Scientific Agent Skills Model Card
这是可索引项目报告证据页：它保留 Scientific 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。
Scientific Agent Skills Model Card
| Field | Value |
|---|---|
| Repository | K-Dense-AI/scientific-agent-skills |
| Category | 科研 Agent Skills 工作流库 |
| Stars / forks snapshot | 25,500 / 2700 |
| Language | Python |
| License | MIT |
| Raw capture | raw-github/k-dense-ai_scientific-agent-skills.md |
| Updated by | hourly public metadata update, 2026-05-24 |
1. Role in Self Evolve
K-Dense 的 Scientific Agent Skills 把生物、化学、医学、材料、地理、数据分析等科研工具和数据库组织为可安装技能，面向 AI co-scientist 工作流。
2. Working Principle
科研任务域 -> 技能包/数据库接口 -> 多步科学工作流
3. Evidence Path
web GitHub page observed 138 ready-to-use scientific/research skills, 78+ database lookup claim, security disclaimer/scanner guidance, MIT license, releases, and public star/fork snapshot; 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。