← 返回 Skills 市场
cat-xierluo

Skill Lint

作者 xierluo · GitHub ↗ · v1.3.0 · MIT-0
cross-platform ✓ 安全检测通过
209
总下载
0
收藏
2
当前安装
2
版本数
在 OpenClaw 中安装
/install skill-lint
功能描述
Skill 格式审查工具,基于 SKILL-DEV-GUIDE.md 规范对技能进行合规性审计。本技能应在用户需要审查 skill 格式合规性、检查文档与代码一致性、识别冗余内容、生成技能审计报告时使用。不要用于:代码审查、功能测试、非 skill 项目。
安全使用建议
This skill appears coherent and low-risk: it will read files under whatever skill-path you give it and produce a structured audit. Before running it (especially if you let the agent invoke it autonomously), only point it at repositories you trust or isolated copies, since the agent will read all files in that path. Because it is instruction-only, there is no bundled executable or external install to review; the main risk is inadvertent disclosure of sensitive files if you supply a path that contains secrets.
功能分析
Type: OpenClaw Skill Name: skill-lint Version: 1.3.0 The skill-lint bundle is a legitimate utility designed to audit other OpenClaw skills for formatting compliance and basic security best practices. The instructions in SKILL.md and references/skill-standards.md guide the AI agent to perform read-only operations (globbing and reading files) to verify directory structures, metadata, and the absence of hardcoded secrets or dangerous commands (e.g., rm -rf /). There is no evidence of malicious intent, data exfiltration, or unauthorized command execution.
能力标签
cryptocan-make-purchases
能力评估
Purpose & Capability
Name/description (skill-lint) match the runtime instructions: steps describe scanning a skill directory, parsing frontmatter, checking file references, and generating a report. There are no unexpected environment variables, binaries, or unrelated capabilities requested.
Instruction Scope
Instructions explicitly tell the agent to glob and read files within the target skill path (SKILL.md, references, scripts, etc.) which is appropriate for a linter. Note: the skill requires the agent to be able to read all files under whatever path the user supplies — ensure you only provide paths you authorize.
Install Mechanism
Instruction-only skill with no install spec and no code files. This minimizes disk-write and supply-chain risk.
Credentials
No environment variables, credentials, or config paths are requested. The included standards explicitly forbid reading ~/.env or hard-coded API keys, which aligns with the linter's purpose.
Persistence & Privilege
always is false and the skill does not request persistent or elevated privileges or modify other skills' configs. Autonomous invocation is allowed by platform default but does not by itself increase risk here.
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 skill-lint
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /skill-lint 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
Skill格式审查工具更新至v1.3.0,增强合规性审计能力
v1.0.0
Skill 格式审查工具
元数据
Slug skill-lint
版本 1.3.0
许可证 MIT-0
累计安装 2
当前安装数 2
历史版本数 2
常见问题

Skill Lint 是什么?

Skill 格式审查工具,基于 SKILL-DEV-GUIDE.md 规范对技能进行合规性审计。本技能应在用户需要审查 skill 格式合规性、检查文档与代码一致性、识别冗余内容、生成技能审计报告时使用。不要用于:代码审查、功能测试、非 skill 项目。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 209 次。

如何安装 Skill Lint?

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

Skill Lint 是免费的吗?

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

Skill Lint 支持哪些平台?

Skill Lint 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 Skill Lint?

由 xierluo(@cat-xierluo)开发并维护,当前版本 v1.3.0。

💬 留言讨论