automation

cangjie-skill: Turn Books, Videos & Podcasts into Actionable AI Agents

Name: cangjie-skill: Turn Books, Videos & Podcasts into Actionable AI Agents
Author: kangarooking

Founder can instantly convert high‑value content into ready‑to‑run agent skills, speeding up product knowledge and automation. Python‑based, 11k+ GitHub stars.

From the repo · “把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills（Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills）”

11,562 stars+244★ this week1,343 forksPythonGuide quality 8/10 · reviewed Oct 9Updated 10/2/2026100% free · open source

What it does

Cangjie-skill extracts executable skills from books, long videos, and podcasts, allowing founders to automate and integrate AI workflows

When to use it

•When you need to automate workflows based on knowledge from long-form content
•When integrating AI into your workflow requires specific, actionable skills
•When you want to leverage high-value content from various sources for executable insights

Ready-to-paste prompt

Create a new Agent Skill for a book by running a command similar to the examples in the README, customized with your specific book details

Heads up: Ensure you have the necessary permissions and access rights to the content you're trying to extract skills from, as cangjie-skill may require specific licenses or APIs to function correctly

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/cangjie-skill && curl -fsSL https://workflowstacks.com/api/skills/cangjie-skill/claude-skill -o ~/.claude/skills/cangjie-skill/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How cangjie-skill: Turn Books, Videos & Podcasts into Actionable AI Agents works

Codeflow

Free to inspect

Cangjie-skill: Turn Books, Videos & Podcasts into Actionable AI Agents is mostly documents (174 doc files, 29 small scripts) — something you read, not something you run. You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license.

Size

Mostly documents

174 documents · 29 small scripts · ~4 h to skim

Setup

Install as a skill / plugin

Add it to Claude Code (or your AI tool) with one command — 28 skills inside. Nothing to run yourself.

Runs on

Inside your AI tool

Nothing to install on your machine

Python 58%Astro 29%TypeScript 8%CSS 3%JavaScript 2%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
SKILL.md
The instructions the AI actually follows

What's in each folder

docs/Documentation9 files

templates/Templates5 files

books/Folder96 files

benchmarks/Evaluations & benchmarks83 files

registry/Folder22 files

website/Project website22 files

scripts/Helper scripts18 files

schemas/Data models & types13 files

READMEHas testsDocumentedCI checksMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/cangjie-skill && curl -fsSL https://workflowstacks.com/api/skills/cangjie-skill/claude-skill -o ~/.claude/skills/cangjie-skill/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

kangarooking

Language

Python