← 返回 Skills 市场
sjj2026

Shike Darwin Optimizer

作者 sjj2026 · GitHub ↗ · v1.3.0 · MIT-0
cross-platform ✓ 安全检测通过
127
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install shike-darwin-optimizer
功能描述
Autonomous skill optimizer inspired by Karpathy's autoresearch. 8-dimension evaluation (structure + effectiveness), hill-climbing with git, test prompts vali...
安全使用建议
This skill is internally consistent for the stated job of optimizing SKILL.md files, but it will read and edit all local skill SKILL.md files and spawn subagents to test changes. Before running: (1) back up your skills directory or work in a clone; (2) verify you trust the author/package if you follow the README's npx / zip links (they're not part of the registry install in this package); (3) ensure you want automated git commits/reverts (and be prepared for any remote push to require your credentials); (4) confirm that you will approve the human-confirm checkpoints rather than giving blanket consent. If you'd like, I can list the exact file and git operations the SKILL.md will perform so you can review them line-by-line.
功能分析
Type: OpenClaw Skill Name: shike-darwin-optimizer Version: 1.3.0 The 'shike-darwin-optimizer' skill is an autonomous framework designed to improve the quality of other AgentSkills through a 'Darwinian' evolution process involving static analysis and live testing. It utilizes git for version control and rollbacks and spawns sub-agents for independent evaluation. While the skill performs high-risk actions like modifying source files (SKILL.md) and executing git commands, these are strictly aligned with its stated purpose and are mitigated by mandatory user confirmation checkpoints (e.g., Phase 2 optimization loop). No evidence of malicious intent, data exfiltration, or unauthorized persistence was found.
能力标签
crypto
能力评估
Purpose & Capability
The name/description claim an autonomous optimizer for agent skills; the SKILL.md instructs scanning SKILL.md files, designing test-prompts, running baseline vs with-skill tests, editing SKILL.md, and using git to commit/revert — all coherent with an optimizer whose asset is SKILL.md.
Instruction Scope
Runtime instructions explicitly read and write local skill files (e.g., .claude/skills/*/SKILL.md), create/modify test-prompts.json and results.tsv, and spawn subagents to run tests. These actions are necessary for the stated purpose, but they give the skill broad ability to modify your local skill repository — ensure you want an automated process that can edit SKILL.md files and run child agents. The SKILL.md does include human-confirmation checkpoints before evaluation/edits/keep-or-revert.
Install Mechanism
Registry entry is instruction-only (no install spec) so nothing is automatically downloaded/installed. README suggests optional install routes (npx package name and a zip URL hosted on an r2.dev domain). That external-install guidance is not reflected in the registry metadata and represents an out-of-band installation option you should validate before using (verify publisher, package contents and URL).
Credentials
The skill requests no environment variables or credentials in metadata. The instructions rely on local Git and the agent platform's ability to spawn child agents and access local skill files; those are proportionate to an optimizer. Note: the skill may cause network activity indirectly when subagents run or if you choose to push commits; such networking/credential usage is not declared (e.g., remote git push), so be prepared to handle prompts or credential use yourself.
Persistence & Privilege
always:false and default model-invocation settings are fine. The skill writes local artifacts (results.tsv, test-prompts.json) and performs git commits/reverts within the skills repo — that is expected for its function. It does not request forced global persistence or modify other skills' configurations beyond editing their SKILL.md files (which is the stated goal).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install shike-darwin-optimizer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /shike-darwin-optimizer 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.3.0
Updated PayPal: paypal.me/skaicn
v1.2.0
Updated payment information: WeChat: ailvyou88999, Alipay: 13359609888, PayPal: [email protected]
v1.1.0
Updated to 100/100 score with Harness Engineering methodology. Added checkpoints, exception handling, and architecture documentation. Contact: [email protected]
v1.0.0
Darwin autonomous optimization with 8-dimension evaluation. Contact: [email protected]
元数据
Slug shike-darwin-optimizer
版本 1.3.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Shike Darwin Optimizer 是什么?

Autonomous skill optimizer inspired by Karpathy's autoresearch. 8-dimension evaluation (structure + effectiveness), hill-climbing with git, test prompts vali... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 127 次。

如何安装 Shike Darwin Optimizer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install shike-darwin-optimizer」即可一键安装,无需额外配置。

Shike Darwin Optimizer 是免费的吗?

是的,Shike Darwin Optimizer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Shike Darwin Optimizer 支持哪些平台?

Shike Darwin Optimizer 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Shike Darwin Optimizer?

由 sjj2026(@sjj2026)开发并维护,当前版本 v1.3.0。

💬 留言讨论