Turn any technical book, document folder, or collection of sources into a unified Claude Code skill — ready to study, reference, and use while you work.
Why · What it generates · Usage · Requirements · How it works · FAQ · Install
You buy a great technical book. You read it once. Three months later you can't remember chapter 7 existed.
The usual workarounds don't help:
- 📄 "Let me just search the PDF" → you get a list of pages, not answers
- 🧠 "I'll ask Claude about this book" → it either hallucinates or says it doesn't have the content
- 📝 "I'll take notes as I read" → you end up with a 200-line doc you never open again
book-to-skill solves this by turning the book into a structured skill Claude loads on demand.
Once installed, you just type /your-book-slug replication and Claude reads the right chapter and answers from the actual content. No hallucination. No digging through PDFs. The book becomes part of your workflow.
Running /book-to-skill your-book.pdf (or a folder, glob, or list of files) creates a full skill at ~/.claude/skills/<slug>/:
| File | Purpose | Size |
|---|---|---|
SKILL.md |
Core mental models + chapter index | ~4,000 tokens |
chapters/ch01-*.md … |
One file per chapter, loaded on-demand | ~1,000 tokens each |
glossary.md |
Every key term, alphabetically sorted with chapter refs | ~1,500 tokens |
patterns.md |
All techniques, algorithms, and design patterns | ~2,000 tokens |
cheatsheet.md |
Decision tables and quick-reference rules | ~1,000 tokens |
Chapter files are loaded on-demand — they don't count against the skill budget until you ask about that topic.
/book-to-skill <path-to-document-folder-or-glob>... [skill-name-slug]
Supported document formats: PDF, EPUB, DOCX, TXT, Markdown, reStructuredText, AsciiDoc, HTML, RTF, MOBI/AZW/AZW3.
Examples:
# Process several files together into a unified skill
/book-to-skill ~/papers/paper1.pdf ~/notes/export.txt unified-research
# Process all supported files in a folder together
/book-to-skill ~/workspace/project-docs/ project-knowledge
# Process files matching a glob pattern
/book-to-skill "~/books/*.epub" my-library
# Update/fold new material into an existing skill folder
/book-to-skill ~/articles/new-paper.pdf ~/.claude/skills/project-knowledgeAfter the skill is created, use it like any other Claude Code skill:
/designing-data-intensive-apps # load core mental models
/designing-data-intensive-apps replication # find and explain a topic
/designing-data-intensive-apps ch05 # dive into chapter 5
/designing-data-intensive-apps "what chapters do you have?"The extractor tries tools in order per format and uses the first available. If nothing is installed, it tells you which command to run. Plain text, Markdown, reStructuredText and AsciiDoc need no extra deps.
PDF — choose by book type:
| Book type | Tool | Install | Speed |
|---|---|---|---|
| Text-heavy (prose, few tables) | pdftotext (poppler) |
sudo apt install poppler-utils |
⚡ instant |
| Text-heavy fallback | PyPDF2 |
pip3 install PyPDF2 |
⚡ instant |
| Text-heavy fallback | pdfminer.six |
pip3 install pdfminer.six |
⚡ instant |
| Technical (code, tables, formulas) | docling |
pip3 install docling |
~1.5s/page |
Before extraction begins, the skill asks you whether the book is technical or text-heavy and picks the right tool automatically. Docling preserves markdown tables and code blocks; pdftotext is faster for prose-only books.
EPUB:
| Tool | Install | Quality |
|---|---|---|
ebooklib + beautifulsoup4 |
pip3 install ebooklib beautifulsoup4 |
⭐⭐⭐ Best |
stdlib zipfile |
built-in — no install needed | ⭐⭐ Always available |
Other formats:
| Format | Tool | Install |
|---|---|---|
| DOCX | python-docx (fallback: stdlib ZIP/XML) |
pip3 install python-docx |
| HTML | beautifulsoup4 (fallback: stdlib html.parser) |
pip3 install beautifulsoup4 |
| RTF | striprtf (fallback: regex) |
pip3 install striprtf |
| MOBI / AZW / AZW3 | Calibre ebook-convert (external app, not pip) |
https://calibre-ebook.com/download |
| TXT / Markdown / reStructuredText / AsciiDoc | built-in | — |
One file · a folder · a glob · a list of paths
│
▼
Step 1.5 — "Technical or text-heavy book?"
