隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载,只有在你同意后,Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills
这个仓库详情页对访问者有帮助,但在补足原创证据和对比上下文前,Git-Stars 会暂时避免让它进入搜索索引。
75
评测分
解决的问题
It solves the problem of converting unstructured, lengthy content into structured, actionable skills for AI agents, bypassing the need for manual prompt engineering or fine-tuning.
部署现实
当前可用的安装信号是:Clone the repo and run `pip install -r requirements.txt`.。这只能作为起点,正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 AGPL-3.0。这是重要的商业使用信号,但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build agents that automatically extract key insights from books or videos and execute tasks like summarization, Q&A, or decision-making based on that knowledge. Real-world use cases include creating study assistants, content curation bots, or domain-specific expert agents. The ceiling is limited only by the quality of source content and the agent's underlying model.
Git-Stars 是独立产品,不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成,依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
kangarooking/cangjie-skill 被追踪为 Python 项目,主要属于 Automation, AI Agent, LLM Tool 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则,而不是复制项目文档。
增长检查:该仓库目前有 8.0k Star,今日 +0,本周 +0,本月 +4.9k。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查:当前活跃度为 一般;最近一次推送距今 66 天,未关闭 Issue 为 13,约占总 Star 的 0.16%。这只是采用信号,不替代工程尽调。
采用检查:961 Fork 和 8.0k Watcher 反映项目被复用和关注的程度。许可证信号:AGPL-3.0。商业或内部使用前请核验许可证兼容性。
适用判断:当你需要「Python 技术栈团队评估生态原生工具」时,这个项目更值得评估;如果「需要法律审查、安全审计或生产 SLA 保证」,则需要谨慎。
来源检查:Git-Stars 当前为这份报告保留了 1 个明确来源引用,近期增长信号为 4.9k。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
不足需要更清晰的来源引用。
许可证
充分已记录 AGPL-3.0,可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
8.0k 星标
复用
961 复刻
关注
8.0k 关注者
维护
moderate
许可证
AGPL-3.0
未解决 Issue
13
Cangjie Skill is an AI agent framework that distills high-value content like books, long videos, and podcasts into executable agent skills, enabling agents to perform complex tasks based on curated knowledge.
Automation
Workflow automation, integration glue, and orchestration
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
Clone the repo and run `pip install -r requirements.txt`.63
健康评分
一般
提交活跃度
Apr 16, 2026
创建于
Aug 9, 2026
最近提交
每日同步积累数据后,Star 历史将在此显示。
复刻
未解决
关注者
kangarooking
GitHub 主页obra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
It solves the problem of converting unstructured, lengthy content into structured, actionable skills for AI agents, bypassing the need for manual prompt engineering or fine-tuning.
能力范围
Developers can build agents that automatically extract key insights from books or videos and execute tasks like summarization, Q&A, or decision-making based on that knowledge. Real-world use cases include creating study assistants, content curation bots, or domain-specific expert agents. The ceiling is limited only by the quality of source content and the agent's underlying model.
结论
This is ideal for developers who want to quickly turn rich content into agent capabilities without manual prompt crafting. Avoid if you need real-time or dynamic knowledge. The key trade-off is dependency on static content distillation.