kangarooking/cangjie-skill
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)
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
3 releases in the last 90 days, the latest 67 days ago, with 6 contributors on GitHub.
Peaked at #94 in the weekly ranking the week of Jul 12, its best in the past year.
Use Cases & Benefits
- Distills high-value content from books, videos, and podcasts into structured, executable AI agent skills using a rigorous multi-stage pipeline.
- Enables practical reuse of complex methodologies by converting raw content into independently callable, composable, and testable AI skills rather than simple summaries.
- Use for transforming lengthy educational videos or podcasts into actionable AI skills for real-time knowledge application.
- Use for extracting and structuring core methodologies from books to build reusable skill toolkits for AI agents.
- Use for creating verified, scenario-driven AI skills that support decision-making and problem-solving in automated workflows.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
读完、看完、听完之后,带走一套能调用的方法论。
最近有一个很火的 idea:把同事蒸馏成 skill。即便一个人离职了,他的经验、语气、工作方式都会被 AI 一定程度替代。nuwa-skill 就是做这件事的——创造"人类 skill",比如马斯克 skill、巴菲特 skill。配套的 darwin-skill 负责让这些 skill 自动进化。
蒸馏人很有价值——nuwa-skill 已经证明了这一点 。而蒸馏人系统性表达过的内容,则是另一个维度的补充:一本书、一场长访谈、一期播客、一个 B 站或 YouTube 长视频,都可能沉淀了作者花很长时间打磨出来的方法论。比起模仿一个人的表达方式,把他系统性输出的方法论拆出来、变成可以帮人解决实际问题的工具,同样是很有价值的事。
而且还有一个真实的痛点:你可能看了很多书、收藏了很多视频、听过很多播客,但就是运用不起来。尤其是各大平台每天都有大量干货长视频,时效性很强,内容又很长;它们往往不可能已经被 AI 训练过,也很难靠一次观看完整吸收。把这些内容蒸馏成 skill 之后,AI agent 可以帮你在真实场景中调用这些知识,而不是让它们躺在笔记、收藏夹或稍后再看列表里落灰。
所以 cangjie-skill 的目标很明确:蒸馏所有值得蒸馏的高价值内容。它不只适用于书,也适用于有字幕/转写文本的视频、播客、访谈、演讲、课程、长文和资料集。只要内容里存在可抽取、可验证、可迁移的方法论,就可以用 cangjie-skill 把它变成一套可独立调用、可组合使用、可压力测试的 AI skill 工具包。
如果要蒸馏视频内容,建议搭配 video-downloader skill 一起使用:先用它下载视频、提取字幕/音频转写和关键素材,再把得到的文本内容交给 cangjie-skill 做方法论抽取、skill 化和压力测试。
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+5,260 stars over 88 days across 16 snapshot days; best day +260 on Aug 11.
Forks
1.4K+564
Open issues
21+9
Compared with peers in Automation
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| vercel-labs/agent-desktop | 21.4K | +8.7K | 75 | 5 days ago |
| D4Vinci/Scrapling | 101.1K | +6.3K | 75 | 6 days ago |
| harry0703/MoneyPrinterTurbo | 142.0K | +3.8K | 75 | 3 days ago |
| superplanehq/superplane | 9.8K | +1.0K | 75 | 13 days ago |
| gosom/google-maps-scraper | 7.9K | +622 | 75 | 2 days ago |
| kangarooking/cangjie-skill | 12.2K | — | 30 | 67 days ago |
| Category median | 21.4K | +3.8K | 75 | — |
Discover Repositories
Search across tracked repositories by name or description