premortem
Analyze what could go wrong with a plan. Use when: - User asks "what could go wrong", "risks", "potential issues" - Before implementing a significant change - User wants to validate an approach - Planning a risky operation
npx skills add majiayu000/claude-skill-registry --skill premortem-darkroomengineering-cc-settings --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.
# Premortem Analysis Analyze potential failure modes before they happen. ## Purpose Imagine the project has failed. What went wrong? This technique surfaces risks that optimism bias might hide. ## Analysis Framework ### 1. Technical Risks - What could break? - What dependencies might fail? - What edge cases are unhandled? - What performance issues might emerge? ### 2. Integration Risks - How might this affect other parts of the system? - What backwards compatibility issues exist? - What migration challenges are there? ### 3. Operational Risks - What could go wrong in production? - What monitoring is missing? - What recovery procedures are needed? ### 4. User Experience Risks - How might users misuse this? - What accessibility issues exist? - What confusion might arise? ## Output Format ``` ## Premortem: [Feature/Change] ### High Risk - [Critical failure mode] → Mitigation: [How to prevent] ### Medium Risk - [Significant issue] → Mitigation: [How to address] ### Low Risk - [Minor concern] → Mitigation: [Simple fix] ### Recommendations 1. [Priority action] 2. [Secondary action] 3. [Nice to have] ``` ## When to Run - Before large refactoring - Before deploying new features - Before ar
- Purpose
- Analysis Framework
- 1. Technical Risks
- 2. Integration Risks
- 3. Operational Risks
- 4. User Experience Risks
- Output Format
- When to Run
- Remember
What does the premortem skill do?
Analyze what could go wrong with a plan. Use when: - User asks "what could go wrong", "risks", "potential issues" - Before implementing a significant change - User wants to validate an approach - Planning a risky operation
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill premortem-darkroomengineering-cc-settings --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.