#213 by GitHub stars

alchaincyf/darwin-skill

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 + effective

Testing

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

8a8b66258e3c → 8a8b66258e3c

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 8a8b66258e3c

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 8a8b66258e3c45d6ae4aea39719468c6428fcb0a

6.8kGitHub stars

113stars in 7 days

1skill in this repository

0commits in 30 days

Heat

6.1

Star growth, last 7 daysAhead of 89% of tracked repositories
Star growth, last 24 hoursAhead of 89% of tracked repositories
Rank movement, last 7 daysAhead of 58% of tracked repositories
Commits, last 30 daysAhead of 0% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

darwin-skill /

How it works

darwin-skill

When your agent uses it

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".

What it loads into context

Frontmatter

201 tokens

Always available to the agent

SKILL.md

9,165 tokens

When the skill is activated

Reference documents

10,733 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

设计哲学
评估 Rubric（9维度，总分100）
Runtime 适配性审查（gate 项，独立于 9 维度评分）
自主优化循环
results.tsv 格式
实战 high-leverage 操作（精髓速查）
优化策略库
异常与边界条件
darwin 操作反例黑名单（dim9 应用：darwin 自己优化时不要做的事）
约束规则
使用方式
设计灵感
成果卡片生成（Result Card）

Scripts executed separately

scripts/screenshot.mjs

Files

.gitignoreasset19 bytes
LICENSEasset1,076 bytes
README.mddoc12,172 bytes
README_EN.mddoc12,480 bytes
SKILL.mdcore31,456 bytes
SKILL.mdcore31,456 bytes
SKILL.mdcore31,456 bytes
assets/aso-hero.pngasset55,953 bytes
assets/banner-check.pngasset35,875 bytes
assets/banner-en-check.pngasset32,420 bytes
assets/banner-en.svgasset6,346 bytes
assets/banner.svgasset5,434 bytes
assets/chart-loop-en.htmlasset7,041 bytes
assets/chart-loop-en.pngasset23,150 bytes
assets/chart-loop.htmlasset8,794 bytes
assets/chart-loop.pngasset25,201 bytes
assets/chart-phases-en.htmlasset4,434 bytes
assets/chart-phases-en.pngasset29,951 bytes
assets/chart-phases.htmlasset4,444 bytes
assets/chart-phases.pngasset31,299 bytes
assets/chart-ratchet-en.htmlasset7,479 bytes
assets/chart-ratchet-en.pngasset22,201 bytes
assets/chart-ratchet.htmlasset7,599 bytes
assets/chart-ratchet.pngasset22,730 bytes
assets/chart-rubric-en.htmlasset8,465 bytes
assets/chart-rubric-en.pngasset56,136 bytes
assets/chart-rubric.htmlasset8,421 bytes
assets/chart-rubric.pngasset54,209 bytes
assets/hero.gifasset2,914,686 bytes
assets/result-card-example.pngasset878,511 bytes
docs/index.htmlasset31,461 bytes
references/runtime-neutrality.mddoc5,171 bytes
references/skilllens-evidence.mddoc6,673 bytes
scripts/screenshot.mjsruns3,262 bytes
showcase.htmlasset31,461 bytes
templates/result-card-dark.htmlasset17,861 bytes
templates/result-card-white.htmlasset11,282 bytes
templates/result-card.htmlasset15,834 bytes
templates/result-card.pngasset878,511 bytes
test-prompts.jsonasset1,213 bytes

Read SKILL.md


# Darwin Skill 2.0

> **v2.1 · 2026-06-10** — keep/revert 棘轮从「绝对分数 delta」改为「**paired 同-judge 比较 + 奇数 N 多数决**」（绝对分数 ±8 judge 噪音淹没保守编辑的真实增益、是 false-revert 源；within-judge 比较消除换尺污染）。绝对分数降级为 triage-only。
> **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：

View the complete source on GitHub

Skills included

darwin-skill

Repository facts

License: MIT
Created: Apr 13, 2026
Last pushed: Sep 18, 2026
Forks: 706
Open issues: 5
Project activity: Active

