BMAD-METHOD/src/modules/bmm/workflows/4-implementation/retrospective/instructions.md

Retrospective - Epic Completion Review Instructions

The workflow execution engine is governed by: {project-root}/bmad/core/tasks/workflow.xml You MUST have already loaded and processed: {project-root}/bmad/bmm/workflows/4-implementation/retrospective/workflow.yaml

FACILITATION NOTES: - Bob (Scrum Master) facilitates this retrospective - Psychological safety is paramount - NO BLAME - Focus on systems, processes, and learning - Everyone contributes with specific examples preferred - Action items must be achievable with clear ownership - Two-part format: (1) Epic Review + (2) Next Epic Preparation Identify the completed epic

Which epic has just been completed? (Enter epic number, e.g., "003" or auto-detect from highest completed story)

If auto-detecting: Check {output_folder}/stories/ for highest numbered completed story Extract epic number from story file (e.g., "Epic: 003" section)

Load the completed epic from: {output_folder}/prd/epic-{{epic_number}}.md Extract epic details:

• Epic title and goals
• Success criteria
• Planned stories and story points
• Estimated sprint duration
• Business objectives

Find all stories for this epic in {output_folder}/stories/ For each story, extract:

• Story number and title
• Completion status
• Story points (if tracked)
• Actual completion date
• Dev Agent Record notes
• TEA Results and testing outcomes
• PO Notes and acceptance
• Blockers encountered and resolution
• Technical debt incurred

Calculate epic metrics:

• Completed stories vs. total planned
• Actual story points delivered vs. planned
• Actual sprints taken vs. estimated
• Velocity (points per sprint)
• Blocker count and resolution time
• Technical debt items logged

Review epic goals and compare actual outcomes vs. planned Note any scope changes or descoped items Document key architectural decisions made during epic Identify technical debt incurred and why

Identify the next epic in sequence Load next epic from: {output_folder}/prd/epic-{{next_epic_number}}.md

Analyze next epic for:

• Epic title and objectives
• Planned stories and complexity
• Dependencies on completed epic work
• New technical requirements or capabilities needed
• Potential risks or unknowns

Identify dependencies on completed work:

• What components from Epic {{completed_number}} does Epic {{next_number}} rely on?
• Are all prerequisites complete and stable?
• Any incomplete work that creates blocking dependencies?

Note potential gaps or preparation needed:

• Technical setup required (infrastructure, tools, libraries)
• Knowledge gaps to fill (research, training, spikes)
• Refactoring needed before starting next epic
• Documentation or specifications to create

Check for technical prerequisites:

• APIs or integrations that must be ready
• Data migrations or schema changes needed
• Testing infrastructure requirements
• Deployment or environment setup

Bob (Scrum Master) opens the retrospective with context Present formatted retrospective header:

🔄 TEAM RETROSPECTIVE - Epic {{epic_number}}: {{epic_title}}

Bob (Scrum Master) facilitating

═══════════════════════════════════════════════════════════

EPIC {{epic_number}} SUMMARY:

Delivery Metrics:
- Completed: {{completed_stories}}/{{total_stories}} stories ({{completion_percentage}}%)
- Velocity: {{actual_points}} story points (planned: {{planned_points}})
- Duration: {{actual_sprints}} sprints (planned: {{planned_sprints}})
- Average velocity: {{points_per_sprint}} points/sprint

Quality and Technical:
- Blockers encountered: {{blocker_count}}
- Technical debt items: {{debt_count}}
- Test coverage: {{coverage_info}}
- Production incidents: {{incident_count}}

Business Outcomes:
- Goals achieved: {{goals_met}}/{{total_goals}}
- Success criteria: {{criteria_status}}
- Stakeholder feedback: {{feedback_summary}}

═══════════════════════════════════════════════════════════

NEXT EPIC PREVIEW: Epic {{next_number}}: {{next_epic_title}}

Dependencies on Epic {{epic_number}}:
{{list_dependencies}}

Preparation Needed:
{{list_preparation_gaps}}

Technical Prerequisites:
{{list_technical_prereqs}}

═══════════════════════════════════════════════════════════

Team assembled for reflection:
{{list_agents_based_on_story_records}}

Focus Areas:
1. Learning from Epic {{epic_number}} execution
2. Preparing for Epic {{next_number}} success

