book-to-skillGitHub
SKILL.mdREADMEReleasesPerformanceSecurity

README.md

Turn any technical book into an agent skill

Install once, convert books and docs you already own, then query frameworks and chapters on demand with 24x to 51x fewer tokens than dumping the book into context.

View source on GitHub

Why it exists

Searching a PDF returns pages. Asking an agent about a book risks hallucination. Notes you never reopen don't help either. book-to-skill turns the book into a structured skill your agent loads when you need it.

Works with any host that supports the open Agent Skills standard. GitHub Copilot CLI, Amp, and Claude Code all read the same SKILL.md format.

Usage

/book-to-skill <path-to-document-folder-or-glob>... [skill-name-slug]
# Several files → one unified skill
/book-to-skill ~/papers/paper1.pdf ~/notes/export.txt unified-research

# Whole folder
/book-to-skill ~/workspace/project-docs/ project-knowledge

# Glob
/book-to-skill "~/books/*.epub" my-library

# Fold new material into an existing skill
/book-to-skill ~/articles/new-paper.pdf ~/.claude/skills/project-knowledge

After conversion, use the generated skill like any other:

/designing-data-intensive-apps
/designing-data-intensive-apps replication
/designing-data-intensive-apps ch05

Install, two paths

Do not confuse them: cloning into a skills folder registers the /book-to-skill agent skill. pip install only installs the extraction CLI.

As an agent skill (recommended)

# GitHub Copilot CLI
git clone https://github.com/virgiliojr94/book-to-skill.git ~/.copilot/skills/book-to-skill

# Cross-agent (Copilot + Amp)
git clone https://github.com/virgiliojr94/book-to-skill.git ~/.agents/skills/book-to-skill

# Claude Code
git clone https://github.com/virgiliojr94/book-to-skill.git ~/.claude/skills/book-to-skill

Standalone CLI (optional)

pip install "book-to-skill[pdf,epub,docx]"
book-to-skill ~/path/to/book.pdf --mode text
book-to-skill --check

Beyond books

  • Internal docs such as ADRs, runbooks, and onboarding guides
  • Brand and design systems such as voice guidelines and component principles
  • Research clusters such as papers plus notes, updated over time
  • Specs and standards such as RFCs, API contracts, and compliance docs

Copyright & fair use

The tool ships no book content. Processing is local. Bring files you own or have the right to read. Generated skills are synthesized notes. Do not redistribute skills of copyrighted third party works.

Check measured savings

See extraction times, discovery loop tax, and one pass generation cost across real books.

Performance & Cost