Rank over the last 12 weeks

Now #213 · best #190 · down 4 in 30 days

#209 from Oct 29 to Oct 30
#213 on Oct 31
#212 from Nov 1 to Nov 2
#213 on Nov 3
#214 on Nov 4
#213 since Nov 5

67 earlier periods

#185 on Aug 2
#185 on Aug 7
#184 from Aug 8 to Aug 9
#187 on Aug 10
#188 on Aug 11
#185 on Aug 12
#189 on Aug 13
#190 from Aug 14 to Aug 16
#191 on Aug 17
#193 from Aug 18 to Aug 19
#191 on Aug 20
#193 on Aug 21
#190 on Aug 22
#196 from Aug 23 to Aug 24
#197 from Aug 25 to Aug 26
#198 on Aug 27
#197 on Aug 28
#198 on Aug 29
#197 on Aug 30
#196 on Aug 31
#199 on Sep 1
#193 on Sep 2
#199 on Sep 3
#195 on Sep 4
#197 on Sep 5
#195 on Sep 6
#198 on Sep 7
#199 on Sep 8
#200 from Sep 9 to Sep 10
#198 on Sep 11
#199 from Sep 12 to Sep 13
#200 on Sep 14
#199 from Sep 15 to Sep 16
#201 on Sep 17
#203 on Sep 18
#201 on Sep 19
#205 on Sep 20
#206 from Sep 21 to Sep 24
#205 on Sep 25
#208 on Sep 26
#206 on Sep 27
#208 on Sep 28
#209 on Sep 29
#207 on Sep 30
#209 on Oct 1
#211 on Oct 2
#207 on Oct 3
#205 on Oct 4
#207 on Oct 5
#206 on Oct 6
#209 on Oct 7
#207 on Oct 8
#211 on Oct 9
#208 from Oct 10 to Oct 11
#211 on Oct 12
#212 on Oct 13
#210 on Oct 14
#208 on Oct 15
#206 on Oct 16
#208 on Oct 17
#207 on Oct 18
#208 on Oct 19
#207 from Oct 20 to Oct 21
#205 on Oct 22
#206 from Oct 23 to Oct 24
#209 on Oct 25
#208 on Oct 28

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 2, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 2 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
2 dangerous shell commandsin 2 files: README.md:146 README_EN.md:142
129 network referencesin 19 files: README.md:10 README_EN.md:15 assets/chart-loop-en.html:4 and 16 more
No hidden or obfuscated text
No instruction overrides
1 executable scriptin 1 file: scripts/screenshot.mjs:1
No access to secrets
No requests to vote in Hot

Show all 132 signals by file

`README.md`

Network accessline 10

<img src="assets/hero.gif" alt="Darwin Skill Animation" />   <br/>   <sub>动画由 <a href="https://github.com/alchaincyf/huashu-design">huashu-design</a> skill 制作</sub>

Network accessline 11

<br/>   <sub>动画由 <a href="https://github.com/alchaincyf/huashu-design">huashu-design</a> skill 制作</sub> </p>

Network accessline 12

<sub>动画由 <a href="https://github.com/alchaincyf/huashu-design">huashu-design</a> skill 制作</sub>

Network accessline 21

受 [Andrej Karpathy 的 autoresearch](https://github.com/karpathy/autoresearch) 启发，将自主实验循环从模型训练搬到 Skill 优化领域。一个只能向前转的棘轮。

Network accessline 23

**v2.0** · 更新于 2026-05-28 · 吸收微软研究院 [SkillLens](https://arxiv.org/abs/2605.23899) 与 [SkillOpt](https://arxiv.org/abs/2605.23904) 两篇论文做的系统性升级。

Network accessline 25

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

Network accessline 26

[![Version](https://img.shields.io/badge/version-2.0-blue.svg)](#whats-new-in-20)

Network accessline 27

[![Agent Skill](https://img.shields.io/badge/Agent%20Skill-Compatible-blueviolet)](https://skills.sh)

Network accessline 28

[![Skills](https://img.shields.io/badge/skills.sh-Compatible-green)](https://skills.sh)

