← 返回 Skills 市场
Clean Code
作者
gabrielsubtil
· GitHub ↗
· v1.0.0
7316
总下载
23
收藏
57
当前安装
1
版本数
在 OpenClaw 中安装
/install clean-code
功能描述
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
安全使用建议
Install only if you are comfortable with a coding assistant that may edit related files and may try to run local validation scripts from other installed skill folders. Review those referenced scripts separately, keep work under version control, and set clear limits if you only want specific files changed.
功能分析
Type: OpenClaw Skill
Name: clean-code
Version: 1.0.0
The skill bundle primarily provides comprehensive guidelines for an AI agent on writing clean code and interacting with the user. While it grants broad `Read, Write, Edit` permissions, these are necessary for a code-modifying skill. The instructions for running local verification scripts (from other skill bundles) are heavily controlled, requiring the agent to capture, parse, summarize, and explicitly ask for user confirmation before acting on any script output. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection intended to subvert the agent for harmful purposes; instead, prompt instructions focus on enforcing coding standards and a controlled workflow.
能力评估
Purpose & Capability
Read, Write, and Edit are appropriate for a code-modifying standards skill, but the artifact also mandates running Python validation scripts even though execution is not declared in allowed tools and the scripts are not included for review.
Instruction Scope
The coding rules are clear, but the mandatory script section reaches outside the reviewed skill bundle into .agent/skills paths and runs checks over the project root before asking the user whether to fix results.
Install Mechanism
The installed artifact appears to be a single non-executable SKILL.md with no bundled scripts or installer, which limits direct install-time risk but makes the referenced verification scripts external dependencies.
Credentials
Broad file reading and editing, including updating dependent files, is proportionate for a clean-code coding assistant, but users should expect changes may span multiple related files.
Persistence & Privilege
No persistence, background workers, credential access, network exfiltration, destructive commands, or privileged account use are present in the reviewed artifact.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install clean-code - 安装完成后，直接呼叫该 Skill 的名称或使用
/clean-code触发 - 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
v1.0.0
Major update: The skill has been overhauled for strict, pragmatic coding standards and robust validation requirements.
- Expanded coding standards with explicit, actionable "Do" and "Don't" lists, core principles, and anti-pattern tables.
- Added mandatory self-checklists for agents to validate goal completion, code correctness, and coverage of all requirements before completing tasks.
- Introduced required validation script mapping per agent skill, with strict output handling, summarized reporting, and confirmation before fixing issues.
- Enforced concise, self-documenting code—no unnecessary comments or abstractions; small, focused functions; and direct responses to user requests.
- Updated rules for naming, code structure, and file editing responsibilities to prevent breakage and ensure maintainability.
- Raised skill priority to CRITICAL and version to 2.0.
元数据
常见问题
Clean Code 是什么？
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 7316 次。
如何安装 Clean Code？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install clean-code」即可一键安装，无需额外配置。
Clean Code 是免费的吗？
是的，Clean Code 完全免费（开源免费），可自由下载、安装和使用。
Clean Code 支持哪些平台？
Clean Code 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 Clean Code？
由 gabrielsubtil（@gabrielsubtil）开发并维护，当前版本 v1.0.0。
推荐 Skills