Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This tool converts various document formats, including PDF and EPUB, into structured agent skills. It extracts frameworks, mental models, principles, and anti-patterns from source texts to make them accessible via CLI agents.
It is designed for users who want to apply an author's specific methodology while working or build a reusable knowledge base that can be queried by coding assistants.
WHO IT'S FOR
AI agent power users
convert technical books into actionable agent skills
Self-taught engineers
study technical frameworks via AI coding assistants
Knowledge management specialists
build reusable knowledge bases from technical files
AI automation builders
integrate author-specific precision into agent workflows
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
I’m using
Cross-host skills CLI
Installs: Complete book-to-skill agent skill, including scripts/extract.py and tools, for every compatible host selected through the skills CLI. · Claude Code, GitHub Copilot CLI, Amp, Codex, Hermes Agent, OpenClaw
Run this terminal command and select the compatible hosts where the complete skill should be installed.
Installs: Complete book-to-skill agent skill exposed to Codex from an existing local checkout through the shared skills folder. · OpenAI Codex
Before you start
An existing local checkout of the book-to-skill repository.
In this terminal command, replace `/path/to/book-to-skill` with the path to the existing local book-to-skill checkout, while leaving the destination unchanged.