Hugging Face Skills Model Card
这是可索引项目报告证据页：它保留 Hugging Face Skills Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
Hugging Face Skills Model Card
| Field | Value |
|---|---|
| Repository | huggingface/skills |
| Category | Agent Skills Registry |
| Stars / forks snapshot | 10600 / 681 |
| Language | Python |
| License | Apache-2.0 |
| Raw capture | raw-github/huggingface_skills.md |
| Updated by | hourly public metadata update, 2026-05-24 |
1. Role in Self Evolve
huggingface/skills 是 Hugging Face 生态的 Agent Skills 仓库，提供 Codex、Claude Code、Gemini CLI、Cursor 可用的 HF CLI、数据集、评测、训练、论文发布等技能包。
2. Working Principle
AI/ML task domain -> SKILL.md package -> agent marketplace/install path -> reusable HF workflow execution
3. Evidence Path
web GitHub page observed 285 commits, Apache-2.0 license, Python primary language, Codex/Claude/Gemini/Cursor compatibility, Agent Skills standard, 10.6k stars and 681 forks. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Agent Skills Registry in the raw -> classification -> project card -> site/report pipeline. The reading path is: raw capture -> classification row -> public site card -> project report -> aggregate GitHub analysis.
5. Limits
当前未克隆源码，未运行 benchmark、SDK examples、skill install flows 或 memory experiments；star/fork/commit 快照来自公开 GitHub 页面文本或可见页面片段。