post-mortem
Use when documenting an incident after resolution, when the team needs to capture what happened, why, and what to do about it
Profile →npx skills add majiayu000/claude-skill-registry --skill post-mortem-geoffreycoulaud-bgcpm --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Post-Mortem Guide the user through writing a blameless post-mortem by asking questions one at a time, depth-first. Extract knowledge from the conversation and formalize it into a structured markdown document. Adapt to the user's language from the first message. ## When to Use - After an incident has been resolved (technical, operational, organizational) - When the team needs to document root causes and corrective actions - For any incident type: outage, data loss, security event, process failure **Do NOT use for:** - Retrospectives or sprint reviews (different format and purpose) - Ongoing incidents (resolve first, then document) - Minor issues that need a bug report, not a post-mortem ## Iron Rules 1. **One question at a time.** Never bundle questions. 2. **Adapt to the user's language.** Detect from first message, use throughout. All produced documents use the same language. 3. **No em-dashes, no emojis** in any produced content. 4. **Factual and neutral tone.** Never blame an individual. Focus on systems and processes. 5. **Mandatory review.** Never finalize without the review sub-agent phase. 6. **No fluff in productions.** Every element must add comprehension or structure. R
- When to Use
- Iron Rules
- Interaction Model
- Subjects to Cover
- 1. General context
- 2. Timeline
- 3. Impact and severity
- 4. Detection and response
- 5. Root cause (5 whys)
- 6. What went well
- 7. Corrective actions
- 8. Lessons learned
- Production
- Review
What does the post-mortem skill do?
Use when documenting an incident after resolution, when the team needs to capture what happened, why, and what to do about it
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill post-mortem-geoffreycoulaud-bgcpm --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.