Generate AI images using MiniMax or fal.ai (Grok Imagine) and send to messaging channels via OpenClaw
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
{ "prompt": "A candid outdoor photo of a group of adults (21+) standing waist-deep in clear water inside a rocky natural pool or cave. The background is a dark, textured rock wall, slightly wet and
{ "scene_analysis": { "environment": { "type": "Outdoor", "setting": "Patio or backyard terrace", "weather": "Sunny, clear sky visible", "background_elements": [
{ "meta": { "type": "image_analysis", "file_name": "image_5e33ac.jpg", "analyst_persona": "Technical Photo Analyst" }, "scene_environment": { "location_type": "Outdoor", "set
Create a photorealistic image of me and a wild ${wild_animal} taking a spontaneous selfie together in the animal’s natural habitat. I am smiling naturally, holding a phone at arm’s length for a se
{ "reference": { "face_identity": "${face_identity:uploaded reference image never change face and hair}", "identity_lock": true, "face_preservation": "100% identical facial structure, pr
Automatically create clips and videos from media files in a specified folder. Uses Agent Swarm for intelligent task delegation and supports cron-based schedu...
Generate platform-tuned social media captions for photography. Use when a user shares a photo and wants captions for posting. Triggers on sharing photos with...
Use when the user asks about OpenClaw — installation, configuration, agents, channels, memory, tools, hooks, skills, deployment, Docker, multi-agent, OAuth,...
Generate AI videos using Vidu — featuring text-to-video, image-to-video, reference-to-video, and start-end-to-video with up to 1080p resolution, anime style...
使用 RDK X5 上的 TogetheROS.Bot (tros.b) Humble 框架：启动 43 个预装 ROS2 算法包、管理 ROS2 话题/节点/服务、构建摄像头+AI+输出（Web/语音/HDMI）集成 pipeline、创
DEPRECATED — this skill has been merged into doc-process (v4.0.0+). Use doc-process instead for document scanning, perspective correction, and dewarping. doc...
### Scene Mirror selfie in an computer corner, blue color tone. ### Subject * Gender expression: female * Age: around 25 * Ethnicity: East Asian * Body type: slim, with a defined waist; natural body
Generate branded AI avatar lip-sync video shorts for TikTok, Reels, and YouTube Shorts. Create 15-second talking-head videos with custom avatars, auto-genera...
Registers reCamera devices, configures AI detection models/rules/schedules, monitors and clears detection events, fetches event snapshots, and runs manual im...
Image processing with oiiotool CLI — format conversion (EXR, TIFF, DPX, PNG, JPEG, HDR), OCIO/ACES color management and display transforms, exposure adjustme...
Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models vi...
Detect and route to the correct visual content type (hero shot, poster, infographic, etc.) from a text description or output type hint. Use when you need to...
Train Robotic AI Models using Qualia. Use when asked to train a robot model, check training status, manage Qualia projects, browse available model types, or...
在 RDK X5 的 10TOPS BPU 上运行单个 AI 推理算法：YOLO 目标检测、图像分类、语义分割、人脸识别、手势识别、人体关键点、开放词汇检测（DOSOD/YOLO-World）
Create high-end cinematic scene prompts and production-ready scene briefs in a Hollywood producer voice. Use when the user asks for movie scene generation, s...
{ "image_prompt": { "subject": { "type": "Adult woman (21+) matching the reference image identity", "appearance": "Fair skin, long dark messy hair with subtle red highlights, nose pi
{ "subject_and_scene": { "main_subject": "A young man with thick curly brown hair, wearing a sophisticated beige turtleneck sweater and a matching tailored wool blazer, displaying a contemplativ