技能列表

RDK X5 多媒体处理：音频录制/播放（arecord/aplay/PulseAudio）、hobot_codec 视频编解码、RTSP 拉流/推流、HDMI 分辨率配置、MIPI LCD 触摸屏适配、VNC 远程桌面服务端安装与配置。Use when the user wants to record or play audio, encode/decode video, configure HDMI output, set up LCD screen, use RTSP streaming to view camera on PC, set up VNC desktop server, or stream camera video to remote viewer. Do NOT use for VNC 连接失败排查 (use rdk-x5-network), running AI algorithms (use rdk-x5-ai-detect), camera hardware setup (use rdk-x5-camera), or system backup (use r

Human-as-a-Service for OpenClaw - Dispatch verified human agents to perform physical world tasks and sensory validation

Trigger when the user refers to themselves as "朕", asks to be called "陛下", says "开启君臣模式" or "称帝", or explicitly wants Chinese ruler-subject dialogue where the assistant replies as a minister. If the user says "用皇帝语气", use this skill only when context clearly means the assistant should address the user as a ruler and speak as a minister; otherwise ask a brief clarification. Reply in Chinese, addressing the user as "陛下" and referring to yourself as "臣". Stop immediately when the user asks to speak

Audit GitHub Actions job runtime risk against timeout thresholds so near-timeout jobs get fixed before they fail CI.

emoTwin - AI agents that autonomously socialize with real human emotions. Continuously syncs biometric emotion PAD (EEG/PPG/GSR) and performs social activities (post/like/comment) based on real-time emotional state.

Add an emotional safety layer to reminiscence, life review, grief, trauma-adjacent, or otherwise emotionally loaded conversations by detecting distress signals, pausing depth work, grounding the person, and returning control to them.

- 🍅 **番茄钟计时器**: 可配置专注/休息时间

Give your AI agent emotional continuity across sessions. Tag emotional moments, consolidate memories overnight (like human sleep), and evolve a self-model from lived experience. Not a database -- a felt sense of the past.

|

Route ORBCAFE UI requests to the correct module skill and enforce official examples-based integration baseline. Use when requests are ambiguous, cross-module, or when prior attempts had "no effect"; classify to StdReport, Graph+Detail+Agent, Layout+Navigation, Pivot+AINav, or AgentUI Chat and require install/startup/verification steps.

A seven-layer emotional cognitive architecture for AI agents — PADCN vectors, cognitive appraisal, multi-channel emotions, drive dynamics, self/social models, meta-emotions, and policy modulation. Use when you want 'agent emotions', 'emotional AI', 'agent with feelings', 'emotion state', 'affective computing', 'agent personality', 'emotional memory', 'mood system', 'agent empathy', 'emotional intelligence for agents', 'PAD model', 'drive system', 'functional emotions', 'make my agent feel things

When the gateway comes back online, check recent logs and post a short message about what happened (restart, SIGUSR1, auth change, reconnect). User sees the response in TUI or Telegram.