Network accessline 29

[![Microsoft SkillOpt](https://img.shields.io/badge/Microsoft_SkillOpt-Listed_Integration-0078D4?logo=microsoft&logoColor=white)](https://github.com/microsoft/SkillOpt)

Network accessline 39

> [!NOTE] > **🤝 微软研究院把达尔文列进了 SkillOpt 的官方集成名单。** > 2026-06-03，微软在 [SkillOpt 仓库](https://github.com/microsoft/SkillOpt) 的更新里写道：

Network accessline 40

> **🤝 微软研究院把达尔文列进了 SkillOpt 的官方集成名单。** > 2026-06-03，微软在 [SkillOpt 仓库](https://github.com/microsoft/SkillOpt) 的更新里写道： > *「gbrain, gbrain-evals, and **darwin-skill** have all integrated SkillOpt.」*

Network accessline 41

> 2026-06-03，微软在 [SkillOpt 仓库](https://github.com/microsoft/SkillOpt) 的更新里写道：

Network accessline 43

> 我们吸收了它的 validation-gated 框架，它把达尔文写进了自己的集成名单。这是一次双向的致意。👉 [去 SkillOpt 仓库看看](https://github.com/microsoft/SkillOpt)

Network accessline 51

**1. 评分标准 8 维 → 9 维**（吸收 [SkillLens](https://arxiv.org/abs/2605.23899) 实证的 73.8% rubric 药方）

Dangerous shell operationline 146

| **高风险行动黑名单** | rm / git reset --hard / force push 等破坏性操作必须明文列禁 |

Network accessline 188

无法访问 GitHub 的朋友，可以直接下载 zip 包：[darwin-skill.zip](https://pub-161ae4b5ed0644c4a43b5c6412287e03.r2.dev/skills/darwin-skill.zip)，解压后把 SKILL.md 放到 `~/.claude/skills/darwin-skill/` 目录即可。

Network accessline 199

这个项目的设计直接受 **Andrej Karpathy 的 [autoresearch](https://github.com/karpathy/autoresearch)** 启发。

Network accessline 203

v2.0 在此基础上吸收了微软研究院 2026-05-22 发布的两篇论文：[SkillLens](https://arxiv.org/abs/2605.23899) 提供了实证验证的 rubric 设计，[SkillOpt](https://arxiv.org/abs/2605.23904) 提供了 validation-gated edits 的形式化框架。

Network accessline 215

- 论文：https://arxiv.org/abs/2605.23899

Network accessline 222

- 🔗 **代码仓库**：[github.com/microsoft/SkillOpt](https://github.com/microsoft/SkillOpt)（`pip install skillopt`，v0.1.0 已上 PyPI）

Network accessline 223

- 项目页：https://microsoft.github.io/SkillOpt/

Network accessline 224

- 论文：https://arxiv.org/abs/2605.23904

Network accessline 232

- 代码：https://github.com/karpathy/autoresearch

Network accessline 241

| | | |:---|:---| | 🌐 官网 | [bookai.top](https://bookai.top) · [huasheng.ai](https://www.huasheng.ai) |

Network accessline 242

|:---|:---| | 🌐 官网 | [bookai.top](https://bookai.top) · [huasheng.ai](https://www.huasheng.ai) | | 𝕏 Twitter | [@AlchainHust](https://x.com/AlchainHust) |

Network accessline 243

| 🌐 官网 | [bookai.top](https://bookai.top) · [huasheng.ai](https://www.huasheng.ai) |

Network accessline 244

| 𝕏 Twitter | [@AlchainHust](https://x.com/AlchainHust) |

Network accessline 245

| 📺 B站 | [花叔](https://space.bilibili.com/14097567) |

Network accessline 246

| ▶<U+FE0F> YouTube | [@Alchain](https://www.youtube.com/@Alchain) |

Network accessline 247

| 📕 小红书 | [花叔](https://www.xiaohongshu.com/user/profile/5abc6f17e8ac2b109179dfdf) |

Network accessline 260

**[女娲](https://github.com/alchaincyf/nuwa-skill)** 造 Skill。<br>

Network accessline 266

MIT License © [花叔 Huashu](https://github.com/alchaincyf)

Network accessline 275

[![FanBox · Coding Agent 的驾驶舱](https://raw.githubusercontent.com/alchaincyf/fanbox/master/assets/promo-banner.jpg)](https://github.com/alchaincyf/fanbox)

`README_EN.md`

Network accessline 15

Inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch). Autonomous experiment loops, applied to skill optimization. A ratchet that only turns forward.

