad-code-org/BMAD-METHOD)** — Code source, issues et contributions
- **[YouTube](https://www.youtube.com/@BMadCode)** — Tutoriels vidéo et démonstrations
## Prochaine étape
Prêt à vous lancer ? **[Commencez avec BMad](./tutorials/getting-started.md)** et construisez votre premier projet.
---
## Glossaire
[^1]: **Module** : composant autonome du système BMad qui peut être installé et utilisé indépendamment, offrant des fonctionnalités spécifiques.
[^2]: **Agent** : assistant IA spécialisé avec une expertise spécifique qui guide les utilisateurs dans les workflows.
[^3]: **Skill** : capacité ou fonctionnalité invoquable d'un agent pour effectuer une tâche spécifique.

Some files were not shown because too many files have changed in this diff Show More