⚠️Install with caution. This skill has very few installs. Always review the source and verify it on clawhub.ai before installing. Community-built skills run with agent permissions — only install ones you trust.

🗂️ Git & Version Control

SkillGuardv4.2.0

Name: SkillGuard
Author: huangjihua007-rgb

skill-butler-cn

huangjihua007-rgb

安装前审查 + 发布前安检 + 安装后体检，三合一全生命周期守护。给 GitHub URL 或 ClawHub slug 审查来源安全性（16条RED FLAGS自动扫描）。贴入 SKILL.md 跑安全检查/依赖检查/多平台适配，P0直接标红给修复代码。不同于 Skill Vetter 的安装前扫描，Sk...

latest

Download Package View on ClawHub

Installs (all time)

Installs (current)

Downloads

1.0K

Stars

CreatedMay 5, 2026

UpdatedMay 17, 2026

Install & Quick Start

Install via ClawdBot CLI:

clawdbot install huangjihua007-rgb/skill-butler-cn

Skill Package4 files

📋SKILL.mdmarkdown

Failed to load file.

Quality Score

B52/100

Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.

Market Validation7/35

· 723 downloads (moderate demand)
· No tracked installs (may still have real users via manual install)

Documentation14/25

· SKILL.md present
· Moderate documentation (≥1500 chars)
· Detailed summary

Package Completeness6/15

· skillAssets present (3 files)

Security Analysis

💙 Low Risk

UNKNOWN_DATA_SINKhigh

Sends data to undocumented external endpoint (potential exfiltration)

webhook → https://...

UNSAFE_SHELLmedium

Potentially destructive shell commands in tool definitions

curl \| bash

UNDOCUMENTED_EXTERNALlow

Calls external URL not in known-safe list

https://...

AI Analysis

The skill definition contains a rule-based signal about an undocumented external endpoint and a potentially unsafe shell command pattern, but the actual skill content shown is a static prompt-only skill that does not include any tool definitions, API calls, or code execution. The signals likely originate from metadata or a different part of the full definition not visible in the excerpt. Without evidence of actual data transmission or hidden instructions, the risk is low.

💡

Usage Guide

Generated May 22, 2026

AI Skill开发者发布审核人员多平台运营人员独立开发者与小型团队beginner

💡 Application Scenarios

发布前安全检查AI Agent开发、Skill发布

开发者提交Skill前，使用该场景进行一票否决项检查、Moderation语义预扫，快速识别违规风险并获取修复代码，确保发布顺利通过审核。

多平台发布检查多平台发布、AI应用分发

针对ClawHub、SkillHub、skills.AI、SkillMP等多个平台，自动对比各平台发布要求差异，生成差异清单，帮助开发者一次性适配所有平台。

运行依赖检查Skill开发、依赖管理

对SKILL.md中的runtime_requires字段进行合规性检查（包括node、python和system依赖），并输出修复后的YAML配置，确保依赖声明准确无误。

全量检查全面质量保障、发布预检

合并执行安全检查、多平台发布检查和运行依赖检查，一次性输出完整报告，提供全面的发布前预检服务。

💼 Business Models

免费增值服务基础免费，高级功能按次或订阅收费

基础检查功能免费开放给所有开发者，通过提供高质量预检服务吸引用户，后续可考虑高级分析或定制报告收费。

企业级许可证企业许可证年费

面向AI平台或大型开发团队提供内嵌式Skill体检服务，以API或插件形式集成到内部CI/CD流程中，按年收费。

生态平台分成平台分成或广告收入

与ClawHub、SkillHub等平台合作，作为平台官方推荐的上架前体检工具，通过流量引导或体检报告内嵌广告获得分成收入。

💬 Integration Tip

通过对话式交互选择场景并粘贴SKILL.md内容即可使用，无需任何安装配置；也可嵌入到CI流水线中实现自动化预检。