Network accessline 17

**v2.0** · Updated 2026-05-28 · A structural upgrade integrating Microsoft Research's [SkillLens](https://arxiv.org/abs/2605.23899) and [SkillOpt](https://arxiv.org/abs/2605.23904) papers.

Network accessline 19

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

Network accessline 20

[![Version](https://img.shields.io/badge/version-2.0-blue.svg)](#whats-new-in-20)

Network accessline 21

[![Agent Skill](https://img.shields.io/badge/Agent%20Skill-Compatible-blueviolet)](https://skills.sh)

Network accessline 22

[![Skills](https://img.shields.io/badge/skills.sh-Compatible-green)](https://skills.sh)

Network accessline 23

[![Microsoft SkillOpt](https://img.shields.io/badge/Microsoft_SkillOpt-Listed_Integration-0078D4?logo=microsoft&logoColor=white)](https://github.com/microsoft/SkillOpt)

Network accessline 33

> [!NOTE] > **🤝 Microsoft Research lists darwin-skill as an official SkillOpt integration.** > On 2026-06-03, the [SkillOpt repo](https://github.com/microsoft/SkillOpt) noted:

Network accessline 34

> **🤝 Microsoft Research lists darwin-skill as an official SkillOpt integration.** > On 2026-06-03, the [SkillOpt repo](https://github.com/microsoft/SkillOpt) noted: > *"gbrain, gbrain-evals, and **darwin-skill** have all integrated SkillOp

Network accessline 35

> On 2026-06-03, the [SkillOpt repo](https://github.com/microsoft/SkillOpt) noted:

Network accessline 37

> We absorbed its validation-gated framework; it added darwin to its integration list. A two-way nod. 👉 [Visit the SkillOpt repo](https://github.com/microsoft/SkillOpt)

Network accessline 45

**1. Rubric expanded from 8 → 9 dimensions** (integrating [SkillLens](https://arxiv.org/abs/2605.23899)'s empirically validated 73.8% rubric recipe)

Dangerous shell operationline 142

| **High-Risk Action Blacklist** | Destructive operations (rm / git reset --hard / force push) must be explicitly forbidden |

Network accessline 184

Can't access GitHub? Download the zip: [darwin-skill.zip](https://pub-161ae4b5ed0644c4a43b5c6412287e03.r2.dev/skills/darwin-skill.zip). Extract and place SKILL.md in `~/.claude/skills/darwin-skill/`.

Network accessline 195

Directly inspired by **Andrej Karpathy's [autoresearch](https://github.com/karpathy/autoresearch)**.

Network accessline 199

v2.0 builds on this foundation by integrating two Microsoft Research papers (published 2026-05-22): [SkillLens](https://arxiv.org/abs/2605.23899) provides the empirically validated rubric design, and [SkillOpt](https://arxiv.org/abs/2605.23

Network accessline 211

- Paper: https://arxiv.org/abs/2605.23899

Network accessline 218

- 🔗 **Code repo**: [github.com/microsoft/SkillOpt](https://github.com/microsoft/SkillOpt) (`pip install skillopt`, v0.1.0 on PyPI)

Network accessline 219

- Project page: https://microsoft.github.io/SkillOpt/

Network accessline 220

- Paper: https://arxiv.org/abs/2605.23904

Network accessline 228

- Code: https://github.com/karpathy/autoresearch

Network accessline 237

| | | |:---|:---| | 🌐 Website | [bookai.top](https://bookai.top) · [huasheng.ai](https://www.huasheng.ai) |

Network accessline 238

|:---|:---| | 🌐 Website | [bookai.top](https://bookai.top) · [huasheng.ai](https://www.huasheng.ai) | | 𝕏 Twitter | [@AlchainHust](https://x.com/AlchainHust) |

