Agent skill
retrospective
Learning from failures and successes, post-mortems, continuous improvement
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/retrospective-baphled-dotopencode
SKILL.md
Skill: retrospective
What I do
I manage the process of reflecting on past work to identify improvements. I facilitate blameless analysis of failures and capture successful patterns to ensure continuous improvement in the development process.
When to use me
- After completing a major feature or project
- Following a production incident (post-mortem)
- Periodically (e.g. every sprint) to refine team workflows
- When a recurring problem or friction point is identified
Core principles
- Blamelessness — Focus on system failures rather than individual mistakes. Assume everyone did the best they could with the information they had.
- Action-oriented — Every retrospective must produce specific, owner-assigned, and time-bound action items.
- Timeline reconstruction — For incidents, build a factual timeline before trying to identify causes.
- Distinguish root vs contributing — Use the "5 Whys" to dig past surface symptoms to the underlying system issue.
Patterns & examples
4Ls Format:
- Liked: What went well? (e.g. "The new CI pipeline saved us hours.")
- Learned: What new knowledge was gained? (e.g. "We learned that library X has a memory leak.")
- Lacked: What was missing? (e.g. "We lacked clear requirements for the edge cases.")
- Longed For: What do we want next time? (e.g. "I longed for more pair programming during the refactor.")
Root Cause Analysis (5 Whys Example):
- Problem: Deployment failed.
- Why? The database migration timed out.
- Why? It was trying to index a 100M row table.
- Why? We didn't test the migration on a production-sized dataset.
- Why? Our staging database is too small.
- Root Cause: Inadequate testing environments for production scale.
Anti-patterns to avoid
- ❌ Pointing fingers — Using the retro to air personal grievances or blame individuals.
- ❌ Retrospective amnesia — Identifying the same problems repeatedly without taking action.
- ❌ Skipping successes — Only focusing on what went wrong; it's equally important to know why things went well.
KB Reference
~/vaults/baphled/3. Resources/Knowledge Base/AI Development System/Skills/Thinking-Analysis/Retrospective.md
Related skills
critical-thinking— Analysing the findings of the retroassumption-tracker— Identifying assumptions that led to failuresystems-thinker— Understanding the system dynamics that led to issuesmemory-keeper— Capturing the "Learned" section for future sessions
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?