← All Skills
book-to-skill distills any technical book (PDF/EPUB/DOCX and more) into a skill your agent loads on demand: it generates core mental models plus a chapter index, per-chapter files, a glossary, a patterns file, and a cheatsheet, with chapters loaded only when asked. Answering one question costs 24–51× fewer tokens than dumping the book into context, and answers come from the real text — no hallucination. It follows the open Agent Skills standard and works in Claude Code, GitHub Copilot CLI, and Amp.
Key Features
- Turn a book into an on-demand skill
- 24–51× fewer tokens vs a context dump
- Generates index, glossary, cheatsheet
- PDF, EPUB, DOCX and more
Installation
Install as an agent skill via git clone into your skills folder. Claude Code:
git clone https://github.com/virgiliojr94/book-to-skill.git ~/.claude/skills/book-to-skill
GitHub Copilot CLI:
git clone https://github.com/virgiliojr94/book-to-skill.git ~/.copilot/skills/book-to-skill
(then run /skills reload in copilot)
Separately, pip install book-to-skill installs only the extraction CLI and does NOT register the skill.
How to Use
In an agent session, point it at a file, folder, or glob:
/book-to-skill <paths…> [skill-name-slug]
e.g. /book-to-skill ~/books/ddia.pdf builds a skill; then use it like any skill: /designing-data-intensive-apps replication finds and explains a topic, /… ch05 dives into chapter 5. Supported formats: PDF, EPUB, DOCX, TXT, Markdown, reStructuredText, AsciiDoc, HTML, RTF, MOBI/AZW.
Requirements
An agent that supports the Agent Skills standard (Claude Code, GitHub Copilot CLI, or Amp). Plain text/Markdown/reStructuredText/AsciiDoc need no extra deps; PDF needs one of pdftotext (poppler), pypdf, pdfminer.six, or docling, and EPUB needs ebooklib + beautifulsoup4 (stdlib zipfile as fallback). Run python3 scripts/extract.py --check to see what's missing.
Related Skills