A comprehensive CLI tool that automates the creation, optimization, and deployment of Claude AI skills from various data sources.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install auto-skill-builder
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install auto-skill-builder using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Auto Skill Builder?
Auto Skill Builder is an advanced workflow engine designed to streamline the lifecycle of creating Openclaw Skills. It integrates the scraping power of skill-seekers with the structural best practices of skill-creator, allowing developers to convert raw technical data into highly structured AI agent capabilities.
By automating the synthesis of SKILL.md files, this tool ensures that AI agents have access to concise, accurate, and actionable technical knowledge. It bridges the gap between raw documentation and the specific formatting requirements needed for high-performance agentic workflows.
Auto Skill Builder Use Cases
- Creating specialized Openclaw Skills from modern web frameworks like React or Vue.js documentation.
- Converting private GitHub repositories into internal technical skills for enterprise AI agents.
- Digitizing legacy PDF manuals into searchable, structured knowledge bases for AI troubleshooting.
- Generating unified skills that merge code analysis with external API documentation.
How Auto Skill Builder Works
- Content Acquisition: The tool scrapes data from provided URLs, clones GitHub repositories, or parses local PDF files.
- AI Synthesis: It processes the raw content through AI enhancement to generate a standardized SKILL.md file.
- Optimization: Best practices are applied to remove redundant text, fix YAML frontmatter, and ensure progressive disclosure of information.
- Quality Audit: The system validates the generated skill for structural integrity, code example coverage, and link validity.
- Deployment: The finalized skill is packaged into a deployable format and can be installed directly into an agent environment.
Auto Skill Builder Setup
To begin building your own Openclaw Skills, follow these installation steps:
# Configure your GitHub token for repository access
export GITHUB_TOKEN=ghp_your_token
# Create a skill from a documentation URL with AI enhancement
auto-skill-builder create --type docs --url https://react.dev --name react --enhance
# Alternatively, create a skill from a GitHub repository
auto-skill-builder create --type github --repo facebook/react --name react --include-code
Auto Skill Builder Data Schema & Taxonomy
The tool generates a standardized directory structure to ensure Openclaw Skills remain modular and maintainable:
| File/Folder | Description |
|---|---|
SKILL.md |
The core definition file containing workflows and primary logic. |
references/ |
Directory for detailed supporting documentation. |
quick-start.md |
Minimal steps to get the skill running. |
api-reference.md |
Technical specifications and endpoint details. |
examples.md |
Curated code snippets and usage scenarios. |
troubleshooting.md |
Common issues and resolution paths. |
Auto Skill Builder Advanced Features
- Unified Scraping: Merge multiple data sources while automatically detecting and resolving content conflicts.
- Local AI Enhancement: Support for local LLM processing via Claude Code for offline skill generation and privacy.
- Asynchronous Processing: High-speed scraping mode utilizing up to 8 parallel workers for massive documentation sets.
- Automated Quality Checks: Built-in validation for code snippet integrity and documentation link health.
- One-Click Packaging: Automatically bundle skills into zip or tar.gz formats ready for distribution.
SKILL.md
Loading
Related Openclaw Skills
Openclaw Starter Skill
A foundational template designed to integrate custom capabilities and automated workflows into the Openclaw environment.
Search Memory
A high-performance local indexing and search utility designed to retrieve information from project memory files using keyword scoring and recency boosts.
Memory Search
A local-first search utility designed to index personal data and provide rapid retrieval via cached memory queries.
gitbackup
Automatically generates self-contained Git bundles of your OpenClaw workspace to ensure your version history is backed up locally.
GitHub Repository Mirror
A professional migration tool to fully mirror GitHub repositories between accounts while preserving all version history, branches, and tags.
OpenClaw Template Generator
An AI-powered generator that scaffolds OpenClaw project configurations including AGENTS.md, workflows, and memory settings through a unified LLM interface.
Featured*
