发现最适合你需求的 AI 技能
技能检验工具：基于ClawHub技能格式规范的验证工具，确保技能符合最新发布要求。自动检测格式问题，提供修复建议，与ClawHub规范同步更新。
Check all installed skills for available upgrades, interpret version changes and risk, and execute upgrades with user confirmation. | 检查所有已安装技能的可用升级，解读版本变更与风险，经用户确认后执行升级"
Manage OpenClaw and installed skill updates with scheduled checks, safe upgrade workflows, rollback-minded guidance, and clear reporting. Use when setting up automatic update routines, checking for newer skill versions, or keeping an OpenClaw environment current.
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
Route user tasks to the most relevant skills using a layered taxonomy, risk model, and minimum-necessary-loading strategy. Use when deciding which skill to load, when multiple skills could apply, when new downloaded skills need classification, when evaluating whether a skill may threaten the system, or when maintaining a persistent task-to-skill routing policy.
Route user tasks to the most relevant skills using a layered taxonomy, risk model, and minimum-necessary-loading strategy. Use when deciding which skill to load, when multiple skills could apply, when new downloaded skills need classification, when evaluating whether a skill may threaten the system, or when maintaining a persistent task-to-skill routing policy.
Security audit tool for ClawHub skills. Scans a skill directory with 65 detection patterns, anti-obfuscation analysis, and dual rating system (Security + Compliance). v0.6.1 fixes batch scan performance by skipping venv/node_modules directories. Use when: installing a new skill, reviewing skill safety, or auditing permissions.
Evaluate external skills before installation and decide whether to install, reject, or absorb only the useful ideas. Use when a user shares a ClawHub/GitHub skill link, asks whether a skill is worth installing, asks for a code/safety review before installation, or wants to compare a skill's workflow with the current OpenClaw workflow.
Enables any skill to gain self-evolution capabilities. Use when: (1) User asks to add self-evolution to a skill, (2) User wants a skill to learn from feedback and errors, (3) Scaling self-improvement to multiple skills with per-skill evolution logic. Outputs domain-specific .learnings/, EVOLUTION.md, and Review-Apply-Report workflow.
在 ClawHub 上搜索现有技能，当找不到匹配时自动创建新的 OpenClaw 技能。
Perform comprehensive security audits on skills to identify vulnerabilities, unsafe patterns, and compliance issues. Use when auditing skills for security, checking for hardcoded secrets, injection risks, or before releasing skills.
Strict secure-install workflow for ClawHub/OpenClaw skills. Use when asked to install a skill safely, inspect skill permissions, review third-party skill risk, or run a pre-install security audit. Enforce full review + sandbox + explicit consent gates, with no author-based trust bypass.
