postmortem
Generate blameless postmortem with root cause analysis
When & Why to Use This Skill
This Claude skill automates the generation of comprehensive, blameless postmortem documents and deep root cause analysis (RCA). By leveraging multi-agent investigation tracks—including codebase exploration, external research, and specialized code analysis—it helps engineering teams identify systemic vulnerabilities, improve monitoring coverage, and foster a culture of continuous learning after technical incidents.
Use Cases
- Automating production outage documentation: Quickly generate detailed post-incident reports that focus on systemic failures and technical factors rather than individual errors to maintain a blameless culture.
- Deep-dive Root Cause Analysis (RCA): Utilize parallel agents to trace failure paths through the codebase and perform '5 Whys' analysis to uncover hidden architectural weaknesses and technical debt.
- Standardizing Incident Knowledge Bases: Automatically format and save postmortem findings to Obsidian with consistent templates, ensuring a searchable and professional record of resolutions and prevention strategies.
| name | postmortem |
|---|---|
| description | Generate blameless postmortem with root cause analysis |
Post-Incident Review
Current Time: !date
Generate a blameless postmortem document with root cause analysis. Investigates the incident and codebase to provide deeper RCA insights.
Input
- Incident reference (Obsidian incident file path or summary)
- Resolution details (what fixed it, when)
- Optional: additional context, timeline notes
Investigation Strategy
Launch three parallel investigation tracks to deepen RCA:
Track 1: External Research (librarian agent)
- Research similar incidents in public postmortems
- Find industry best practices for preventing recurrence
- Identify patterns from similar failures
Track 2: Codebase Exploration (explore agent)
- Trace the full failure path through the codebase
- Identify systemic issues (missing tests, error handling gaps)
- Find related code that may have similar vulnerabilities
- Review monitoring/alerting coverage for affected paths
Track 3: Code Analysis (inferred agent: go/frontend/postgres/etc.)
- Infer appropriate agent from incident context
- Deep analysis of root cause code
- Identify contributing technical factors
- Assess fix completeness and durability
Output
Write to Obsidian via obsidian_append_content at:
$OBSIDIAN_PATH/Postmortems/YYYY-MM-DD-incident-title.md
Note:
$OBSIDIAN_PATHmust be a vault-relative path (e.g.,Projects/myapp), set per-project via direnv. Theobsidian_append_contenttool expects paths relative to the vault root.
Document Structure
Use this template for the Obsidian document:
@~/.config/opencode/templates/postmortem.md
Behavior
- Parse incident reference to extract context (read from Obsidian if path provided)
- Infer appropriate code agent from incident context
- Launch librarian, explore, and inferred code agent in parallel
- Analyze failure path and identify systemic issues
- Generate 5 Whys analysis based on findings
- Synthesize into blameless postmortem document
- Write to Obsidian via
obsidian_append_contentwith auto-generated filename:YYYY-MM-DD-incident-title.md - Include wiki-link back to original incident document
$ARGUMENTS