git-repo-to-book
Write a full-length technical book using multi-agent AI orchestration. Spawns parallel research, writing, and review agents to produce 60K-100K+ word manuscripts. Also supports revising individual chapters of existing books. Based on the real workflow that produced an 88,000-word, 14-chapter book in under 18 hours.
Why use this skill?
Use the git-repo-to-book skill to transform codebases into 100k+ word technical books using multi-agent orchestration. Build professional manuals fast.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/chunhualiao/git-repo-to-bookWhat This Skill Does
The git-repo-to-book skill transforms complex codebases or abstract technical topics into professional-grade, long-form manuscripts. Using sophisticated multi-agent orchestration, the skill automates the entire lifecycle of book production, including research, outline generation, multi-chapter drafting, and iterative peer review. Designed specifically for technical documentation and non-fiction, it mimics the rigorous process used to produce 'The OpenClaw Paradigm', ensuring high-quality, cohesive output. The system manages inter-agent coordination through the WORKLOG protocol, allowing for massive parallelization of tasks, which significantly reduces the time required to move from an initial concept to a 60K-100K+ word manuscript. It also provides granular support for revising existing chapters, making it a powerful tool for maintaining living documentation.
Installation
To integrate this skill into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/chunhualiao/git-repo-to-book
Use Cases
- Documentation Generation: Automatically generate comprehensive technical manuals from existing project repositories.
- Content Repurposing: Convert internal GitHub repositories or project wikis into structured, reader-friendly technical books.
- Knowledge Transfer: Codify complex architectural patterns or library documentation into a cohesive narrative for team onboarding.
- Chapter Iteration: Revise specific sections of an existing book without disrupting the entire manuscript integrity.
Example Prompts
- "Create a 12-chapter technical book about the architecture of my project located at github.com/user/my-web-framework. Aim for a target length of 80,000 words."
- "I need to revise chapter 4 of my current draft. The focus should be on explaining the new asynchronous middleware implementation with clearer examples."
- "Write a 50,000-word book on the history and application of quantum computing algorithms. No source repository provided, use default research agents."
Tips & Limitations
- Scaling: The skill automatically suggests chapter counts based on repository size, but you can override these parameters at any time.
- Cost Management: Set a budget limit to ensure the multi-agent orchestration remains within your financial constraints. The default is $100.
- Format: The skill outputs primary content in Markdown, with options for HTML and PDF exports. It does not handle graphic design or cover art; use dedicated media skills for those tasks.
- Non-Fiction Focus: The agent is optimized for technical, factual, and informative prose. It is not designed for creative fiction writing.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-chunhualiao-git-repo-to-book": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api, code-execution
Related Skills
claude-usage
Check Claude Max plan usage limits by launching Claude Code and running /usage. Use when the user asks about Claude plan usage, remaining quota, rate limits, or sends /claude_usage.
save-to-obsidian
Saves markdown content to remote Obsidian vault via SSH
task-runner
Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronously via subagents. A heartbeat/cron dispatcher wakes periodically to check pending tasks, spawn workers, and report completions. The system never "finishes" — it always remains ready for the next task.
openclaw-docker-setup
Install and configure a fully operational Dockerized OpenClaw instance on macOS from scratch. Includes browser pairing, Discord channel setup, and optional Gmail/Google Drive integration. Use when user asks to "install openclaw docker", "set up dockerized openclaw", "openclaw in docker", or "isolated openclaw instance".
skill-releaser
Release skills to ClawhHub through the full publication pipeline — auto-scaffolding, OPSEC scan, dual review (agent + user), force-push release, security scan verification. Use when releasing a skill, preparing a skill for release, reviewing a skill for publication, or checking release readiness.