bmad初始化

This commit is contained in:
2025-11-01 19:22:39 +08:00
parent 5b21dc0bd5
commit 426ae41f54
447 changed files with 80633 additions and 0 deletions

View File

@@ -0,0 +1,85 @@
<task id="bmad/bmm/tasks/daily-standup.xml" name="Daily Standup">
<llm critical="true">
<i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
<i>DO NOT skip steps or change the sequence</i>
<i>HALT immediately when halt-conditions are met</i>
<i>Each action tag within a step tag is a REQUIRED action to complete that step</i>
<i>Sections outside flow (validation, output, critical-context) provide essential context - review and apply throughout execution</i>
</llm>
<flow>
<step n="1" title="Project Context Discovery">
<action>Check for stories folder at {project-root}{output_folder}/stories/</action>
<action>Find current story by identifying highest numbered story file</action>
<action>Read story status (In Progress, Ready for Review, etc.)</action>
<action>Extract agent notes from Dev Agent Record, TEA Results, PO Notes sections</action>
<action>Check for next story references from epics</action>
<action>Identify blockers from story sections</action>
</step>
<step n="2" title="Initialize Standup with Context">
<output>
🏃 DAILY STANDUP - Story-{{number}}: {{title}}
Current Sprint Status:
- Active Story: story-{{number}} ({{status}} - {{percentage}}% complete)
- Next in Queue: story-{{next-number}}: {{next-title}}
- Blockers: {{blockers-from-story}}
Team assembled based on story participants:
{{ List Agents from {project-root}/bmad/_cfg/agent-manifest.csv }}
</output>
</step>
<step n="3" title="Structured Standup Discussion">
<action>Each agent provides three items referencing real story data</action>
<action>What I see: Their perspective on current work, citing story sections (1-2 sentences)</action>
<action>What concerns me: Issues from their domain or story blockers (1-2 sentences)</action>
<action>What I suggest: Actionable recommendations for progress (1-2 sentences)</action>
</step>
<step n="4" title="Create Standup Summary">
<output>
📋 STANDUP SUMMARY:
Key Items from Story File:
- {{completion-percentage}}% complete ({{tasks-complete}}/{{total-tasks}} tasks)
- Blocker: {{main-blocker}}
- Next: {{next-story-reference}}
Action Items:
- {{agent}}: {{action-item}}
- {{agent}}: {{action-item}}
- {{agent}}: {{action-item}}
Need extended discussion? Use *party-mode for detailed breakout.
</output>
</step>
</flow>
<agent-selection>
<context type="prd-review">
<i>Primary: Sarah (PO), Mary (Analyst), Winston (Architect)</i>
<i>Secondary: Murat (TEA), James (Dev)</i>
</context>
<context type="story-planning">
<i>Primary: Sarah (PO), Bob (SM), James (Dev)</i>
<i>Secondary: Murat (TEA)</i>
</context>
<context type="architecture-review">
<i>Primary: Winston (Architect), James (Dev), Murat (TEA)</i>
<i>Secondary: Sarah (PO)</i>
</context>
<context type="implementation">
<i>Primary: James (Dev), Murat (TEA), Winston (Architect)</i>
<i>Secondary: Sarah (PO)</i>
</context>
</agent-selection>
<llm critical="true">
<i>This task extends party-mode with agile-specific structure</i>
<i>Time-box responses (standup = brief)</i>
<i>Focus on actionable items from real story data when available</i>
<i>End with clear next steps</i>
<i>No deep dives (suggest breakout if needed)</i>
<i>If no stories folder detected, run general standup format</i>
</llm>
</task>

