my-failure-museum
Turn a mistake into a reusable lesson — a short, unsentimental 'here's what happened and the rule so it doesn't happen again' entry you can actually keep. Use when asked help me learn from this mistake, I keep making the same error, capture this lesson, or turn this failure into something useful. Produces an honest, blame-free autopsy of what happened, the real root cause (not the surface one), the specific rule or trigger that prevents a repeat, and a one-line entry for your growing 'failure museum' — because unexamined mistakes repeat and examined ones compound into wisdom.
Profile →npx skills add mohitagw15856/pm-claude-skills --skill my-failure-museum --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.
# My Failure Museum A mistake you don't examine is one you'll make again; a mistake you turn into a rule never costs you twice. This does the turning: a short, honest, blame-free autopsy of what went wrong, the *real* root cause underneath the obvious one, and the specific rule or trigger that stops the repeat — captured as a one-line entry for a growing collection. Over time, your failure museum becomes your hardest-won operating manual. ## What This Skill Produces - **The honest autopsy** — what actually happened, blame-free (self-flagellation teaches nothing; analysis does) - **The real root cause** — the underlying reason, not the surface one ("I was busy" → "I don't build in buffer time") - **The prevention rule** — a specific, actionable rule or trigger that would have caught it, and will next time - **The one-line museum entry** — a compact, keepable lesson to add to your collection - **A pattern check** — whether this is a one-off or part of a recurring theme worth a bigger fix ## Required Inputs Ask for these if not provided: - **What happened** — the mistake or failure - **The consequence** — what it cost - **Your read on why** — your first explanation (we'll dig past it)
- What This Skill Produces
- Required Inputs
- Framework: Autopsy Without Blame, Extract The Rule
- Output Format
- Failure: [what happened] · cost: [consequence]
- Quality Checks
- Anti-Patterns
- Example Trigger Phrases
What does the my-failure-museum skill do?
Turn a mistake into a reusable lesson — a short, unsentimental 'here's what happened and the rule so it doesn't happen again' entry you can actually keep. Use when asked help me learn from this mistake, I keep making the same error, capture this lesson, or turn this failure into something useful. Produces an honest, blame-free autopsy of what happened, the real root cause (not the surface one), the specific rule or trigger that prevents a repeat, and a one-line entry for your growing 'failure museum' — because unexamined mistakes repeat and examined ones compound into wisdom.
How do I install it?
Run `npx skills add mohitagw15856/pm-claude-skills --skill my-failure-museum --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 mohitagw15856/pm-claude-skills, a repository with 1,277 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.