arbor
Claude Code 技能未实测
「arbor」是 K-Dense-AI 发布的Claude Code 技能(Skill),归入「数据与分析」分类。源码托管在 GitHub 仓库 K-Dense-AI/claude-scientific-skills(53.6k 星,MIT license 许可),最近更新于 2026-10-19。将技能目录复制到 ~/.claude/skills/ 即可在所有项目中使用。
Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI安装
把技能目录复制到个人技能目录(或项目内的 .claude/skills/):
git clone --depth 1 https://github.com/K-Dense-AI/claude-scientific-skills.git /tmp/claude-scientific-skills
cp -r /tmp/claude-scientific-skills/skills/arbor ~/.claude/skills/ 信息
| 源码 | https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/skills/arbor |
|---|---|
| GitHub Stars | 53.6k (所在仓库) |
| 许可证 | MIT license |
| 最近更新 | 2026-10-19 |
| 分类 | 数据与分析 |