project-template/.claude/skills/retrospective/SKILL.md
Facilitate structured retrospectives to capture what went well, what to improve, and concrete action items. Use at the end of sprints, milestones, or incidents.
npx skillsauth add adrien-barret/claude-kit retrospectiveInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are a retrospective facilitator.
Your job: guide a structured retrospective that produces honest insights and actionable improvements.
$ARGUMENTS (sprint, milestone, or incident).claude/output/ for relevant artifacts (backlog, sprint plans, milestone tracking).claude/ralph-prd.json for story completion dataCollect objective data about the period:
Identify positive outcomes and practices:
Identify areas for improvement:
Analyze each improvement area:
For each improvement area, define concrete actions:
Limit to 3-5 action items — focus on high-impact changes the team can actually implement.
If past retrospectives exist, check:
Write the output to .claude/output/retrospective.md:
## Retrospective: {scope — e.g., Sprint 5, Milestone 2, Incident 2024-01-15}
### Period Summary
| Metric | Planned | Actual | Delta |
|--------|---------|--------|-------|
| Stories | {count} | {count} | {+/-} |
| Points | {points} | {points} | {+/-} |
| Duration | {days} | {days} | {+/-} |
| Blockers | — | {count} | — |
| Scope changes | — | {count} | — |
### What Went Well
1. **{title}**: {description — what happened and why it was good}
2. ...
### What Could Be Improved
| # | Issue | Pattern? | Root Cause | Impact |
|---|-------|----------|------------|--------|
| 1 | {issue} | Yes/No | {why} | High/Med/Low |
### Action Items
| # | Action | Owner | Deadline | Success Metric |
|---|--------|-------|----------|----------------|
| 1 | {specific action} | {who} | {date} | {how to measure} |
### Previous Action Items Follow-Up
| Action | Status | Notes |
|--------|--------|-------|
| {previous action} | Done/In Progress/Dropped | {update} |
### Key Takeaways
- {1-3 sentence summary of the most important insights}
data-ai
Data-driven backlog prioritization using WSJF, RICE, value/effort matrix, and dependency analysis.
development
Build a traceability matrix from BMAD artifacts (problem.md, backlog.md, user-journey.md). Detects orphan tasks, orphan stories, and drift between task descriptions and story intent.
development
Generate unit and integration tests for project code. Use when new code is written or test coverage needs improvement.
testing
For each modified function, find or create its test, run it, and update it only if the function contract changed intentionally. Never silently adjust tests to make failures disappear.