darwin-skill
darwin skill
What it does
- 维度1-7、9：每个维度打 1-10 分，乘以权重得到该维度得分
- 维度8（实测表现）：跑2-3个测试prompt，按输出质量打1-10分
- 总分 = Σ(维度分 × 权重) / 10，满分100
- 改进后总分必须 严格高于 改进前才保留
- SkillLens 发现 LLM-as-judge 准确率仅 46.4%（接近随机），加入 meta-skill 三维度后升到 73.8%
- 本机对 huashu-research 做 4 类 degradation → 5 个独立 judge 盲测一致 V1>V2，Δ 均值 +46.5（5/5 high confidence）
- 输出是否完成了用户意图？
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
darwin-skill FAQ
What does the darwin-skill skill do?
Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions \"优化skill\", \"skill评分\", \"自动优化\", \"auto optimize\", \"skill质量检查\", \"达尔文\", \"darwin\", \"帮我改改skill\", \"skill怎么样\", \"提升skill质量\", \"skill review\", \"skill打分\". 维度1-7、9：每个维度打 1-10 分，乘以权重得到该维度得分 维度8（实测表现）：跑2-3个测试prompt，按输出质量打1-10分
How do I install darwin-skill?
Run: npx -y skills add https://github.com/alchaincyf/darwin-skill --skill darwin-skill --agent claude-code — the source lives at github.com/alchaincyf/darwin-skill.
Maintain darwin-skill?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/alchaincyf-darwin-skill-darwin-skill?ref=badge) npx agentictools info skills/alchaincyf-darwin-skill-darwin-skill The second line is the CLI lookup for this page — handy in READMEs and docs.
