AI Research SKILLs Model Card
这是可索引项目报告证据页：它保留 AI Research 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。
AI Research SKILLs Model Card
| Field | Value |
|---|---|
| Repository | Orchestra-Research/AI-research-SKILLs |
| Category | Agent Research Skill Library |
| Stars / forks snapshot | 8.9k / 679 |
| Language | Markdown |
| License | MIT |
| Raw capture | raw-github/orchestra-research_ai-research-skills.md |
| Updated by | hourly public metadata update, 2026-05-26 06:45 +0800 |
1. Role in Self Evolve
AI Research SKILLs is not an autonomous evolution algorithm by itself. It is relevant because it turns research workflow knowledge into installable agent skills, which can become the reusable know-how layer for self-improving research agents.
2. Working Principle
research objective -> autoresearch orchestration -> domain skills for ideation, experiments, evaluation, prompting and paper writing -> reusable agent research workflow
3. Evidence Path
Web-observed GitHub evidence showed 8.9k stars, 679 forks, 213 commits, MIT licensing, and 98 skills across 23 categories. The README describes installer support for Claude Code, Hermes Agent, OpenCode, Cursor, Gemini CLI and related coding-agent environments.
4. Teaching Use
Use this card to explain the skills-as-assets layer: self-evolving agents need more than memory and evaluators; they also need portable procedural knowledge that can be installed, versioned, reviewed, and reused across sessions.
5. Limits
The repository was not cloned or executed locally. Metadata is web-observed from the public GitHub page, not authenticated GitHub API data.