Network accessline 239

| 🌐 Website | [bookai.top](https://bookai.top) · [huasheng.ai](https://www.huasheng.ai) |

Network accessline 240

| 𝕏 Twitter | [@AlchainHust](https://x.com/AlchainHust) |

Network accessline 241

| 📺 Bilibili | [花叔](https://space.bilibili.com/14097567) |

Network accessline 242

| ▶<U+FE0F> YouTube | [@Alchain](https://www.youtube.com/@Alchain) |

Network accessline 243

| 📕 Xiaohongshu | [花叔](https://www.xiaohongshu.com/user/profile/5abc6f17e8ac2b109179dfdf) |

Network accessline 256

**[Nuwa](https://github.com/alchaincyf/nuwa-skill)** creates skills.<br>

Network accessline 262

MIT License © [花叔 Huashu](https://github.com/alchaincyf)

`SKILL.md`

Network accessline 11

> 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

Network accessline 13

> GitHub: https://github.com/alchaincyf/darwin-skill

Network accessline 449

- **SkillLens**（arXiv [2605.23899](https://arxiv.org/abs/2605.23899)）：9 维 rubric 的实证来源（LLM 自评 46.4% → 加 meta-skill 三维度后 73.8%）。

Network accessline 450

- **SkillOpt**（arXiv [2605.23904](https://arxiv.org/abs/2605.23904)）：validation-gated edits 形式化框架。代码 [github.com/microsoft/SkillOpt](https://github.com/microsoft/SkillOpt)（`pip install skillopt`）、项目页 [microsoft.github.io/SkillOpt](https://m

Network accessline 451

- **autoresearch**：[github.com/karpathy/autoresearch](https://github.com/karpathy/autoresearch)，本 skill 1.0 的原始灵感。

`assets/banner-en.svg`

Network accessline 1

<svg width="1200" height="400" viewBox="0 0 1200 400" xmlns="http://www.w3.org/2000/svg">

Network accessline 2

<defs>     <style>       @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;700;900&amp;display=swap');

Network accessline 3

<style>       @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;700;900&amp;display=swap');     </style>

Network accessline 4

@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;700;900&amp;display=swap');

`assets/banner.svg`

Network accessline 1

<svg width="1200" height="400" viewBox="0 0 1200 400" xmlns="http://www.w3.org/2000/svg">

Network accessline 2

<defs>     <style>       @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;700;900&amp;display=swap');

Network accessline 3

<style>       @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;700;900&amp;display=swap');     </style>

Network accessline 4

@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;700;900&amp;display=swap');

`assets/chart-loop-en.html`

Network accessline 4

<meta charset="UTF-8"> <title>darwin.skill - Core Loop</title> <link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 5

<title>darwin.skill - Core Loop</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 6

<link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 7

<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 8

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800;900&display=swap" rel="stylesheet">

Network accessline 19

</head> <body> <svg width="1200" height="500" xmlns="http://www.w3.org/2000/svg">

Network accessline 20

<body> <svg width="1200" height="500" xmlns="http://www.w3.org/2000/svg">   <defs>

Network accessline 21

<svg width="1200" height="500" xmlns="http://www.w3.org/2000/svg">

`assets/chart-loop.html`

Network accessline 4

<meta charset="UTF-8"> <title>达尔文.skill - Core Loop</title> <link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 5

<title>达尔文.skill - Core Loop</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 6

<link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 7

<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 8

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800;900&display=swap" rel="stylesheet">

Network accessline 19

</head> <body> <svg width="1200" height="500" xmlns="http://www.w3.org/2000/svg">

Network accessline 20

<body> <svg width="1200" height="500" xmlns="http://www.w3.org/2000/svg">   <defs>

Network accessline 21

<svg width="1200" height="500" xmlns="http://www.w3.org/2000/svg">

`assets/chart-phases-en.html`

Network accessline 4

<meta charset="UTF-8"> <title>Optimization Lifecycle</title> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800;900&display=swap" rel="stylesheet">

Network accessline 5

<title>Optimization Lifecycle</title> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800;900&display=swap" rel="stylesheet"> <style>

Network accessline 6

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800;900&display=swap" rel="stylesheet">

