← 返回
未分类 中文

Clawhub Skill Compliance

Pre-flight checklist for ClawHub skill publishing. Focus: metadata completeness, dependency transparency, security scope documentation. Use when: (1) prepari...
ClawHub 技能发布前的检查清单,聚焦元数据完整性、依赖透明性和安全范围文档化,适用于(1)准备发布时
tchen6500 tchen6500 来源
未分类 clawhub v1.2.2 1 版本 100000 Key: 无需
★ 0
Stars
📥 404
下载
💾 0
安装
1
版本
#latest

概述

ClawHub Skill Compliance Checklist

Purpose: Ensure skills have complete metadata, transparent dependencies, and clear security scope before publishing.

Target: Legitimate skill authors seeking clean publishing status.


Pre-flight Checklist

1. Metadata Completeness

CheckFix
------------
Missing name?Add: name: skill-name
Vague description?Add triggers: "Use when: X, Y"
Missing exclusions?Add: "NOT for: simple X"

2. Dependency Transparency

CheckFix
------------
References external skill?Declare: dependencies.skills
Uses specific tools?Declare: dependencies.tools
Forced skill loading?Make optional

Transparency principle: All dependencies should be declared in frontmatter.


3. Environment Variables

CheckFix
------------
Uses API keys?Declare: env.optional
Hardcoded secrets?Use annotated placeholder

Placeholder format: (not actual values)


4. Security Scope

CheckFix
------------
Missing section?Add Security Scope
Unclear capabilities?List: does / does NOT

Template:

## Security Scope
**What this skill does**: [list]
**What this skill does NOT**: [list]

5. Instruction Consistency

CheckFix
------------
Header contradicts examples?Align both
Shows excluded behavior?Remove from examples

6. Platform Commands

CheckFix
------------
Platform-specific command?Mark as optional

7. Content Simplicity

CheckFix
------------
Complex examples?Simplify for clarity
Redundant details?Consolidate into tables

Simplicity principle: Clear, concise content is easier for scanners to analyze accurately.


8. Safe Package References

CheckFix
------------
Using remote execution?Prefer global install
Using npx -y?Remove (no verification bypass)

Safe pattern: Verify package, install globally, use binary name.


Transparency Guidelines

When simplifying content:

  1. Use annotated placeholders: ,
  2. Keep necessary context: Security scope, dependencies
  3. Don't remove security information: Keep what reviewers need
  4. Log all changes: Track what was simplified and why

Goal: Accurate scanner analysis, not hiding content.


Security Warning

This skill is for legitimate skill authors only.

Do NOT use this checklist:

  • To publish malicious content
  • To hide harmful behavior
  • To bypass legitimate security reviews

Misuse: Using these guidelines for malicious skills violates trust and may result in account suspension.


Issue Coverage

CategoryCoverage
--------------------
Metadata completeness100%
Dependency transparency100%
Security scope100%
Instruction consistency90%
Safe package references100%

Compliance Checklist v2.2 - 2026-04-05

版本历史

共 1 个版本

  • v1.2.2 当前
    2026-05-07 07:07 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-agent

self-improving agent

pskoett
记录自身发现以实现自我改进的技能
★ 4,124 📥 874,959
ai-agent

Agent Browser

rez0
用于 AI 代理的浏览器自动化 CLI。当用户需要与网站交互(包括浏览页面、填写表单、点击按钮、截图等)时使用。
★ 845 📥 327,289
ai-agent

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,413 📥 325,573