Agent Skills Directory Model Card
这是可索引项目报告证据页：它保留 Agent Skills Directory 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。
Agent Skills Directory Model Card
| Field | Value |
|---|---|
| Repository | dmgrok/agent_skills_directory |
| Category | Agent 技能发现索引 |
| Stars / forks snapshot | 16 / 2 |
| Language | Python |
| License | MIT |
| Raw capture | raw-github/dmgrok_agent_skills_directory.md |
| Updated by | hourly public metadata update, 2026-05-24 |
1. Role in Self Evolve
AI Agent skills 发现与安装目录，聚合 40+ providers、130+ curated skills，并提供本地质量评分、维护状态和安全扫描。
2. Working Principle
把分散的 agent skills 转成可搜索、可评分、可安装的目录，降低 agent 能力扩展时的发现成本。
3. Evidence Path
web GitHub page observed skill catalog, provider count, quality scoring, and local CLI install paths; shell GitHub API was blocked by DNS and gh auth was invalid, so this run marks freshness as web-page observed rather than API verified.
4. Teaching Use
Use this card to explain whether a repository is a runtime, benchmark, harness-evolution loop, memory/skill substrate, or resource index. The key 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；star/fork/commit 快照来自公开 GitHub 页面文本。