book-to-skill

Feed it a technical book and it hands back a skill your coding agent can actually search. The pitch is token economy: instead of dumping 400 pages into context and paying for every one of them, the generated skill loads only the chapters relevant to the question. The project claims 24x to 51x fewer tokens per answer. MIT licensed, runs entirely on your machine, no API key.

Setup is three commands: pip install, register the skill, point it at a file. Format support comes through optional dependencies, so PDFs want pdftotext or pypdf and EPUBs want ebooklib. Nothing gets uploaded. Output works with Claude Code, GitHub Copilot CLI, and Amp.

The obvious use is reference material your agent keeps guessing about: language specs, framework books, internal standards documents. Solo and small teams: free, and no reason not to try it on one book first. Medium and large teams get more out of converting shared internal docs once and committing the result.

The catch is legal, not technical. The MIT license covers the converter, not the book you put through it. Turning a purchased title into a skill you commit to a shared repo is redistribution, and the tool will happily let you do it. The other limit is mechanical: a scanned image-only PDF has no text to extract.