From magician
Runs a blameless post-mortem/RCA after an incident: gathers facts, reconstructs timeline, runs 5-Whys, writes report, commits it.
How this skill is triggered — by the user, by Claude, or both
Slash command
/magician:autopsyThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run a structured post-mortem for an incident or significant failure.
Run a structured post-mortem for an incident or significant failure.
This process is blameless. The goal is to understand what happened and prevent recurrence — not to assign fault.
Ask all three questions in one message:
"To run a proper post-mortem, I need the basics:
- What was the incident? (brief description)
- What was the impact? (users affected, duration, data loss, revenue)
- When did it start and end? (approximate times / dates)"
End your turn. Wait for all three answers before running any git or CI commands.
Then collect timeline evidence:
git log --oneline --since="<start>" --until="<end>"
gh run list --limit 20
Build a chronological timeline:
HH:MM — <event> (source: git log / monitoring / manual)
HH:MM — <event>
...
Problem: <symptom>
Why 1: <immediate cause>
Why 2: <cause of cause>
Why 3: <deeper cause>
Why 4: <systemic cause>
Why 5: <root cause>
The root cause is where action items should be aimed.
For each root cause identified:
ACTION: <what to do>
OWNER: <role, not person>
DEADLINE: <date>
PREVENTS: <which Why this addresses>
Categories: Detection (better monitoring), Prevention (code/process), Response (runbook), Recovery (backup/rollback).
Save to .workspace/shared/postmortems/YYYY-MM-DD-<incident-name>.md:
# Post-Mortem: <incident name>
**Date:** <date>
**Severity:** P1/P2/P3
**Duration:** <N minutes/hours>
**Impact:** <users/systems affected>
## Timeline
<reconstructed timeline>
## Root Cause
<5 Whys analysis>
## Action Items
| Action | Owner | Deadline | Status |
|--------|-------|----------|--------|
| <item> | <role> | <date> | Open |
## What Went Well
- <things that helped limit the incident>
## What Could Be Improved
- <systemic improvements>
git add .workspace/shared/postmortems/
git commit -m "docs: add post-mortem for <incident>"
Offer to remember this incident in the global reference store via /chronicle: one line capturing what + date + postmortem path. Only do this with explicit user confirmation.
"Autopsy complete. Post-mortem written to .workspace/shared/postmortems/<filename>.md. N action items identified."
npx claudepluginhub alexander-tyagunov/magician --plugin magicianWriting comprehensive postmortems: timeline, root cause, prevention, action items.
Conducts blameless postmortems for outages and incidents with timeline reconstruction, root cause analysis (5 Whys, fishbone), and corrective action tracking.
Structures blameless post-mortems with incident timelines, impact assessment, root cause analysis, response evaluation, action items, and lessons learned. Useful after production incidents or outages.