darwin-skill skillA
darwin-skill is agent-read markdown (skill) from kingxiaozhe/cm-workflow: 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 diminis.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Darwin Skill 2.0 > **v2.0 · 2026-05-28** — 吸收 Microsoft Research SkillLens（arXiv 2605.23899）的 9 维评分药方 + SkillOpt（arXiv 2605.23904）的 validation-gated 验证机制 + human in the loop 三层守关。 > > 借鉴 Karpathy autoresearch 的自主实验循环，对 skills 进行持续优化。 > 核心理念：**评估 → 改进 → 实测验证 → 人类确认 → 保留或回滚 → 生成成果卡片** > GitHub: https://github.com/alchaincyf/darwin-skill --- ## 设计哲学 autoresearch 的精髓： 1. **单一可编辑资产** — 每次只改一个 SKILL.md 2. **双重评估** — 结构评分（静态分析）+ 效果验证（跑测试看输出） 3. **棘轮机制** — 只保留改进，自动回滚退步 4. **独立评分** — 评分用子agent，避免「自己改自己评」的偏差 5. **人在回路** — 每个skill优化完后暂停，用户确认再继续 与纯结构审查的区别：不只看 SKILL.md 写得规不规范，更看改完后**实际跑出来的效果是否更好**。 --- ## 评估 Rubric（9维度，总分100） > **设计依据**：基于 SkillLens 论文（arXiv 2605.23899）实证发现——LLM-as-judge 评估 skill 质量准确率仅 46.4%（接近随机），加入 meta-skill 三维度后提升到 73.8%。本 rubric 强化 dim3 / dim5 评分标准，新增 dim9「反例与黑名单」，权重平衡到 100。**目的：让评分对真实质量更敏感，减少 LLM judge 的乐观偏差。** ### 结构维度（59分）— 静态分析 | # | 维度 | 权重 | 评分标准 | |---|------|------|---------| | 1 | **Frontmatter质量** | 7 | name规范、description包含做什么+何时用+触发词、≤1024字符、**禁结尾加"灵活应用/根据情况判断"等空话尾巴** | | 2 | **工作流清晰度** | 12 | 步骤明确可执行、有序号、每步有明确输入/输出 | | 3 | **失败模式编码** | 12 | **必须显式编码失败模式**（写出"如果 X 失败 → Y"的明确分支）；有fallback路径、错误恢复；**只写正向流程而不写失败分支扣 ≥3 分**（SkillLens meta-skill 维度） | …
Read the whole file at its exact version.
How to install
mdr add kingxiaozhe/cm-workflow/darwin-skill@git:20260716.3ee7e6cmdr add kingxiaozhe/cm-workflow/darwin-skill@sha256:c3220018f42a3d4cPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_dtlukcnndma3w3vo)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (26528 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kingxiaozhe/cm-workflow · 29 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dtlukcnndma3w3vo GET https://markdownregistry.com/api/v1/resolve?ref=kingxiaozhe/cm-workflow/darwin-skill GET https://markdownregistry.com/api/v1/blob/c3220018f42a3d4cfb242c449df47fd72907670b52d5f00a59179065837044a8
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from kingxiaozhe/cm-workflow
Every file in kingxiaozhe/cm-workflow