Agent skill
postmortem
Generate blameless postmortem with root cause analysis
Install this agent skill to your Project
npx add-skill https://github.com/thoreinstein/opencode-config/tree/main/skill/postmortem
SKILL.md
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
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
thoreinstein/opencode-config
seo
Implement SEO optimizations for specified pages or entire site
thoreinstein/opencode-config
runbook
Generate operational runbooks for services, procedures, or incident response
thoreinstein/opencode-config
file-organizer
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
thoreinstein/opencode-config
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
thoreinstein/opencode-config
ultrathink
Ultra-deep multi-perspective analysis for complex architectural and strategic decisions
thoreinstein/opencode-config
commit
Analyze unstaged changes and suggest atomic commit groups with messages
Didn't find tool you were looking for?