Skip to main content
AIDiveForge AIDiveForge
🧯

Runbook Skeleton

Productivity & Ops · by AIDiveForge · Apr 20, 2026 · Intermediate

Produce a first-draft runbook from a postmortem — detection, diagnosis, mitigation, rollback — so the next incident has a template to follow.

🧠 Why it works

Runbooks are famously under-written because nobody wants to stop and write one right after an incident. Generating a first draft automatically removes the blank-page problem and captures the knowledge while it is fresh, which is when postmortems already require writing things down.

⚙️ How it works

  1. Parse the postmortem into labeled sections (timeline, contributing factors, action items). 2. Map each runbook section to likely postmortem content: Symptoms from the timeline's first entries, Diagnosis from the root-cause analysis, Mitigation from the hotfix actions, Rollback from the revert procedure. 3. For each section, extract verbatim quotes + a one-paragraph synthesis. 4. Emit as a markdown runbook with TODO markers where the postmortem didn't cover a section. 5. Cross-link to related runbooks by searching the runbook directory for similar symptom keywords.

Description

Reads a postmortem document (markdown or Google Doc export) and emits a runbook skeleton with the five standard sections: Symptoms, Detection, Diagnosis, Mitigation, Rollback. Each section is pre-filled with the relevant excerpts from the postmortem, ready for the on-call engineer to review and tighten.

Install this skill

A Claude skill is a skill.md file with YAML frontmatter and a markdown body. Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.

Download skill.md
mkdir -p ~/.claude/skills/runbook-skeleton \
  && curl -L https://aidiveforge.com/skill/runbook-skeleton.skill-md \
       -o ~/.claude/skills/runbook-skeleton/skill.md

Save to ~/.claude/skills/runbook-skeleton/skill.md

Recommended Use

Tools and workflow packs this skill pairs well with. Forge picks are auto-generated from category + capability signals; Community picks are added by people who've used the pairing.