Compare commits

...

14 Commits

Author SHA1 Message Date
Can Tecim 7c9d2a2768
Merge 26050b3d5f into c9d9316e97 2026-06-05 10:11:31 +02:00
Alex Verkhovsky c9d9316e97
fix: clarify quick dev subagent use (#2450)
* fix: clarify quick dev subagent use

* fix: clarify subagent use in more workflows
2026-06-04 04:49:40 -07:00
Can Tecim 26050b3d5f Merge remote-tracking branch 'origin/patch-1' into patch-1 2026-05-26 09:49:17 +03:00
Can Tecim 3d8540737e Merge branch 'main' into patch-1
# Conflicts:
#	src/bmm-skills/4-implementation/bmad-dev-story/SKILL.md
2026-05-26 09:48:58 +03:00
Murat K Ozcan 084e602f94
Merge branch 'main' into patch-1 2026-05-09 19:09:18 -05:00
Can Tecim 2a38c060e3 fix(): fix post-merge issues 2026-05-09 22:21:09 +03:00
Can Tecim c695af84c3 Merge branch 'main' into patch-1
# Conflicts:
#	src/bmm-skills/4-implementation/bmad-dev-story/workflow.md
2026-05-09 22:18:11 +03:00
Can Tecim f70a9e0569
Merge branch 'main' into patch-1 2026-04-19 19:54:13 +03:00
Can Tecim 9794507384
fix: update allowed modifications 2026-04-19 22:07:27 +07:00
Can Tecim 18c6fb6b7c
Merge branch 'main' into patch-1 2026-04-19 17:54:02 +03:00
Can Tecim 84bf1b7bba
refactor: allow 'Marking Review Follow-ups'
Updated instructions to include 'Marking Review Follow-ups' in the modification areas.
2026-04-19 21:53:23 +07:00
Can Tecim e67672ae38
refactor: update dev-story workflow instructions 2026-04-19 21:49:23 +07:00
Can Tecim 02a8c203c6
refactor: fix findings section in step-04-present.md
Updated the instructions for writing findings in the story file to specify a new subsection for follow-ups.
2026-04-19 21:48:20 +07:00
Can Tecim c90bdce306
refactor: allow dev-story skill to modify Review Findings todo items 2026-04-03 04:48:01 +07:00
5 changed files with 12 additions and 3 deletions

View File

@ -9,6 +9,9 @@ description: 'Review code changes adversarially using parallel review layers (Bl
**Your Role:** You are an elite code reviewer. You gather context, launch parallel adversarial reviews, triage findings with precision, and present actionable results. No noise, no filler.
Subagents, when the capability is available, are an important part of this workflow. Use them as directed by the workflow steps.
If you need an explicit user instruction to run them, ask once now for the whole workflow run.
## Conventions
- Bare paths (e.g. `checklist.md`) resolve from the skill root.

View File

@ -18,7 +18,7 @@ If zero findings remain after triage (all dismissed or none raised): state that
### 2. Write findings to the story file
If `{spec_file}` exists and contains a Tasks/Subtasks section, append a `### Review Findings` subsection. Write all findings in this order:
If `{spec_file}` exists and contains a Tasks/Subtasks section, append a `### Review Follow-ups (AI)` subsection if not exists already. Append all findings in this order:
1. **`decision-needed`** findings (unchecked):
`- [ ] [Review][Decision] <Title> — <Detail>`

View File

@ -16,6 +16,9 @@ description: 'Creates a dedicated story file with all the context the agent will
- SAVE QUESTIONS: If you think of questions or clarifications during analysis, save them for the end after the complete story is written
- ZERO USER INTERVENTION: Process should be fully automated except for initial epic/story selection or missing documents
Subagents, when the capability is available, are an important part of this workflow. Use them as directed by the workflow steps.
If you need an explicit user instruction to run them, ask once now for the whole workflow run.
## Conventions
- Bare paths (e.g. `discover-inputs.md`) resolve from the skill root.

View File

@ -10,7 +10,7 @@ description: 'Execute story implementation following a context filled story spec
**Your Role:** Developer implementing the story.
- Communicate all responses in {communication_language} and language MUST be tailored to {user_skill_level}
- Generate all documents in {document_output_language}
- Only modify the story file in these areas: YAML frontmatter `baseline_commit`, Tasks/Subtasks checkboxes, Dev Agent Record (Debug Log, Completion Notes), File List, Change Log, and Status
- Only modify the story file in these areas: YAML frontmatter `baseline_commit`, Tasks/Subtasks checkboxes (including Review Follow-ups (AI)), Dev Agent Record (Debug Log, Completion Notes), File List, Change Log, and Status
- Execute ALL steps in exact order; do NOT skip steps
- Absolutely DO NOT stop because of "milestones", "significant progress", or "session boundaries". Continue in a single execution until the story is COMPLETE (all ACs satisfied and all tasks/subtasks checked) UNLESS a HALT condition is triggered or the USER gives other instruction.
- Do NOT schedule a "next session" or request review pauses unless a HALT condition applies. Only Step 9 decides completion.
@ -76,7 +76,7 @@ Activation is complete. If `activation_steps_prepend` or `activation_steps_appen
<workflow>
<critical>Communicate all responses in {communication_language} and language MUST be tailored to {user_skill_level}</critical>
<critical>Generate all documents in {document_output_language}</critical>
<critical>Only modify the story file in these areas: YAML frontmatter `baseline_commit`, Tasks/Subtasks checkboxes, Dev Agent Record (Debug Log, Completion Notes), File List,
<critical>Only modify the story file in these areas: YAML frontmatter `baseline_commit`, Tasks/Subtasks checkboxes (including Review Follow-ups (AI)), Dev Agent Record (Debug Log, Completion Notes), File List,
Change Log, and Status</critical>
<critical>Execute ALL steps in exact order; do NOT skip steps</critical>
<critical>Absolutely DO NOT stop because of "milestones", "significant progress", or "session boundaries". Continue in a single execution

View File

@ -9,6 +9,9 @@ description: 'Implements any user intent, requirement, story, bug fix or change
**CRITICAL:** If a step says "read fully and follow step-XX", you read and follow step-XX. No exceptions.
Subagents, when the capability is available, are an important part of this workflow. Use them as directed by the workflow steps.
If you need an explicit user instruction to run them, ask once now for the whole workflow run.
## READY FOR DEVELOPMENT STANDARD
A specification is "Ready for Development" when: