What makes 达尔文.skill notable?

4K downloads. Trust evidence available

How should 达尔文.skill be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

agentCLAWHUBUnverified

达尔文.skill

Autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hill-c... Skill: 达尔文.skill Owner: alchaincyf Summary: Autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hill-c... Tags: autoresearch:1.0.0, darwin:1.0.0, latest:1.0.0, optimization:1.0.0, skill:1.0.0 Version history: v1.0.0 | 2026-04-13T14:33:32.290Z | user Initial release: autoresearch-inspired autonomous skill optimization sy

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

4.0k

Updated

Oct 9, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 4K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 4K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.0release · observed Apr 13, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s175vj0ymzerswhb0n313k9eq9848avz:darwin-skill

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-alchaincyf-darwin-skill/snapshot"

Documentation

CLAWHUB

14,785 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: darwin-skill
description: Autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hill-climbing with git version control, and validates improvements through test prompts. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize skills", "skill质量检查", "这个skill写得不好", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".
---

# 达尔文.skill

> 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**

---

## 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（8维度，总分100）

### 结构维度（60分）— 静态分析

| # | 维度 | 权重 | 评分标准 |
|---|------|------|---------|
| 1 | **Frontmatter质量** | 8 | name规范、description包含做什么+何时用+触发词、≤1024字符 |
| 2 | **工作流清晰度** | 15 | 步骤明确可执行、有序号、每步有明确输入/输出 |
| 3 | **边界条件覆盖** | 10 | 处理异常情况、有fallback路径、错误恢复 |
| 4 | **检查点设计** | 7 | 关键决策前有用户确认、防止自主失控 |
| 5 | **指令具体性** | 15 | 不模糊、有具体参数/格式/示例、可直接执行 |
| 6 | **资源整合度** | 5 | references/scripts/assets引用正确、路径可达 |

### 效果维度（40分）— 需要实测

| # | 维度 | 权重 | 评分标准 |
|---|------|------|---------|
| 7 | **整体架构** | 15 | 结构层次清晰、不冗余不遗漏、与花叔生态一致 |
| 8 | **实测表现** | 25 | 用测试prompt跑一遍，输出质量是否符合skill宣称的能力 |

### 评分规则
- 维度1-7：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

### 关于「实测表现」维度

这是与纯结构评分最大的区别。评分方式：

1. 为每个skill设计2-3个**典型用户prompt**（不是边缘case，是最常见的使用场景）
2. 用子agent执行：一个带skill跑，一个不带skill跑（baseline）
3. 对比输出质量，从以下角度打分：
   - 输出是否完成了用户意图？
   - 相比不带skill的baseline，质量提升明显吗？
   - 有没有skill引入的负面影响（过度冗余、跑偏、格式奇怪）？

如果无法跑子agent（时间/资源限制），可以退化为「干跑验证」：读完skill后模拟一个典型prompt的执行思路，判断流程是否合理。但要在results.tsv中标注 `dry_run`。

---

## 自主优化循环

### Phase 0: 初始化

```
1. 确认优化范围：
   - 全部skills → 扫描 .claude/skills/*/SKILL.md
   - 指定skills → 用户指定列表
2. 创建 git 分支：auto-optimize/YYYYMMDD-HHMM
3. 初始化 results.tsv（如不存在）
4. 读取现有 results.tsv 了解历史优化记录
```

### Phase 0.5: 测试Prompt设计

在评估之前，为每个skill设计测试prompt。这步很关键——没有测试prompt，「实测表现」维度就打不了分。

```
for each skill:
  1. 读取 SKILL.md，理解它做什么
  2. 设计2-3个测试prompt，覆盖：
     - 最典型的使用场景（happy path）
     - 一个稍复杂或有歧义的场景
  3. 保存到 skill目录/test-prompts.json：
     [
       {"id": 1, "prompt": "用户会说的话", "expected": "期望输出的简短描述"},
       {"id": 2, "prompt": "...", "expected": "..."}
     ]
```

展示所有测试prompt给用户，**确认后再进入评估**。测试prompt的质量决定了优化方向是否正确。

### Phase 1: 基线评估（Baseline）

```
for each skill in 优化范围:

  # 结构评分（主agent可以做）
  1. 读取 SKILL.md 全文
  2. 按维度1-7逐项打分（附简短理由）

  # 效果评分（用子agent做，独立于主agent）
  3. 对每个测试prompt，spawn子agent：
     - with_skill: 带着SKILL.md执行测试prompt
     - baseline: 不带skill执行同一prompt
  4. 对比两组输出，打维度8的分

  # 汇总
  5. 计算加权总分
  6. 记录到 results.tsv
```

**如果子agent不可用**（超时、环境限制），维度8用干跑验证打分，标注 `dry_run`。不要因为跑不了测试就跳过这个维度——哪怕是模拟推演也比完全不看效果好。

基线评估完成后，展示评分卡：

```
┌──────────────────────────┬───

README.md

![达尔文.skill](assets/banner.svg)

# 达尔文.skill

**像训练模型一样优化你的 Claude Code Skills。**

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。

---

## 核心循环

![Core Loop](assets/chart-loop.png)

---

## 为什么做这个

Claude Code 的 Skill 生态在快速扩张。当你有 10 个 Skills 时可以手动维护；当你有 60+ 个 Skills 时，你需要一个系统。

传统的 Skill 审查是**纯结构性的**：检查格式对不对、步骤有没有编号、路径能不能访问。但一个格式完美的 Skill，跑出来的效果可能很差。

达尔文.skill 同时评估**结构质量**和**实际效果**，然后只保留真正有改进的修改。

---

## 从 autoresearch 到 Skill Optimizer

这个项目直接受 Karpathy autoresearch 启发。autoresearch 的做法是：写一个 `program.md` 定义目标和约束，让 agent 自主生成和测试代码变更，只保留可测量的改进。

我们把同样的思路搬到了 Skill 优化：

| autoresearch | 达尔文.skill | 为什么这样映射 |
|:---|:---|:---|
| `program.md` | 本 SKILL.md | 定义评估标准和约束规则 |
| `train.py` | 每个待优化的 SKILL.md | 被优化的资产，每次实验只改它 |
| `val_bpb` | 8 维加权总分（满分100） | 可量化的优化目标 |
| `git ratchet` | keep / revert 机制 | 只保留有改进的 commit |
| `test set` | test-prompts.json | 验证改进是否真的有效 |
| 全自主运行 | **人在回路** | Skill 的好坏比 loss 更微妙，需要人的判断 |

关键区别：autoresearch 全自主运行（loss 可以自动比较），Skill 优化增加了**人在回路**。因为 Skill 的「好坏」不像 loss 那样可以纯数值判断。

---

## 五条核心原则

| # | 原则 | 说明 |
|:---|:---|:---|
| 01 | **单一可编辑资产** | 每次只改一个 SKILL.md，变量可控，改进可归因 |
| 02 | **双重评估** | 结构评分（静态分析）+ 效果验证（跑测试看输出） |
| 03 | **棘轮机制** | 只保留改进，自动回滚退步，分数只升不降 |
| 04 | **独立评分** | 评分用子 agent，避免「自己改自己评」的偏差 |
| 05 | **人在回路** | 每个 Skill 优化完后暂停，用户确认再继续下一个 |

---

## 8 维度评估体系

总分 100。结构维度靠静态分析（60分），效果维度必须实测（40分）。

![Evaluation Rubric](assets/chart-rubric.png)

> 实测表现权重最高（25分）。Skill 写得再漂亮，跑出来效果不好就是零。

---

## 优化循环：5 个阶段

系统在每个阶段内自主运行，但在阶段之间暂停等待人类确认。

![Optimization Lifecycle](assets/chart-phases.png)

**Phase 2 的核心逻辑**：

1. 找出得分最低的维度
2. 针对该维度生成 1 个具体改进方案
3. 编辑 SKILL.md，git commit
4. 子 agent 独立重新评分
5. 新分 > 旧分 → 保留；否则 → git revert
6. 每个 Skill 完成后暂停，展示 diff + 分数变化，等用户确认

---

## 棘轮机制

分数只能上升。每一轮要么改进 Skill，要么干净地回滚。不会随时间积累局部退化。

![Ratchet Mechanism](assets/chart-ratchet.png)

轮次 2 的 75 分低于当前最优的 78 分，被自动回滚。有效基线始终锁定在 78，后续改进从 78 继续。

---

## 快速开始

### 安装

```bash
# 将 SKILL.md 放入 Claude Code Skills 目录
mkdir -p ~/.claude/skills/darwin-skill
cp SKILL.md ~/.claude/skills/darwin-skill/SKILL.md
```

### 使用

```
# 评估所有 Skills（只评估不改）
> 评估所有 skills

# 优化指定 Skill
> 优化 huashu-slides 这个 skill

# 全量优化（推荐首次使用）
> 优化所有 skills

# 查看历史
> 看看 skill 优化历史
```

### 输出示例

```
┌──────────────────────────┬────────┬────────┬────────┐
│ Skill                    │ Before │ After  │ Δ      │
├──────────────────────────┼────────┼────────┼────────┤
│ huashu-proofreading      │ 78     │ 87     │ +9     │
│ huashu-slides            │ 72     │ 83     │ +11    │
│ huashu-publish           │ 81     │ 88     │ +7     │
├──────────────────────────┼────────┼────────┼────────┤
│ 平均                     │ 77     │ 86     │ +9     │
└──────────────────────────┴────────┴────────┴────────┘
```

---

## 设计灵感

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

autoresearch 证明了一个优雅的想法：你可以把「写论文」这件事变成一个自主实验循环。定义目标（`program.md`），让 agent 不断生成和测试变更（`train.py`），用可量化的指标（`val_bpb`）决定保留还是回滚

_meta.json

{
  "ownerId": "kn790wwtqpc4wthzy7rq6s5yp5849443",
  "slug": "darwin-skill",
  "version": "1.0.0",
  "publishedAt": 1776090812290
}

skill-card.md

## Description:

Autonomous skill optimizer inspired by Karpathy's autoresearch that evaluates SKILL.md files with an 8-dimension rubric, runs hill-climbing with git version control, and validates changes through test prompts.

This skill is ready for commercial/non-commercial use.

## Publisher:

[alchaincyf](https://clawhub.ai/user/alchaincyf)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and skill maintainers use this skill to evaluate and improve Claude Code skills by designing test prompts, scoring structure and behavior, proposing focused edits, and retaining only improvements after review.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The workflow can broadly inspect and modify installed skill files.

Mitigation: Run it first on a named skill or reviewed allowlist, and avoid full-scan optimization unless all local skill instructions are acceptable inputs.

Risk: Generated edits may introduce incorrect or lower-quality skill guidance.

Mitigation: Review generated test prompts, score changes, diffs, and sample outputs before accepting changes.

Risk: The workflow creates git branches and commits while optimizing skills.

Mitigation: Inspect the generated branch and commits before merging or deploying, and rely on revert behavior for changes that do not improve the score.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/alchaincyf/skills/darwin-skill)
- [Publisher profile](https://clawhub.ai/user/alchaincyf)
- [Karpathy autoresearch](https://github.com/karpathy/autoresearch)
- [Claude Code](https://claude.ai/code)

## Skill Output:

**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown with inline code blocks, tabular scoring summaries, JSON or TSV artifacts, and proposed file edits.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May create git branches, commits, test-prompts.json, results.tsv, and SKILL.md changes when the user approves the optimization workflow.]

## Skill Version(s):

1.0.0 (source: ClawHub release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/alchaincyf/skills/darwin-skill",
      "sourceUrl": "https://clawhub.ai/alchaincyf/skills/darwin-skill",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T06:17:13.033Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-alchaincyf-darwin-skill/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-alchaincyf-darwin-skill/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T06:17:13.033Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "4K downloads",
      "href": "https://clawhub.ai/alchaincyf/darwin-skill",
      "sourceUrl": "https://clawhub.ai/alchaincyf/darwin-skill",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T06:17:13.033Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.0.0",
      "href": "https://clawhub.ai/alchaincyf/darwin-skill",
      "sourceUrl": "https://clawhub.ai/alchaincyf/darwin-skill",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-13T14:33:32.290Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-alchaincyf-darwin-skill/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-alchaincyf-darwin-skill/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.0.0",
      "description": "Initial release: autoresearch-inspired autonomous skill optimization system",
      "href": "https://clawhub.ai/alchaincyf/darwin-skill",
      "sourceUrl": "https://clawhub.ai/alchaincyf/darwin-skill",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-13T14:33:32.290Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

README.md

_meta.json

skill-card.md

Related agents

activepieces

cherry-studio

AionUi

CopilotKit

Machine-readable data