Book-to-Skills Distiller

Name: Book-to-Skills Distiller
Author: kangarooking

By kangarooking· kangarooking/cangjie-skill· 0

Extract actionable frameworks and methodologies from books into reusable Claude skills.

Installation

1
Make sure Claude is on your device and in your terminal.
Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.
One-time setup
```
npm i -g @anthropic-ai/claude-code
```
Already have it? Skip ahead.

Paste into Claude Code or into your terminal.

Install

git clone ht••••••••••••••••••••••••••••••••••••••••••••••• •••••••••••••••••••••••••••••••• •• ••••• •• ••••••••••••••••••••••••••••••••••••••••••• •• •• •• •••••••••••••••••••••••••••••••••••• ••••••••••••••••••••••••••••••••••••••••••••

This copies the whole skill folder into ~/.claude/skills/cangjie-skill-kangarooking/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

Faster alternative (instruction-only skills)

Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

Quick install (SKILL.md only)

mkdir -p ~/.•••••••••••••••••••••••••••••••••••••••• •• •••• ••••• •••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••• •• ••••••••••••••••••••••••••••••••••••••••••••••••••••

Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.
Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Use when you want a book, long-video transcript, podcast, course, or interview distilled into skills — extracts the frameworks, principles, and methodologies into atomic, reusable Claude skills an agent can invoke. Not for simple summaries, book reviews, or role-playing the author.

What this skill does

This skill distills long-form content—books, video transcripts, podcasts, courses, interviews—into atomic, reusable Claude skills that agents can invoke in real scenarios. Rather than producing summaries or author impersonations, it extracts methodologies, frameworks, principles, and decision models into executable skill sets organized for practical use.

What it does

Parallel framework extraction — Five specialized sub-agents (framework, principle, case, counter-example, and glossary extractors) independently analyze the source material and identify candidate methodology units.
Triple-verification filtering — Validates each candidate against cross-domain evidence, predictive power, and uniqueness before advancing to skill construction.
RIA++ skill construction — Builds each skill with Reading (original quotes), Interpretation (methodology restatement), Past Application (author examples), Future Trigger (when users need it), Execution (1–2–3 steps), and Boundary (limitations).
Zettelkasten linking — Maps skill relationships, generates cross-references, and produces a shared glossary and index with dependency diagrams.
Darwin-compatible pressure testing — Designs 5–10 test prompts per skill, including decoy scenarios and cross-skill confusion tests, then iterates on failures.
Delivery pipeline — Generates a reader-facing digest and installs passing skills to the user's skill directory.

How to use it

Provide the skill with the source material (PDF, EPUB, TXT, transcript, or plain text) and confirm three inputs: the content's text source and metadata (title, author, publication date for books; title, creator, and date for video/podcast/course), and whether this is your first trial run. The skill then executes a five-stage plus verification pipeline, updating progress at each checkpoint and pausing for user confirmation before the most time-intensive phases.

Note: this skill's internal instructions are written in Chinese. Claude reads them natively and will work with you in English.

Related skills

Learn Mistake

ilang-ai

Record and check past mistakes to avoid repeating them in similar tasks.

Pattern Learner

ilang-ai

Detect recurring patterns in your project and apply them automatically next time.

Learn Preference

ilang-ai

Remember your coding style and apply it automatically to future work.

Persistent Memory

a5c-ai

Store and retrieve decisions, discoveries, and patterns across chat sessions.