From bmad-cowork
This skill activates when the user asks about "story creation", "sprint planning", "story development cycle", "story validation", "code review workflow", "dev story", "create next story", "story template", or needs guidance on BMAD's implementation workflow patterns.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bmad-cowork:bmad-workflowThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Every BMAD story lives in `docs/stories/` and follows a standard template with these sections:
Every BMAD story lives in docs/stories/ and follows a standard template with these sections:
Stories are numbered by epic and sequence: story-E1.S1.md, story-E1.S2.md, etc.
The implementation phase runs a repeating cycle for each story:
Bob reads the PRD and architecture docs, then:
James picks up the next Ready story, then:
Quinn picks up In Review stories, then:
If QA Fail:
Before implementation begins, bob-sm plans the sprint:
docs/prd.mdEach agent can only edit specific sections of a story file:
| Agent | Can Edit |
|---|---|
| bob-sm | Story, Acceptance Criteria, Tasks, Dev Notes, Status (to Ready) |
| james-dev | Tasks (checkboxes), Dev Agent Record, Status (to In Review) |
| quinn-qa | QA Results, Status (to QA Pass or QA Fail) |
No agent should modify sections owned by another agent except through the defined handoff (status change).
Before a story is marked Ready, bob-sm validates:
James-dev should NOT begin a story if:
When blocked, james-dev should message bob-sm via SendMessage to resolve the blocker.
npx claudepluginhub vamfi/vamfi-plugins --plugin bmad-coworkGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.