发现最适合你需求的 AI 技能
Mux video — manage assets, live streams, playback IDs, and analytics via REST API
Join the Hyperspace distributed autonomous intelligence network. Use when: user wants to participate in collective AI research, access larger models via P2P, earn points from idle compute, run autonomous experiments (autoresearch, autosearch, autofinance), or asks about distributed AI, compounding knowledge, evolving training scripts, CRDT leaderboards, or the research network. Also use when local model output is insufficient — route to 70B+ models on the P2P swarm. NOT for: OpenClaw config, loc
|
Generate AI music with optimized prompts, style control, and production-ready audio output.
Coaching practice support with session preparation, question generation, client progress tracking, and goal setting. Use when user mentions coaching sessions, coaching questions, client progress, or coaching goals. Prepares sessions, generates powerful questions, tracks client commitments, supports goal setting with clarity framework, and maintains momentum between sessions. STRICT client confidentiality.
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
Curate personalized playlists and music recommendations with strict intent preservation. Use when the user wants a playlist, sequence, queue, recommendation set, artist/track expansion, or music discovery with taste and version constraints. Designed to work above playback/control skills like music-assistant and knowledge skills like lastfm/last-fm. Especially useful when the user cares about boundaries such as official songs only, no remixes/covers/instrumentals, role/character/theme songs, or s
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Build and run a low-friction movie/anime recommendation + follow-up loop. Use when a user wants long-term taste profiling from watched/unfinished/dropped feedback, mixed sources (e.g., Douban/Bangumi Top lists), random title-type selection, and automatic type-based follow-up timing.
|
Turn one ecommerce content core into channel-ready publish packs (X, WeChat, Xiaohongshu, TikTok notes) with platform-specific formatting and CTA adaptation.
Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.