jakenuts Agent Skills Model Card
这是可索引项目报告证据页：它保留 jakenuts Agent 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。
jakenuts Agent Skills Model Card
| Field | Value |
|---|---|
| Repository | jakenuts/agent-skills |
| Category | Agent Skills and Expert-Agent Toolkit |
| Stars / forks snapshot | 0 / 0 |
| Language | Shell/PowerShell/Markdown |
| License | MIT |
| Raw capture | raw-github/jakenuts_agent-skills.md |
| Updated by | hourly public metadata update, 2026-05-25 |
1. Role in Self Evolve
jakenuts Agent Skills 是面向 Claude Code 与 OpenAI Codex CLI 的技能和专家 agent toolkit，用 init 脚本部署 skills/agents，并通过分层专家定义控制上下文成本。
2. Working Principle
skill definitions + expert agents -> init detector -> deploy to Claude/Codex dirs -> on-demand dependencies and specialist invocation
3. Evidence Path
web GitHub page observed 47 commits, MIT license, 0 stars and 0 forks; README says unified Agent Skills plus Expert Agent definitions compatible with Claude Code and OpenAI Codex CLI, with init scripts, bundled tools, hierarchical expert agents, and supported Codex skill/agent directories. 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 and Expert-Agent Toolkit 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、memory experiments、agent evolution loops 或 production deployments；star/fork/commit 快照来自公开 GitHub 页面文本或可见页面片段。