runbook

Create, update, or validate one evidence-backed operational runbook when the user explicitly requests runbook work.

IndexedMIT

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/oppegard-runbook

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Create, update, or validate one evidence-backed operational runbook when the user explicitly requests runbook work.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/runbook

What's inside

Skill name: runbook
Description: Create, update, or validate one evidence-backed operational runbook when the user explicitly requests runbook work.
License: MIT
Instructions: 14 lines in SKILL.md · view on GitHub

Files (7)

SKILL.md
authoring-workflow.md · references/
capability-boundary.md · references/
evidence-gate.md · references/
quality-check.md · references/
runbook-template.md · references/
writing-blocklist.md · references/

SKILL.md (first lines)

# Runbook

Create, update, or validate one operational runbook per invocation. Do not
author a runbook merely because another readiness review reports that one is
missing.

Read the bundled [Capability boundary](references/capability-boundary.md),
[Authoring workflow](references/authoring-workflow.md), and
[Evidence gate](references/evidence-gate.md) before handling the requested
runbook. Use the [Runbook template](references/runbook-template.md) when the
project does not already have an established runbook format. Apply the
[Quality check](references/quality-check.md) before presenting the result.

From oppegard/operations-agent-skills, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 8
Last commit (this folder): Jul 30, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/oppegard/operations-agent-skills
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from oppegard

Cite this page

runbook skill. Agent Mart. https://agentmart.dev/skills/oppegard-runbook (last updated 2026-10-24)