git-repo-to-book

# Git Repo to Book

Write a full-length technical book using multi-agent AI orchestration. Based on the
real workflow that produced [The OpenClaw Paradigm](https://github.com/chunhualiao/openclaw-paradigm-book)
— 88,000+ words, 14 chapters, 42 diagrams in under 18 hours.

## Scope & Boundaries

**This skill handles:**
- Planning, researching, writing, reviewing, and publishing multi-chapter technical books
- **Revising individual chapters** of existing books (review → rewrite → re-integrate)
- Orchestrating parallel sub-agents for each phase
- Merging chapters into a polished manuscript with TOC, metadata, and HTML export
- Managing the WORKLOG protocol for agent coordination

**This skill does NOT handle:**
- Cover design or artwork generation (use an illustration skill)
- Publishing to Amazon/Kindle/bookstores (output is Markdown + HTML)
- Fiction/creative writing (optimized for technical/non-fiction)
- Translation to other languages

## Inputs

| Input | Required | Description |
|-------|----------|-------------|
| Topic/subject | Yes | What the book is about |
| Source repo | No | GitHub URL to analyze as source material |
| Chapter count | No | Auto-scaled from repo size (see below), or user override |
| Target length | No | Auto-scaled from repo size (see below), or user override |
| Budget limit | No | Max API cost in dollars. Default: $100. Agent pauses if exceeded |
| Output formats | No | Markdown (always), HTML (optional), PDF (optional) |
| Model preferences | No | Defaults in Agent Model Recommendations section |

## Outputs

- `book/final-manuscript.md` — polished, publication-ready manuscript
- `book/illustrated-manuscript.md` — manuscript with scrapbook illustrations (if article-illustrator available)
- `book/metadata.json` — title, author, word count, chapter count, date
- `book/book.html` — HTML export (optional)
- Git repository with full project history

## Auto-Scaling: Repo Size → Book Size

When a source repo is provided, automatically assess...

# Git Repo to Book

An [OpenClaw](https://openclaw.ai) skill for writing full-length technical books using multi-agent AI orchestration.

Based on the workflow that produced [The OpenClaw Paradigm](https://github.com/chunhualiao/openclaw-paradigm-book): 88,000+ words, 14 chapters, 42 Mermaid diagrams in under 18 hours.

## How It Works

The skill orchestrates 7 phases, each running isolated sub-agents in parallel:

```
PLANNING → RESEARCH → OUTLINES → WRITING → REVIEWING → INTEGRATING → POLISHING → PUBLISHING
```

A Director agent coordinates everything via an append-only `WORKLOG.md` — no polling, no blocking. Writing agents run 4-5 in parallel, each handling 3 chapters.

## Installation

Copy the skill directory to your OpenClaw workspace:

```bash
cp -r git-repo-to-book ~/.openclaw/<workspace>/skills/
```

### Requirements

- Python 3.8+ (for merge, polish, and HTML scripts)
- git (version control)
- `sessions_spawn` tool (for parallel sub-agents)
- Optional: `pandoc` for better HTML conversion

## Usage

```
Write a technical book about [topic]. Use the book-writer skill.
Source material: [optional GitHub URL]
Chapters: 12
Target: ~70,000 words
```

The agent will set up the repo, spawn parallel research/writing/review agents, and deliver a polished manuscript.

## What You Get

| Output | Description |
|--------|-------------|
| `book/final-manuscript.md` | Polished manuscript with TOC, title page, metadata |
| `book/metadata.json` | Title, author, word count, chapter count, date |
| `book/book.html` | HTML export (optional) |
| `chapters/*.md` | Individual chapter files |
| `research/*.md` | Research findings and pattern synthesis |
| `reviews/*.md` | Quality review results |

## Agent Roles

| Role | Model | Task |
|------|-------|------|
| Director | claude-sonnet-4-6 | Planning, coordination, quality gates |
| Research | gemini-2.5-pro | Source analysis, pattern identification |
| Writing | claude-sonnet-4-6 | 3 chapters per agent, 6-8K words each |
| Revie...