What do I need to use Support Runbook?

The issue type; How to recognise it; The resolution path(s); Escalation.

Is Support Runbook free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Support Runbook

Q: How do I know the Support Runbook output is good?

The skill verifies itself against its own quality checks: Identification covers how customers actually describe it (not just the internal name); Severity/triage guidance sets response expectations; Diagnosis is a clear ordered path / decision tree, not a wall of tips; Escalation has an explicit trigger, target, and the diagnostics to attach.

🔵 Stable🕐 updated 2026-06-28 🔷 SkillSpec L3 pm-support

Write a support runbook for handling a recurring issue type consistently. Use when asked to write a support runbook, a troubleshooting playbook for agents, a handling guide for a common issue, or a tier-1 response procedure. Produces a runbook — issue identification, triage/severity, step-by-step diagnosis & resolution, decision tree, when/how to escalate, and the customer-comms templates — so any agent resolves it the same way.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The issue type — the recurring problem this runbook covers (e.g. "sync failures," "login loops," "billing discrepancy").

▸How to recognise it — symptoms and how it's reported.

▸The resolution path(s) — diagnostic steps and fixes (including the branches — "if X then…").

▸Escalation — when it exceeds tier-1, who it goes to, and with what diagnostics.

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Identification covers how customers actually describe it (not just the internal name)

✓Severity/triage guidance sets response expectations

✓Diagnosis is a clear ordered path / decision tree, not a wall of tips

✓Escalation has an explicit trigger, target, and the diagnostics to attach

✓Customer-comms snippets cover acknowledge / update / resolve / escalate

✓Flags the upstream fix if the issue is frequent (so support feeds product)

⚠️ What it refuses to do

Do not write a tip list instead of an ordered path — agents need "do this, then this," with branches

Do not leave escalation vague — "escalate if needed" means everyone escalates differently; time-box and specify the target + attachments

Do not omit the customer comms — resolution + silence still feels like bad support

Do not ignore severity — treating a full outage like a how-to question loses trust fast

Do not let a high-frequency issue stay a runbook forever — flag the root-cause fix to product

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="support-runbook"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Support Runbook is one of 551 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog