Awesome Agent Skills (itgoyo) Model Card
这是可索引项目报告证据页：它保留 Awesome Agent Skills (itgoyo) 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。
Awesome Agent Skills (itgoyo) Model Card
| Field | Value |
|---|---|
| Repository | itgoyo/awesome-agent-skills |
| Category | Cross-Platform Agent Skills Resource Index |
| Stars / forks snapshot | 112 / 10 |
| Language | Markdown |
| License | CC-BY-4.0 (README declared) |
| Raw capture | raw-github/itgoyo_awesome-agent-skills.md |
| Updated by | hourly public metadata update, 2026-05-29 16:12 +0800 |
1. Role in Self Evolve
itgoyo/awesome-agent-skills is a cross-runtime skills index covering Claude Code, Codex, Gemini CLI, Cline, Cursor and MCP-oriented skill resources. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
curate agent-skill resources across runtimes -> map official and community skill ecosystems -> link install/readme paths -> help teams bootstrap reusable skill workflows quickly
3. Evidence Path
web-observed GitHub page showed 112 stars, 10 forks, 4 commits, and README sections for multi-runtime skill resources; repository license was not explicit in metadata but README includes a CC BY 4.0 note. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Cross-Platform Agent Skills Resource Index: it shows how harness/runtime/benchmark layers convert agent behavior into reproducible and auditable engineering workflows.
5. Limits
The repository was not cloned in this iteration; no benchmark run, plugin install, workflow execution, or agent loop experiment was executed. Counts and claims are visible public-page/search signals unless independently revalidated later.