`assets/chart-phases.html`

Network accessline 4

<meta charset="UTF-8"> <title>Optimization Lifecycle</title> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800;900&display=swap" rel="stylesheet">

Network accessline 5

<title>Optimization Lifecycle</title> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800;900&display=swap" rel="stylesheet"> <style>

Network accessline 6

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800;900&display=swap" rel="stylesheet">

`assets/chart-ratchet-en.html`

Network accessline 6

<title>Ratchet Mechanism</title> <style>   @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800&display=swap');

Network accessline 8

@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800&display=swap');

`assets/chart-ratchet.html`

Network accessline 6

<title>Ratchet Mechanism</title> <style>   @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800&display=swap');

Network accessline 8

@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800&display=swap');

`assets/chart-rubric-en.html`

Network accessline 4

<meta charset="UTF-8"> <meta name="viewport" content="width=1200"> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&display=swap" rel="stylesheet">

Network accessline 5

<meta name="viewport" content="width=1200"> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&display=swap" rel="stylesheet"> <style>

Network accessline 6

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&display=swap" rel="stylesheet">

`assets/chart-rubric.html`

Network accessline 4

<meta charset="UTF-8"> <meta name="viewport" content="width=1200"> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&display=swap" rel="stylesheet">

Network accessline 5

<meta name="viewport" content="width=1200"> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&display=swap" rel="stylesheet"> <style>

Network accessline 6

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&display=swap" rel="stylesheet">

`docs/index.html`

Network accessline 5

<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>自主技能优化系统</title> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800;900&display=swap" rel="stylesheet">

Network accessline 6

<title>自主技能优化系统</title> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800;900&display=swap" rel="stylesheet"> <style>

Network accessline 7

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800;900&display=swap" rel="stylesheet">

`references/runtime-neutrality.md`

Network accessline 9

花叔的 skills 基于 Anthropic 开放的 [Agent Skills](https://agentskills.io) 协议，应当能在 Claude Code、Codex、Cursor、OpenClaw、Hermes Agent、CodeBuddy、Workbuddy、Gemini CLI、OpenCode 等 50+ skills-compatible runtime 上通用。

`scripts/screenshot.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`showcase.html`

Network accessline 5

<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>自主技能优化系统</title> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800;900&display=swap" rel="stylesheet">

Network accessline 6

<title>自主技能优化系统</title> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800;900&display=swap" rel="stylesheet"> <style>

Network accessline 7

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800;900&display=swap" rel="stylesheet">

`templates/result-card-dark.html`

Network accessline 5

<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Darwin Skill - 暗夜成就</title> <link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 6

<title>Darwin Skill - 暗夜成就</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 7

<link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 8

<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 9

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800;900&family=Noto+Sans+SC:wght@400;500;700;900&display=swap" rel="stylesheet">

`templates/result-card-white.html`

Network accessline 5

<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Darwin Skill - 我的Skill进化报告（白金版）</title> <link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 6

<title>Darwin Skill - 我的Skill进化报告（白金版）</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 7

<link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 8

<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 9

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800;900&family=Noto+Sans+SC:wght@300;400;500;700;900&display=swap" rel="stylesheet">

`templates/result-card.html`

Network accessline 5

<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Darwin Skill - 我的Skill进化报告</title> <link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 6

<title>Darwin Skill - 我的Skill进化报告</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 7

<link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 8

<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 9

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800;900&family=Noto+Sans+SC:wght@400;500;700;900&display=swap" rel="stylesheet">

