cangjie-skill
cangjie-skill distills books, long-form videos, podcasts, and courses into atomic, executable skills for AI agents. It follows a five-stage pipeline including Adlerian understanding, parallel extraction, triple verification, Zettelkasten linking, and pressure testing to ensure skills are reusable and actionable.
Is cangjie-skill safe to install?
Review before installing: our audit of cangjie-skill's source files found 0 shell commands, 0 external URLs, file reads and writes (medium risk). Every command and URL listed appears verbatim in the skill's source. The skill reads local files provided by the user and writes multiple files to the local directory, including pipeline states, skill definitions, and test results.
How we audit skills: our security review methodology.
Who is this skill for?
Users who want to convert long-form content like books, video transcripts, or courses into structured, atomic skills that an AI agent can invoke in real-world scenarios.
What can you do with it?
- Distilling a book into a set of decision frameworks or principles.
- Converting a video transcript or podcast into reusable agent skills.
- Creating atomic skills from course materials or interview transcripts.
- Building a structured knowledge base from long-form content for agent automation.
How good is this skill?
Quality score: 5/10. The skill provides a highly structured, rigorous, and verifiable pipeline for knowledge extraction. It includes clear boundaries, audit trails, and compatibility with other agent tools like darwin-skill.
What does the skill file contain?
# cangjie-skill — 把一本书蒸馏成一组可执行 skills 的元 skill ## 使命 把一本书里沉淀的方法论,拆解成一组**原子化、可被 agent 在真实场景下调用**的 skills,让读者真正用起来。 > **术语约定**: 本文档及 `methodology/`、`extractors/` 中所有的"书",泛指一切被蒸馏的长内容 — 书籍、长视频转写、播客文字稿、课程、访谈、长文、资料集。 **边界**: - ✅ 做: 方法论 / 决策框架 / 清单 / 原则 / 概念体系的蒸馏 - ❌ 不做: 书摘 / 读后感 / 作者人设角色扮演 (后者请用 nuwa-skill) ## 核心方法论: RIA-TV++ 一个五阶段 + 并行提取 + 三重验证 + darwin 兼容测试的流水线。详见 `methodology/00-overview.md`。 ``` 阶段 0: Adler 整书理解 → BOOK_OVERVIEW.md 阶段 1: 5 个 agent 并行提取 → 候选方法论单元池 阶段 1.5: 三重验证筛选 → 通过的单元 (用户轻确认) 阶段 2: RIA++ 构造 skill → 每个 skill 的 SKILL.md 阶段 3: Zettelkasten 链接 → INDEX.md + GL...
Frequently asked questions
What content formats does this skill support?
It supports books, long-video transcripts, podcasts, courses, interviews, long articles, and data collections provided as PDF, EPUB, TXT, or subtitle files.
How does this differ from nuwa-skill?
cangjie-skill focuses on distilling methodologies, frameworks, and principles from content, whereas nuwa-skill focuses on distilling a person's persona, thinking style, and expression.
Can I resume the process if it gets interrupted?
Yes. The skill uses a PIPELINE_STATE.md file to track progress. Before starting, it checks this file to resume from the last completed stage.
What happens if I do not have the source text?
The skill requires the source text to function. It does not distill content from memory and will prompt the user to provide the text or file path.
Related skills
lark-workflow-meeting-summary
219.7KUsers who need to summarize meeting minutes, generate weekly reports, or review meeting history within the Lark ecosystem
The lark-workflow-meeting-summary skill provides a structured workflow for agents to aggregate meeting minutes from Lark VC, generate summaries, and create or update reports in Lark Docs.
caveman-commit
214.4KDevelopers who want to maintain clean, terse, and informative git commit histories
The caveman-commit skill generates concise commit messages following the Conventional Commits specification. It prioritizes the reasoning behind changes over the description of the changes themselves.
browser-act-skill-forge
64.0KUsers who need to automate data collection or website interactions at scale and want to convert manual browser workflows into reusable, agent-executable skills
browser-act-skill-forge automates the creation of reusable AI agent skills by exploring websites to identify API endpoints or DOM extraction methods. It generates standardized SKILL.md files and Python scripts, enabling agents to perform data extraction or site operations reliably without re-exploring the target site.
notion-api
52.2KDevelopers and AI agents requiring programmatic access to Notion workspaces
This skill provides instructions for interacting with the Notion REST API. It enables agents to read, create, update, and delete Notion pages, databases, blocks, and comments using curl and jq.