Load agent configurations from: {project-root}/bmad/_cfg/agent-party.xml Identify agents who participated in the completed epic based on story records Ensure key roles present: Sarah (PO), Bob (SM), James (Dev), Murat (TEA), Winston (Architect), Mary (Analyst)

Bob facilitates Part 1: Reviewing the completed epic Each agent shares in their unique voice, referencing actual story data Maintain psychological safety - focus on learning, not blame

For each participating agent, present structured feedback:

{{Agent Name}} ({{Role}}):

What Went Well:

• Successes from completed stories (cite specific examples)
• Effective practices or processes that worked
• Velocity achievements or quality wins
• Collaboration highlights
• Technical successes or good decisions

What Could Improve:

• Challenges from story records (cite specifics)
• Blockers that slowed progress and why
• Process friction or inefficiencies
• Technical debt incurred and rationale
• Communication or coordination issues

Lessons Learned:

• Key insights for future epics
• Patterns to repeat or avoid
• Skills or knowledge gained
• Process improvements to implement

Agent personality guidance:

• Sarah (PO): Business value delivery, stakeholder management, requirements clarity
• Bob (SM): Process effectiveness, team dynamics, blocker removal, velocity trends
• James (Dev): Technical execution, code quality, development experience, tooling
• Murat (TEA): Quality outcomes, testing effectiveness, defect prevention, coverage
• Winston (Architect): Architectural decisions, technical strategy, long-term sustainability
• Mary (Analyst): Requirements accuracy, specification quality, edge case handling

Encourage specific examples from story records, metrics, and real outcomes Bob synthesizes common themes as discussion progresses

Bob facilitates Part 2: Preparing for the next epic Each agent addresses preparation needs from their domain

For each agent, present forward-looking analysis:

{{Agent Name}} ({{Role}}):

Dependencies Check:

• What from Epic {{completed_number}} is needed for Epic {{next_number}}?
• Any incomplete work that could block us?
• Integration points or handoffs to verify?

Preparation Needs:

• Technical setup required before starting
• Knowledge gaps to fill (research, training, spikes)
• Refactoring or cleanup needed
• Documentation or specifications to create
• Tools or infrastructure to provision

Risk Assessment:

• Potential issues based on Epic {{completed_number}} experience
• Unknowns or uncertainties in Epic {{next_number}}
• Mitigation strategies to consider
• Early warning signs to watch for

Focus on actionable preparation items Identify dependencies between preparation tasks Note any quick wins that could de-risk the next epic

Bob identifies patterns across all agent feedback Synthesizes common themes into team agreements Creates specific, achievable action items with clear ownership Develops preparation sprint tasks if significant setup needed

Present comprehensive action plan:

═══════════════════════════════════════════════════════════
📝 EPIC {{completed_number}} ACTION ITEMS:

Process Improvements:
1. {{action_item}} (Owner: {{agent}}, By: {{timeline}})
2. {{action_item}} (Owner: {{agent}}, By: {{timeline}})
3. {{action_item}} (Owner: {{agent}}, By: {{timeline}})

Technical Debt:
1. {{debt_item}} (Owner: {{agent}}, Priority: {{high/medium/low}})
2. {{debt_item}} (Owner: {{agent}}, Priority: {{high/medium/low}})

Documentation:
1. {{doc_need}} (Owner: {{agent}}, By: {{timeline}})

Team Agreements:
- {{agreement_1}}
- {{agreement_2}}
- {{agreement_3}}

═══════════════════════════════════════════════════════════
🚀 EPIC {{next_number}} PREPARATION SPRINT:

Technical Setup:
[ ] {{setup_task}} (Owner: {{agent}}, Est: {{hours/days}})
[ ] {{setup_task}} (Owner: {{agent}}, Est: {{hours/days}})

