claude-skill-validator

Cloudflare Workers MCP server: claude-skill-validator

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
97%
命名质量
85%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~397token 数(工具定义)
~719 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.31%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "claude-skill-validator": {
      "url": "https://api.lazy-mac.com/claude-skill-validator/mcp"
    }
  }
}

远程端点

https://api.lazy-mac.com/claude-skill-validator/mcpstreamable-http

它能做什么

工具清单

工具(4)

🟢 只读🟡 写入🔴 删除⚪ 未知
⚪validate_skill(skill_md, tools, allowed_tools)

Fully validate a Claude SKILL.md file — frontmatter rules, body quality, security scan, tool collision check. Returns score (0–100), gate (pass/review/fail), and structured errors/warnings.

输入模式

{
  "type": "object",
  "properties": {
    "skill_md": {
      "type": "string",
      "description": "Full contents of the SKILL.md file including --- frontmatter ---"
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional override tool list if not declared in frontmatter"
    },
    "allowed_tools": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional whitelist; non-listed tools will produce errors"
    }
  },
  "required": [
    "skill_md"
  ]
}
🟢lint_frontmatter(yaml)

Parse and validate only the YAML frontmatter of a Claude Skill. Returns parsed fields and any rule violations. Use during iterative authoring.

输入模式

{
  "type": "object",
  "properties": {
    "yaml": {
      "type": "string",
      "description": "Raw YAML content without --- delimiters (just key: value lines)"
    }
  },
  "required": [
    "yaml"
  ]
}
⚪scan_security(skill_md)

Scan a Claude Skill for dangerous shell commands, hardcoded secrets, or prompt-injection phrases. Returns findings with excerpts.

输入模式

{
  "type": "object",
  "properties": {
    "skill_md": {
      "type": "string",
      "description": "The skill text to scan for security issues"
    }
  },
  "required": [
    "skill_md"
  ]
}
⚪score_skill(skill_md, tools, allowed_tools)

Run full validation and return a 0–100 score plus a ship gate (pass/review/fail). Minimal payload suitable for CI/CD pipelines.

输入模式

{
  "type": "object",
  "properties": {
    "skill_md": {
      "type": "string",
      "description": "Full SKILL.md contents"
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "allowed_tools": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "skill_md"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本4 个工具
已验证未记录版本4 个工具