book-to-skill compiles large documents into a structured agent skill with on-demand chapter loading, reducing token usage 24x-51x compared to raw context dumping. It extracts text and structure from multiple file formats and registers the resulting skill with supported coding agent CLIs.
Project overview
Achieves 24x-51x token reduction for querying large documents by paying extraction cost only once and enabling on-demand chapter loading, directly addressing high token costs and hallucination risks from raw context dumping.
Project type
RAG · Prompt Engineering
Use cases
Knowledge Q&A
Deployment
Refer to project documentation
License
MIT
Best for
Developers who need to query large technical books or documents through agent CLIs and want to reduce token costs while mitigating hallucinations.
Key capabilities
Extracts text and structure from PDF, EPUB, DOCX, TXT, Markdown, HTML, RTF, and MOBI files.
Folds new documents into an existing generated skill folder to merge knowledge incrementally.
Provides a standalone command-line interface for the text extraction engine without registering the agent skill.
Limitations and risks
Publishing or sharing a generated skill of a copyrighted work can infringe the rights holder. Users must verify they have appropriate rights before distributing generated skills.
Getting started
Install via pip or git clone. A first successful run uses pip install book-to-skill followed by book-to-skill ~/path/to/book.pdf --mode text.
Evidence and sources
GitHub project description: Turn any technical book PDF into a Claude Code skill
README: Turn any technical book, document folder, or collection of sources into a unified agent skill — ready to study, reference, and use while you work in GitHub Copilot CLI, Amp, or Cl…