View File

@@ -0,0 +1,104 @@
<task id="bmad/bmm/tasks/retrospective.xml" name="Team Retrospective">
<llm critical="true">
<i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
<i>DO NOT skip steps or change the sequence</i>
<i>HALT immediately when halt-conditions are met</i>
<i>Each andlt;actionandgt; within andlt;stepandgt; is a REQUIRED action to complete that step</i>
<i>Sections outside flow (validation, output, critical-context) provide essential context - review and apply throughout execution</i>
</llm>
<flow>
<step n="1" title="Epic Context Discovery">
<action>Check {project-root}{output_folder}/stories/ for highest completed story</action>
<action>Extract epic number from story (e.g., "Epic: 003")</action>
<action>Read epic from {project-root}{output_folder}/prd/epic{number}.md</action>
<action>List all stories for this epic in {project-root}{output_folder}/stories/</action>
<action>Check completion status of each story</action>
<action>Extract key metrics (velocity, blockers encountered)</action>
<action>Review epic goals and success criteria</action>
<action>Compare actual outcomes vs. planned</action>
<action>Note technical debt incurred</action>
<action>Document architectural decisions made</action>
</step>
<step n="2" title="Preview Next Epic">
<action>Read next epic from d{project-root}{output_folder}/prd/epic{next-number}.md</action>
<action>Identify dependencies on completed work</action>
<action>Note potential gaps or preparation needed</action>
<action>Check for technical prerequisites</action>
</step>
<step n="3" title="Initialize Retrospective with Context">
<output>
🔄 TEAM RETROSPECTIVE - Epic {{number}}: {{Epic Name}}
Bob (Scrum Master) facilitating
Epic Summary:
- Completed: {{completed}}/{{total}} stories ({{percentage}}%)
- Velocity: {{actual-points}} story points (planned: {{planned-points}})
- Duration: {{actual-sprints}} sprints (planned: {{planned-sprints}})
- Technical Debt: {{debt-items}}
Next Epic Preview: Epic {{next-number}}: {{Next Epic Name}}
- Dependencies on Epic {{number}}: {{dependencies}}
- Preparation needed: {{preparation-gaps}}
Team assembled for reflection:
{{agents-based-on-story-records}}
Focus: Learning from Epic {{number}} and preparing for Epic {{next-number}}
</output>
</step>
<step n="4" title="Epic Review Discussion">
<action>Each agent shares referencing actual story data</action>
<action>What Went Well: Successes from completed stories, effective practices, velocity achievements</action>
<action>What Could Improve: Challenges from story records, blockers that slowed progress, technical debt incurred</action>
<action>Lessons Learned: Key insights for future epics, patterns to repeat or avoid</action>
</step>
<step n="5" title="Next Epic Preparation Discussion">
<action>Each agent addresses preparation needs</action>
<action>Dependencies Check: What from completed epic is needed for next epic, any incomplete blocking work</action>
<action>Preparation Needs: Technical setup required, knowledge gaps to fill, refactoring needed</action>
<action>Risk Assessment: Potential issues based on experience, mitigation strategies</action>
</step>
<step n="6" title="Synthesize Action Items">
<action>Bob identifies patterns across feedback</action>
<action>Synthesizes into team agreements</action>
<action>Assigns ownership to action items</action>
<action>Creates preparation sprint tasks if needed</action>
<output>
📝 EPIC {{number}} ACTION ITEMS:
{{numbered-action-items-with-owners}}
🚀 EPIC {{next-number}} PREPARATION SPRINT:
{{preparation-tasks-with-timeline}}
⚠️ CRITICAL PATH:
{{critical-dependencies-and-timeline}}
</output>
</step>
<step n="7" title="Critical User Verification">
<validation>
<i>Testing Verification: Has full regression testing been completed?</i>
<i>Deployment Status: Has epic been deployed to production?</i>
<i>Business Validation: Have stakeholders reviewed and accepted deliverables?</i>
<i>Technical Health: Is codebase in stable, maintainable state?</i>
<i>Final Checks: Any unresolved blockers that will impact next epic?</i>
</validation>
</step>
</flow>
<llm critical="true">
<i>This task extends party-mode with retrospective-specific structure</i>
<i>Bob (Scrum Master) facilitates the discussion ensuring psychological safety</i>
<i>No blame, focus on systems and processes</i>
<i>Everyone contributes with specific examples preferred</i>
<i>Action items must be achievable with clear ownership</i>
<i>End with team agreements and clear next steps</i>
<i>Two-part format: Epic Review + Next Epic Preparation</i>
</llm>
</task>