Summary
Turns a book into a set of executable Claude skills rather than just a summary or book report. You give it the full text (PDF, EPUB, or TXT), and it runs a four-stage pipeline: Adler-style reading for structure, five parallel extractors hunting for frameworks and principles, triple verification to filter out platitudes, then RIA++ templating to build actual skills with trigger conditions and execution steps. Each output skill gets test prompts in darwin-skill format so you can evolve them later. The rejected candidates folder is a nice touch for audit trails. Best for methodology-heavy books where you want the decision frameworks and checklists, not the narrative.
Install to Claude Code
npx -y skills add kangarooking/cangjie-skill --skill book2skill --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
