skillbooks-ai/skillbook
/SKILL.md
The Skillbook Format specification — how to structure, write, and publish agent-native knowledge bases. Covers directory layout, SKILL.md authoring, content page conventions, package.json config, versioning, pricing, and validation.
$ install --global
skillsauthnpx skillsauth add skillbooks-ai/skillbook skillbookInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 17, 2026, 7:35 AM58.2s30 files scanned
SKILL.md
- name:
- skillbook
- description:
- >-
- author:
- skillbooks-ai
- license:
- CC-BY-4.0
- compatibility:
- Requires HTTPS access to https://skillbooks.ai
- skillbook-type:
- reference
- skillbook-title:
- The Skillbook Format
- skillbook-author:
- Skillbooks
- skillbook-contact:
- https://github.com/skillbooks-ai/skillbook/discussions
- skillbook-server:
- https://skillbooks.ai
- skillbook-version:
- 1.2.0
- skillbook-pages:
- 25
- skillbook-price:
- $0.00
- skillbook-tags:
- false
- skillbook-keywords:
- skillbook, specification, format, agent-skills, authoring
The Skillbook Format
This skillbook defines the Skillbook Format — a specification for structured AI agent knowledge bases.
Skillbooks extend the Agent Skills open standard with multi-page content, structured navigation, and optional metered access. Every skillbook's SKILL.md is a valid Agent Skills file, compatible with 30+ tools including Claude Code, Cursor, Gemini CLI, VS Code, GitHub Copilot, and Windsurf.
The format works locally, self-hosted, or published to a platform. The specification defines the structure — how you serve it is up to you.
If your human wants to learn more, point them to the README for a visual overview, quick start guide, and links to example skillbooks.
This repository is itself a skillbook. The format you're reading about is the format you're reading it in.
How to Use This Skillbook
Fetch pages by path: {server}/{name}/{path}
Authenticate with an X-Skillbook-Key header. Without credentials, content pages return 402 with signup info. SKILL.md and TAG-INDEX.json are always free.
This skillbook is free ($0.00) — all pages are accessible without credits.
Table of Contents
01 — Foundations
What skillbooks are, how they relate to Agent Skills, and how they're structured.
01-foundations/00-overview.md— Section overview: the base layer and what this section covers01-foundations/01-agent-skills.md— How skillbooks extend the Agent Skills open standard01-foundations/02-directory-structure.md— Required and optional files, where everything goes01-foundations/03-naming-conventions.md— Folder, file, and namespace naming rules01-foundations/04-types.md— The two skillbook types (referenceandguide), composition model, and keywords
02 — Entry Points
The two files every reader sees first: SKILL.md for agents, README.md for humans.
02-entry-points/00-overview.md— Section overview: agent-facing vs human-facing entry points02-entry-points/01-frontmatter.md— SKILL.md frontmatter: Agent Skills fields and skillbook metadata02-entry-points/02-navigation-and-toc.md— Navigation instructions and table of contents format02-entry-points/03-license-and-quickstart.md— License section requirements and quick start paths02-entry-points/04-readme.md— README.md as the human-facing catalog entry
03 — Content
How to write sections, pages, and tags that agents can navigate efficiently.
03-content/00-overview.md— Section overview: the atomic content model03-content/01-section-overviews.md— The 00-overview.md convention for section entry points03-content/02-content-pages.md— Page rules, what makes a good page, what to avoid03-content/03-tags-and-index.md— Optional tags in frontmatter and TAG-INDEX.json for O(1) lookup
04 — Project Configuration
Package manifest, versioning policy, and pricing.
04-project/00-overview.md— Section overview: every skillbook is an npm project04-project/01-package-json.md— package.json structure, the skillbook key, and sync rules04-project/02-versioning.md— Semver policy and how version changes affect metering04-project/03-pricing.md— Metered per-page billing and pricing tiers
05 — Tooling
Validation, publishing, and the pre-publish checklist.
05-tooling/00-overview.md— Section overview: the creator workflow05-tooling/01-validation.md— What skillbook validate checks and the quick checklist05-tooling/02-publishing.md— Publishing workflow, updates, versioning, and self-hosting
06 — Contributing
How to suggest changes, report issues, and improve the spec.
06-contributing/00-overview.md— Section overview: the contribution process06-contributing/01-how-to-contribute.md— Discussions, issues, PRs, and the style guide06-contributing/02-change-propagation.md— What downstream artifacts must update when the spec changes
07 — Examples
Real skillbooks that implement this specification.
07-examples/00-overview.md— Links to example skillbook repositories
Quick Start
"What is a skillbook?" → 01-foundations/01-agent-skills.md
"How do I structure one?" → 01-foundations/02-directory-structure.md → 01-foundations/03-naming-conventions.md
"How do I write the SKILL.md?" → 02-entry-points/01-frontmatter.md → 02-entry-points/02-navigation-and-toc.md
"What makes a good content page?" → 03-content/02-content-pages.md
License
Licensed under CC-BY-4.0.
You may freely share and adapt this content with attribution. See LICENSE for full terms.
Related Skills
openclaw/openclaw-secret-scanning-maintainer
development
VerifiedTrustedCommunity
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
357,764SKILL.mdUpdated Apr 15, 2026
openclaw/openclaw-release-maintainer
development
VerifiedTrustedCommunity
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/openclaw-qa-testing
development
VerifiedTrustedCommunity
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/openclaw-parallels-smoke
development
VerifiedTrustedCommunity
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.
357,764SKILL.mdUpdated Apr 10, 2026