安全拦截型技能，确保安装任何技能前都经过 skill-vetter 的安全审查，输出审查报告并要求用户明确确认，禁止私自安装。
Security-first skill vetting for AI agents. Use BEFORE installing any skill from ClawHub, GitHub, or other sources. Checks for red flags, dangerous patterns,...
Enterprise-grade security vetting protocol for AI agent skills. Automated threat detection, quantified risk scoring, and zero-trust code analysis.
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification L...
Skills 安全安装工具 - 整合 Vetter 代码审查 + ClawHub 评分 + ThreatBook 沙箱扫描三层验证
Validate OpenClaw skills during authoring. Use when creating, revising, or preparing a skill for release and you need to scaffold `evals/` files, check readi...
当 ClawHub CLI 速率限制或安装失败时，通过多种备用方式安装技能：1) clawhub.ai 下载 zip；2) GitHub 搜索并克隆；3) 手动流程指导。
授权保护技能 - 所有外部 API 操作必须经过用户明确授权。这是最高优先级的安全层，确保没有任何自动化可以擅自使用你的授权。核心原则：用户指令
One-stop skill management for OpenClaw. 一站式技能管理，引导式使用，嵌套搜索、审计、创建、发布、批量更新等必要 skill。Use when reviewing installed skills, searching
一体化技能注册表 - 本地优先匹配，无匹配则自动搜索ClawHub并安全安装，新装技能自动注册到细分分类。
Discovers and recommends the best agent skills based on user intent — not just keywords. Activates when users ask "how do I do X", "find a skill for X", "is...
360-degree comprehensive security review Skill. Use before installing any Skill from ClawHub, GitHub, or other sources. Performs full security scans includin...
Install and set up the OpenClaw Skill Usage plugin. Use when users say: - "install skill usage" - "setup skill usage" - "add skill usage analytics" - "instal...
An AI-first knowledge management system with evolvable memory - 一套 AI 时代的注意力保护架构
Open identity and encrypted communication protocol for AI agents. Register on the Koan mesh, get a cryptographic identity, browse other agents, and send your...
Route the current task to the most relevant installed skill, and only suggest new skills when existing ones are not enough. Use when the user asks things lik...