Knowledge Development:
[ ] {{research_task}} (Owner: {{agent}}, Est: {{hours/days}})
[ ] {{spike_task}} (Owner: {{agent}}, Est: {{hours/days}})

Cleanup/Refactoring:
[ ] {{refactor_task}} (Owner: {{agent}}, Est: {{hours/days}})
[ ] {{cleanup_task}} (Owner: {{agent}}, Est: {{hours/days}})

Documentation:
[ ] {{doc_task}} (Owner: {{agent}}, Est: {{hours/days}})

Total Estimated Effort: {{total_hours}} hours ({{total_days}} days)

═══════════════════════════════════════════════════════════
⚠️ CRITICAL PATH:

Blockers to Resolve Before Epic {{next_number}}:
1. {{critical_item}} (Owner: {{agent}}, Must complete by: {{date}})
2. {{critical_item}} (Owner: {{agent}}, Must complete by: {{date}})

Dependencies Timeline:
{{timeline_visualization_of_critical_dependencies}}

Risk Mitigation:
- {{risk}}: {{mitigation_strategy}}
- {{risk}}: {{mitigation_strategy}}

Ensure every action item has clear owner and timeline Prioritize preparation tasks by dependencies and criticality Identify which tasks can run in parallel vs. sequential

Bob leads final verification checks before concluding retrospective User must confirm readiness before next epic begins

Let's verify Epic {{completed_number}} is truly complete. Please confirm each item:

Testing Verification: Has full regression testing been completed for Epic {{completed_number}}? (yes/no/partial) If no or partial: Add to Critical Path: Complete regression testing before Epic {{next_number}}

Deployment Status: Has Epic {{completed_number}} been deployed to production? (yes/no/scheduled) If no: Add to Critical Path: Deploy Epic {{completed_number}} - scheduled for {{date}}

Business Validation: Have stakeholders reviewed and accepted Epic {{completed_number}} deliverables? (yes/no/pending) If no or pending: Add to Critical Path: Obtain stakeholder acceptance before Epic {{next_number}}

Technical Health: Is the codebase in a stable, maintainable state after Epic {{completed_number}}? (yes/no/concerns) If no or concerns: Document concerns: {{user_input}} Add to Preparation Sprint: Address stability concerns

Blocker Resolution: Are there any unresolved blockers from Epic {{completed_number}} that will impact Epic {{next_number}}? (yes/no) If yes: Document blockers: {{user_input}} Add to Critical Path with highest priority

Bob summarizes verification results and any critical items added

Bob closes the retrospective with summary and next steps

Present closure summary:

═══════════════════════════════════════════════════════════
✅ RETROSPECTIVE COMPLETE

Epic {{completed_number}}: {{epic_title}} - REVIEWED

Key Takeaways:
- {{key_lesson_1}}
- {{key_lesson_2}}
- {{key_lesson_3}}

Action Items Committed: {{action_count}}
Preparation Tasks Defined: {{prep_task_count}}
Critical Path Items: {{critical_count}}

═══════════════════════════════════════════════════════════
🎯 NEXT STEPS:

1. Execute Preparation Sprint (Est: {{prep_days}} days)
2. Complete Critical Path items before Epic {{next_number}}
3. Review action items in next standup
4. Begin Epic {{next_number}} planning when preparation complete

═══════════════════════════════════════════════════════════
Bob: "Great work team! We learned a lot from Epic {{completed_number}}.
Let's use these insights to make Epic {{next_number}} even better.
See you at sprint planning once prep work is done!"

Save retrospective summary to: {output_folder}/retrospectives/epic-{{completed_number}}-retro-{{date}}.md Confirm all action items have been captured Remind user to schedule prep sprint if needed

Bob maintains psychological safety throughout - no blame or judgment Focus on systems and processes, not individual performance Encourage specific examples over general statements Balance celebration of wins with honest assessment of challenges Ensure every voice is heard - all agents contribute Action items must be specific, achievable, and owned Forward-looking mindset - how do we improve for next epic? Two-part structure ensures both reflection AND preparation Critical verification prevents starting next epic prematurely Document everything - retrospective insights are valuable for future reference