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>
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>
* 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>
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>
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>
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>
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>
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>
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>
- 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>
- 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>
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>
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>
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>
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>
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
)
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>
- 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>
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>
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>
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>
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>
Alex Verkhovsky
Brian
JasonYe
github-actions[bot]
梁山河
leon