Randroids Dojo Skills Model Card
这是可索引项目报告证据页：它保留 Randroids Dojo 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。
Randroids Dojo Skills Model Card
| Field | Value |
|---|---|
| Repository | Randroids-Dojo/skills |
| Category | Agent Skill Loop Library |
| Stars / forks snapshot | 33 / 2 |
| Language | HTML/Shell/Python |
| License | MIT |
| Raw capture | raw-github/randroids-dojo_skills.md |
| Updated by | hourly public metadata update, 2026-05-24 |
1. Role in Self Evolve
Randroids Dojo Skills 是面向 Claude Code、Codex CLI 和 OpenCode 的双格式技能库，把 randroid-loop、task tracking、game-dev skills 和 spiral scaffold 组织成可安装的 agent skill bundle。
2. Working Principle
skill bundle -> plugin manifest -> Codex/Claude/OpenCode discovery -> reusable autonomous loop -> cross-agent install path
3. Evidence Path
web GitHub page observed 48 commits, MIT license, dual-format Claude Code/Codex/OpenCode skills, .agents/.codex compatibility paths, 33 stars and 2 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 Skill Loop Library 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 或 production deployments；star/fork/commit 快照来自公开 GitHub 页面文本或可见页面片段。