Agent skill
ai-postmortem
Use when documenting an incident, outage, or production failure using the structured DERP model (Detection, Escalation, Recovery, Prevention).
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/ai-postmortem-arcasilesgroup-ai-engineering
SKILL.md
Postmortem
Purpose
Structured incident postmortem using the DERP model. Guides through Detection, Escalation, Recovery, and Prevention phases with targeted questions. Produces blameless, actionable postmortem documents.
Trigger
- Command:
/ai-postmortem start|continue|find|generate - Context: incident occurred, production failure, outage resolution, near-miss analysis.
Modes
start -- New postmortem
- Assign ID -- generate
PM-YYYY-NNN(sequential within year). - Set status --
draft. - Scaffold -- create
.ai-engineering/postmortems/{id}.mdwith DERP template. - Interview -- Detection:
- When was the incident first detected?
- How was it detected? (monitoring, user report, manual discovery)
- What was the time between incident start and detection?
- What monitoring should have caught it earlier?
- Interview -- Escalation:
- Who was notified and when?
- Was the escalation path appropriate?
- Were the right people involved at the right time?
- Interview -- Recovery:
- What actions were taken to restore service?
- What was the total downtime/impact duration?
- Was there a rollback? What was the rollback procedure?
- Interview -- Prevention:
- Root cause (use 5-Whys if needed)
- What changes prevent recurrence?
- Action items with owners and deadlines
Ask ONE section at a time. Wait for answers before proceeding to the next DERP phase.
continue -- Resume postmortem
- Load -- read
.ai-engineering/postmortems/{id}.md. - Find gap -- identify the first incomplete DERP section.
- Resume interview -- continue from the incomplete section.
find [query] -- Search postmortems
- Search -- scan
.ai-engineering/postmortems/*.mdfor matching content. - List -- show ID, title, date, status, and root cause summary.
generate -- Create from existing notes
- Collect -- gather incident-related commits, PRs, Slack threads, and notes from context.
- Draft -- populate DERP sections from available data, mark gaps as
[NEEDS INPUT]. - Review -- present draft for user validation before saving.
Document Template
# {id}: {title}
**Date**: YYYY-MM-DD
**Status**: draft | in-review | complete
**Severity**: SEV-1 | SEV-2 | SEV-3
**Duration**: {total impact time}
## Detection
{How and when the incident was discovered}
## Escalation
{Notification chain and response timeline}
## Recovery
{Steps taken to restore service}
## Prevention
### Root Cause
{5-Whys analysis}
### Action Items
| # | Action | Owner | Deadline | Status |
|---|--------|-------|----------|--------|
## Timeline
| Time | Event |
|------|-------|
Status Progression
draft -> in-review (all DERP sections complete) -> complete (action items assigned)
Quick Reference
/ai-postmortem start # begin new postmortem
/ai-postmortem continue PM-2026-001 # resume in-progress postmortem
/ai-postmortem find database # search past postmortems
/ai-postmortem generate # generate from existing context
Storage
- Location:
.ai-engineering/postmortems/{id}.md - ID format:
PM-YYYY-NNN
$ARGUMENTS
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?