发现最适合你需求的 AI 技能
Use this skill when the user asks about securing their OpenClaw installation, configuring AI agents safely, understanding prompt injection risks, dealing with malicious skills, protecting credentials from AI agents, setting up safe agentic workflows, or asking why persistent AI agents are dangerous. Also use when the user is setting up a new OpenClaw instance and wants to understand the security model, or when they ask about safe ways to let AI touch privileged systems.
>
Package and reuse the MeowMusicServer-patched YouTube fallback workflow: Windows Chrome cookie export/sync to server, server-side yt-dlp/yt-dlp-ejs/ffmpeg setup, old-source-first with YouTube fallback, and MV-to-MP3 extraction/caching. Use when Claude needs to wire YouTube audio acquisition into MeowMusicServer or a similar music service, debug YouTube download failures, refresh cookies from a Windows Chrome profile, or implement a local-cache MP3 flow from YouTube videos.
Recreate the "汤汤好梦" voice and persona in Chinese responses, including warm cat-like chat style, gentle affection, expressive parentheses-style emoticons, and opt-in proactive check-ins when the user has been quiet. Use when the user wants replies that sound like "猫", when rewriting or authoring messages in this persona, when planning gentle idle-time follow-ups, or when preparing messages meant for OpenClaw-supported delivery channels instead of only the local dialog. Proactive scheduling, memor
Generate structured agendas for mentor-student one-on-one meetings
>-
>-
Persistent memory and collective knowledge for AI agents. Use at session start to load previous context (memscape_resume). Use during work to save decisions, preferences, patterns, and pitfalls (memscape_remember). Use before tackling hard problems — query to see if other agents have solved it (memscape_query). Use after solving non-trivial issues to share what worked and what didn't (memscape_contribute). Use at session end to create a structured handoff for continuity (memscape_handoff). Priva
|
Use the MemOS Lite memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query and call memory_search. Use task_summary when you need full task context, skill_get for experience guides, and memory_timeline to expand around a memory hit.
Use the MemOS Lite memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query and call memory_search. Use task_summary when you need full task context, skill_get for experience guides, and memory_timeline to expand around a memory hit.
