← 返回 Skills 市场
207
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install skill-quality-auditor
功能描述
Evaluate and score AgentSkills on design, content, security, and usability, producing a detailed numeric scorecard with improvement suggestions.
安全使用建议
This skill appears internally consistent for auditing other skills. Before using it: (1) only point the reviewer at the skill directory you intend to audit (do not pass system or home directories), (2) run it on a copy/sandbox of the target skill if you're concerned about malicious payloads, (3) pay special attention to any grep/CRITICAL hits it reports (they warrant manual review), and (4) remember SKILL.md and reference files themselves can contain prompt-injection patterns — treat flagged findings as candidates for manual inspection rather than automatic trust.
功能分析
Type: OpenClaw Skill
Name: skill-quality-auditor
Version: 1.0.0
The skill is a comprehensive quality and security auditor designed to help an AI agent evaluate other skill bundles. It uses standard system tools like 'find' and 'grep' to perform static analysis, specifically looking for vulnerabilities, hardcoded secrets, and malicious patterns as defined in 'references/security.md'. The instructions are transparent, defensive in nature, and strictly aligned with the stated purpose of improving skill quality and security.
能力评估
Purpose & Capability
Name/description match the actual behavior: it is an on-disk reviewer that reads SKILL.md, references/, scripts/, and other files to produce a scorecard. No unrelated environment variables, binaries, or installs are requested.
Instruction Scope
Instructions require reading all files under the provided skill path and running grep-like checks against those files (explicitly: find, read SKILL.md, scan scripts/, references/ and assets/). This is appropriate for an auditor, but the skill will read any path you point it at — avoid passing system/root paths or other sensitive directories. The references include prompt-injection detection guidance (good), so the agent is expected to inspect SKILL.md for hidden directives.
Install Mechanism
Instruction-only skill with no install spec and no code files to write or execute. Lowest-risk install profile.
Credentials
No required environment variables, credentials, or config paths are declared or referenced. The audit checks look for credential usage inside the target skill but do not themselves require secret access.
Persistence & Privilege
Does not request always:true or system-wide configuration changes. Autonomous invocation is allowed (platform default) but not excessive for this type of tool.
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 skill-quality-auditor - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-quality-auditor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
Initial release. Four-dimension skill quality auditor: design, content, security, usability. Includes weight-adjustment by skill type, security grep sweeps, orphan file detection, and structured pass/revise reports.
元数据
常见问题
Skill Quality Auditor 是什么？
Evaluate and score AgentSkills on design, content, security, and usability, producing a detailed numeric scorecard with improvement suggestions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 207 次。
如何安装 Skill Quality Auditor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-quality-auditor」即可一键安装，无需额外配置。
Skill Quality Auditor 是免费的吗？
是的，Skill Quality Auditor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Skill Quality Auditor 支持哪些平台？
Skill Quality Auditor 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 Quality Auditor？
由 Ann0501（@ann0501）开发并维护，当前版本 v1.0.0。
推荐 Skills