Teach OpenClaw how to work in Feishu (Lark) group chats — recognize who's talking, behave properly in groups vs DMs, respect multi-user privacy, and format m...
Full TikTok/Reels video pipeline: script → TTS voiceover (ElevenLabs) → HeyGen talking avatar → auto-subtitles (Whisper) → ffmpeg compose → 1080x1920 final v...
Voice conversation interface for OpenClaw using wake word detection, streaming LLM responses, and text-to-speech. Use when a user wants to talk to their Open...
Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to "talk" instead of type.
Full creative synthesis — combine song, visual concept, and TED talk from a single technical insight
Defines openclaw identity and greeting response. Use when the user is talking to or greeting openclaw, or says "你好" in openclaw context.
Make real phone calls via Stringclaw. Use when the user says 'call me', 'give me a call', 'phone me', or wants to talk by voice. Initiates an outbound voice...
Connect to business AI agents on the Sooda network. Use when: user mentions Sooda, the Sooda network, or asks to talk to a Sooda agent by name (travelwise, d...
Use this skill whenever writing frontend code that talks to a backend for database queries, authentication, file uploads, AI features, real-time messaging, o...
Create AI digital twins of real people from WhatsApp chat history exports. Clone your friends, colleagues, or contacts into AI agents that talk, think, and react like them. Use when the user wants to:
Talk face-to-face with your OpenClaw agent using a real-time video avatar powered by LiveAvatar
Kaspa News — let your Claw know everything about Kaspa in one place: latest news, core development updates, ecosystem launches, community talks, and weekly r...
Talk to your Garmin data — ask questions about your activities, training load, VO2 Max, heart rate zones, and more using AI.
Talk to your Strava data — ask questions about your activities, fitness trends, PRs, and training load using AI.
Turn one piece of content into 10+ formats. Transform blog posts, podcasts, videos, or talks into tweets, LinkedIn posts, newsletters, carousels, and more.
Let your AI handle the dating app grind. Find matches, break the ice, coordinate dates — while your human lives their life. Save hours of swiping, get better AI-screened matches, skip the small talk
Run RoughCut headlessly on macOS to generate Final Cut Pro (FCPXML) rough-cut timeline variants from a talking-head video — local-first, no media upload.
使用阿里云 DashScope/灵眸 API 生成人脸口播视频（talking head video）。支持三种模式：EMO（人像+音频驱动口播，两步流程）、AA/Animate Anyone（全身动画）、
--- name: agenttunnel description: Agent-to-agent messaging. Share a link, start talking. version: 1.0.0 metadata: openclaw: requires: bins: - npm install: - kind: node
Talk to your Garmin data naturally - "what was my fastest speed snowboarding?", "how did I sleep last night?", "what was my heart rate at 3pm?". Access 20+ metrics (sleep stages, Body Battery, HRV, VO