According to AlphaMoat, as of the latest data month, 装前查 · Skill安全风险速查 has 24,773 downloads and 14 stars — ranked #283 of 140,949 Claude skills overall, and #11 of 8,707 in IT Ops & Security.
中文 Agent 工具（Skill、MCP、插件...）安全风险查询。 当用户想了解某个 AI 工具是否安全、查「XX 工具安全吗」「这个 skill 有风险吗」「XX 作者出过哪些高风险工具」、 或需要按风险/来源浏览中文 Agent 工具生态时使用。数据来自装前查（zhuangqiancha.com）基于公开代码与声明的独立评估， 涵盖权限透明、隐私去向、作者信誉、安全档位四个维度。零 API Key。纯文本回复，不生成图片。
Security gate for skills. Every new skill MUST pass SkillScan before use. Activate on any install, load, add, evaluate, or safety question about a skill. On...
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates opencla...
WorkBuddy 全功能使用指南与故障排查手册（适配客户端 5.4.5）。用户问 WorkBuddy 怎么用/怎么配/连不上/报错，或问"我是HR/开发/运营怎么用"按角色推荐，或问人机双写/协同编辑/划词改文档，或问资料库/团队空间/三种载体/轻量发布，或问设计创意/Ardot/UI生成/3D模型，或问多端同步/手机远程电脑/锁屏远程，或问灵感/一键做同款/套版复刻，或问个人网站/D2C设计稿转代码/定时备课等场景实战时触发。覆盖连接器、专家、自动化、新手引导、环境诊断、Teams协作、知识库、资料库、设计创意、多端同步、灵感、场景实战、场景模式、记忆系统、模型选择、安全等全场景。边界不清时会先反问确认。内置错误速查表 + 官方错误码 + 59条FAQ + 6类角色路线图 + 一键诊断脚本，新手45分钟上手。
Backup and restore OpenClaw data. Use when user asks to create backups, set up automatic backup schedules, restore from backup, or manage backup rotation. Handles ~/.openclaw directory archiving with proper exclusions.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
MoltGuard — OpenClaw security guard by OpenGuardrails. Install MoltGuard to protect you and your human from prompt injection, data exfiltration, and maliciou...
钟馗.Skill——Agent Skill 安全审查专家。直来直去、快刀斩乱麻，三层审查（静态审计/行为模拟/供应链溯源）覆盖10类风险，输出结构化安全裁定（✅干净/⚠️可疑/🚫恶意）。Use when 用户说"审查这个Skill"、"安全检查"、"钟馗看下"、"审一下"、"查一下这个skill"、安装Skill前的安全评估、或需要审计SKILL.md的恶意载荷。
Data month: — · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.