No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by kangarooking · Agent Tool · ★ 10.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is cangjie-skill safe to install? View the security audit →
Cangjie Skill 把书、长视频、播客里的方法论，蒸馏成可调用的 AI Skills 读完、看完、听完之后，带走一套能调用的方法论。 官方网站 🌐 访问 Cangjie Skill 官方网站 官网提供 Skill Packs 可视化浏览、从零开始的使用教程、Skill 详情与生态共建提交入口。GitHub 仓库仍是 cangjie-skill 代码、方法论和模板的唯一来源，官网负责展示、导航与使用指引。 DeepSeek Harness 插件 cangjie-skill 同时提供独立的 DeepSeek Harness 插件安装包。适配层封装在 Release 安装包中，不会向本仓库加入特定平台的包装文件。 已安装 DeepSeek Harness 后，运行： 下载 DeepSeek Harness 插件（适配仓颉 Skill v2.0.0） 启动新任务后，可以直接说： 为什么做这件事 最近有一个很火的 ide
| Stars | 9,988 |
| Forks | 1,156 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 63.2332310217071/100 |
| Open Issues | 18 |
| Last Updated | 2026-09-13 |
| Created | 2026-04-16 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with cangjie-skill for enhanced workflows:
Looking for a cangjie-skill alternative? If you're comparing cangjie-skill with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome t
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answer
Agent skill that removes signs of AI-generated writing from text
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
An autonomous agent that conducts deep research on any data using any LLM providers
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable re
Explore other popular agent tool tools:
cangjie-skill is 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）. It is categorized as a Agent Tool with 10.0k GitHub stars.
cangjie-skill is primarily written in Python. It covers topics such as agent-workflows, ai-skills, automation.
You can find installation instructions and usage details in the cangjie-skill GitHub repository at github.com/kangarooking/cangjie-skill. The project has 10.0k stars and 1156 forks, indicating an active community.
cangjie-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to cangjie-skill on Agent Skills Hub include colleague-skill, headroom, humanizer. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: