gitwtfhub

wtf is cangjie-skill?

kangarooking/cangjie-skill — explained in plain English

Analysis updated 2026-08-13

7,635PythonAudience · developerComplexity · 3/5LicenseSetup · moderate

TL;DR

Cangjie Skill turns long books, videos, and podcasts into structured, verifiable AI skills that agents like Claude Code can call on.

Mindmap

mindmap
  root((Cangjie Skill))
    What it does
      Book to skill
      Video to skill
      Podcast to skill
    Tech stack
      Python
      Claude Code
      OpenClaw
    Use cases
      Reasoning distillation
      Skill libraries
      Stress testing
    Audience
      Developers
      AI skill builders
      Researchers

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Turn a book or long interview transcript into a reusable, structured AI skill.

REASON 2

Build a library of verified reasoning frameworks an agent can call during real tasks.

REASON 3

Distill lengthy podcast or YouTube transcripts into skills instead of plain summaries.

REASON 4

Stress test generated skills with built-in trick question test cases before using them.

What's in the stack?

PythonClaude CodeOpenClaw

How it stacks up

kangarooking/cangjie-skillpaddlepaddle/erniewiseodd/generative-models
Stars7,6357,7207,496
LanguagePythonPythonPython
Setup difficultymoderatehardmoderate
Complexity3/54/53/5
Audiencedeveloperresearcherresearcher

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · moderate Time to first run · 1h+

Requires feeding it long source transcripts and running a multi-stage extraction pipeline.

You can use and modify it, but if you run a modified version as a network service, you must share your source code with users of that service.

Wtf does this do

Cangjie Skill is a Chinese-language project that turns the reasoning found inside books, long videos, and podcasts into structured AI skills that an agent like Claude Code can actually call on. The idea builds on a related project called nuwa skill, which distills a specific person's way of thinking into a usable skill. Cangjie Skill focuses instead on distilling the systematic reasoning that a person has already written down or spoken at length, such as in a book, a long interview, a podcast episode, or a long form video. The problem it addresses is a common one. People read many books, watch many videos, and listen to many podcasts, but struggle to actually apply what they learned at the moment a real decision needs to be made. Summaries and notes tend to compress information without making it something an agent can reliably call up and use. The tool works through a seven stage pipeline it calls RIA-TV++. It first analyzes a whole piece of content using a structured reading method, then runs five parallel extractors that pull out candidate frameworks, principles, cases, counterexamples, and terminology. Each candidate has to survive three checks, including independent verification within the source and the ability to answer new questions the source never directly addressed. Only 25 to 50 percent of candidates typically pass. Surviving material is then built into a structured skill file with clear sections for the original quote, a rewritten explanation, book examples, future trigger scenarios, executable steps, and known boundaries. The project also generates a stress test set of trick questions for each skill and links related skills together. The repository already includes many generated skill packs distilled from sources such as Warren Buffett's shareholder letters, Robert Cialdini's Influence, and various Chinese business and philosophy texts, each represented as its own linked GitHub repository. The project is licensed under GNU AGPL v3 and is built to work with platforms like Claude Code and OpenClaw.

Yoink these prompts

Prompt 1
Help me run the RIA-TV++ pipeline on a book transcript to generate a skill pack.
Prompt 2
Explain how the five parallel extractors in Cangjie Skill work and what each one pulls out.
Prompt 3
Show me how to install a generated skill pack into Claude Code's skills directory.
Prompt 4
Walk me through the triple verification step that filters candidate frameworks.

Frequently asked questions

wtf is cangjie-skill?

Cangjie Skill turns long books, videos, and podcasts into structured, verifiable AI skills that agents like Claude Code can call on.

What language is cangjie-skill written in?

Mainly Python. The stack also includes Python, Claude Code, OpenClaw.

What license does cangjie-skill use?

You can use and modify it, but if you run a modified version as a network service, you must share your source code with users of that service.

How hard is cangjie-skill to set up?

Setup difficulty is rated moderate, with roughly 1h+ to a first successful run.

Who is cangjie-skill for?

Mainly developer.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.