│
├── technical → Docling (tables + code blocks as markdown, ~1.5s/page)
└── text → pdftotext → PyPDF2 → pdfminer (instant)
│
▼
scripts/extract.py <paths…> --mode <technical|text>
per source: PDF → pdftotext/Docling · EPUB → ebooklib → stdlib zipfile · DOCX/HTML/RTF/…
(one bad source is skipped with a warning; the rest still process)
│
├── /tmp/book_skill_work/full_text.txt (all sources merged, with source markers)
└── /tmp/book_skill_work/metadata.json (aggregated stats + per-source array)
│
▼
Claude analyzes structure
(title, author, chapters, ToC — spanning all sources)
── or, if targeting an existing skill: folds new content in (Mode 4)
│
▼
Generates per-chapter summaries (800–1,200 tokens each)
technical → includes Code Examples + Reference Tables sections
Generates glossary, patterns, cheatsheet
Generates master SKILL.md with core mental models
│
▼
~/.claude/skills/<slug>/ ✅ written
/tmp/book_skill_work/ 🗑️ cleaned up
Extraction benchmark (103-page technical book, CPU only):
| Method | Time | Tokens | Tables | Code blocks |
|---|---|---|---|---|
| pdftotext | 0.1s | 27K | 0 | 0 |
| Docling | 164s | 27K (+1.2%) | 48 | 36 |
Design principles (click to expand)
- Density over completeness — a 1,000-token summary beats a 10,000-token excerpt
- Practitioner voice — "Use X when Y", not "The book explains X"
- Front-loaded SKILL.md — compaction keeps the first ~5,000 tokens; the most important content comes first
- On-demand chapters — the topic index tells Claude which file to read; chapters load only when needed
- Never raw text — always synthesize, summarize, extract signal from the source
"Can't I just dump the PDF/EPUB into my Claude project context?"
You can — but every conversation will burn that token budget upfront. A 400-page book is ~200K tokens. With a skill, only the chapters relevant to your question load. The rest stays on disk until you need it.
More importantly: raw text injection is retrieval. A skill is reasoning. When you load a chapter file, Claude isn't searching for keyword matches — it's working with pre-extracted named frameworks, principles, and mental models structured for application, not for reading.
"Isn't this just RAG?"
RAG works at query time: chunk the book → embed everything → find similar vectors → inject into prompt. It's optimized for "find me the part that talks about X."
book-to-skill works at compile time: one deep analysis run extracts the author's actual frameworks, names them, describes when to use each, captures the anti-patterns. The output is structure the author spent years building — not a similarity search over their sentences.
RAG answers: "here are chunks close to your query."
A skill answers: "here are the 12 frameworks this author built, ready to reason with."
For searching across 50+ books, RAG wins. For going deep on one book and using its frameworks while you work, a skill wins.
"Popular books are already in Claude's training data. Why bother?"
For widely-known books (Clean Code, DDIA, Pragmatic Programmer), Claude has general knowledge — but it's compressed, averaged across the entire internet's discussion of the book, and may hallucinate specific quotes or chapter locations.
book-to-skill works from your actual copy. Every framework name, every anti-pattern list, every chapter number is grounded in the text you provided. No training data drift, no hallucinated chapter titles.
It also shines for books Claude doesn't know at all: niche technical references, internal company documentation, recent publications, translated works.
"NotebookLM handles multiple books better."
Absolutely true — if your workflow is "I have 80 separate books and I want to search across all of them," NotebookLM is the right tool.
book-to-skill is built for a different job: you want to go deep on a specific topic or library, having multiple related documents (papers, chapters, notes) folded into a single unified skill, and even updating it over time as new material arrives! This integrates your customized knowledge base right into your coding or writing workflow, rather than in a separate browser tab.
Copy this into your Claude Code session:
Install book-to-skill: https://raw.githubusercontent.com/virgiliojr94/book-to-skill/master/SKILL.md
Or manually using standard git clone (ensures modular engine files are fetched correctly):
git clone https://github.com/virgiliojr94/book-to-skill.git ~/.claude/skills/book-to-skillThen in any Claude Code session:
/book-to-skill ~/path/to/your-book.pdf
# or
/book-to-skill ~/path/to/your-book.epubbook-to-skill/
├── SKILL.md # Skill definition + step-by-step instructions
├── scripts/
│ ├── extract.py # Thin entrypoint wrapper
│ └── extractor/ # Modular extraction package
│ ├── __init__.py
│ ├── config.py # Extensions, paths, dependency constants
│ ├── dependencies.py
│ ├── exceptions.py # ExtractionError (per-source failures, batch-safe)
│ ├── utils.py # CLI parsing, multi-source resolution, runner
│ └── parsers/ # Format-specific parsers (pdf, epub, docx, html, rtf, calibre, text)
├── tests/
│ └── test_extractor.py # Test suite (multi-source, batch resilience, EPUB, parsers)
└── README.md # This file
MIT