Agent skill
doc-runbook
Generate an operational runbook from template. Use when the user says "write a runbook", "create an ops guide", "incident response procedure", "how to handle [X] in production", or "document the on-call procedure for".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/doc-runbook
SKILL.md
Generate Runbook
Path Resolution
- Read
workflow.jsonin the project root - If it exists and
docsRepois".": this IS the docs repo — use local paths - If it exists and
docsRepois a repo name: resolve viapwsh .claude/skills/tool-worktree/scripts/resolve-repo.ps1 <docsRepo>to get the docs root path. Templates at<resolved>/templates/, output to<resolved>/runbooks/ - If no
workflow.json: templates attemplates/, output todocs/runbooks/
Instructions
- Resolve paths (see Path Resolution above)
- Read the template at
<templates>/runbook.md - Understand the operation/incident:
- What triggers this runbook? (Alert, symptom, scheduled task)
- What services are involved?
- What access/permissions are needed?
- Generate the runbook with emphasis on:
- Concrete commands: Every diagnosis and resolution step should have copy-pasteable commands
- Decision tree: Clear "if X then Y" logic for diagnosis
- Escalation path: When and how to escalate
- Verification: How to confirm the issue is resolved
- Save to
<output>/[slug].md
Quality Checklist
- Every diagnosis step has a concrete command or dashboard link
- Common causes are ordered by likelihood (most likely first)
- Resolution steps are copy-pasteable (not abstract instructions)
- Rollback procedure is included
- Escalation criteria are specific (time-based or condition-based)
- Verification steps confirm the fix worked
- Prerequisites list required access and tools
Tips
- Write for someone who's been paged at 3 AM — be explicit, don't assume context
- Include actual commands, not descriptions of commands
- Order diagnosis steps by likelihood to minimize mean time to resolution
- Link to monitoring dashboards and log queries
- Update runbooks after every incident (add what was learned)
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?