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 71 facts

Network access in prose of documentationREADME.md:10Low confidence
Network access in prose of documentationREADME.md:11Low confidence
Network access in prose of documentationREADME.md:12Low confidence
Network access in prose of documentationREADME.md:21Low confidence
Network access in prose of documentationREADME.md:23Low confidence
Network access in prose of documentationREADME.md:25Low confidence
Network access in prose of documentationREADME.md:26Low confidence
Network access in prose of documentationREADME.md:27Low confidence
Network access in prose of documentationREADME.md:28Low confidence
Network access in prose of documentationREADME.md:29Low confidence
Network access in prose of documentationREADME.md:39Low confidence
Network access in prose of documentationREADME.md:40Low confidence
Network access in prose of documentationREADME.md:41Low confidence
Network access in prose of documentationREADME.md:43Low confidence
Network access in prose of documentationREADME.md:51Low confidence
Dangerous shell operation in prose of documentationREADME.md:146Low confidence
Network access in prose of documentationREADME.md:188Low confidence
Network access in prose of documentationREADME.md:199Low confidence
Network access in prose of documentationREADME.md:203Low confidence
Network access in prose of documentationREADME.md:215Low confidence
Network access in prose of documentationREADME.md:222Low confidence
Network access in prose of documentationREADME.md:223Low confidence
Network access in prose of documentationREADME.md:224Low confidence
Network access in prose of documentationREADME.md:232Low confidence
Network access in prose of documentationREADME.md:241Low confidence
Network access in prose of documentationREADME.md:242Low confidence
Network access in prose of documentationREADME.md:243Low confidence
Network access in prose of documentationREADME.md:244Low confidence
Network access in prose of documentationREADME.md:245Low confidence
Network access in prose of documentationREADME.md:246Low confidence
Network access in prose of documentationREADME.md:247Low confidence
Network access in prose of documentationREADME.md:260Low confidence
Network access in prose of documentationREADME.md:266Low confidence
Network access in prose of documentationREADME.md:275Low confidence
Network access in prose of documentationREADME_EN.md:15Low confidence
Network access in prose of documentationREADME_EN.md:17Low confidence
Network access in prose of documentationREADME_EN.md:19Low confidence
Network access in prose of documentationREADME_EN.md:20Low confidence
Network access in prose of documentationREADME_EN.md:21Low confidence
Network access in prose of documentationREADME_EN.md:22Low confidence
Network access in prose of documentationREADME_EN.md:23Low confidence
Network access in prose of documentationREADME_EN.md:33Low confidence
Network access in prose of documentationREADME_EN.md:34Low confidence
Network access in prose of documentationREADME_EN.md:35Low confidence
Network access in prose of documentationREADME_EN.md:37Low confidence
Network access in prose of documentationREADME_EN.md:45Low confidence
Dangerous shell operation in prose of documentationREADME_EN.md:142Low confidence
Network access in prose of documentationREADME_EN.md:184Low confidence
Network access in prose of documentationREADME_EN.md:195Low confidence
Network access in prose of documentationREADME_EN.md:199Low confidence

and 21 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![alchaincyf/darwin-skill on hotskills](https://hotskills.dev/badge/alchaincyf-darwin-skill.svg)](https://hotskills.dev/skill/alchaincyf-darwin-skill/)

alchaincyf/darwin-skill

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

darwin-skill

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

README.md

README_EN.md

SKILL.md

assets/banner-en.svg

assets/banner.svg

assets/chart-loop-en.html

assets/chart-loop.html

assets/chart-phases-en.html

assets/chart-phases.html

assets/chart-ratchet-en.html

assets/chart-ratchet.html

assets/chart-rubric-en.html

assets/chart-rubric.html

docs/index.html

references/runtime-neutrality.md

scripts/screenshot.mjs

showcase.html

templates/result-card-dark.html

templates/result-card-white.html

templates/result-card.html

How the signals fit together

Works with

You might also use

h4ckf0r0day/obscura

jnMetaCode/superpowers-zh

op7418/guizang-social-card-skill

SawyerHood/dev-browser

callstack/agent-device

remorses/playwriter

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`README.md`

`README_EN.md`

`SKILL.md`

`assets/banner-en.svg`

`assets/banner.svg`

`assets/chart-loop-en.html`

`assets/chart-loop.html`

`assets/chart-phases-en.html`

`assets/chart-phases.html`

`assets/chart-ratchet-en.html`

`assets/chart-ratchet.html`

`assets/chart-rubric-en.html`

`assets/chart-rubric.html`

`docs/index.html`

`references/runtime-neutrality.md`

`scripts/screenshot.mjs`

`showcase.html`

`templates/result-card-dark.html`

`templates/result-card-white.html`

`templates/result-card.html`