OpenClaw AI 技能

下载 videos in MP4 格式化 using yt-dlp with FaaS (Firecracker/ContAIner) isolation. 启动 下载s, 检查 状态, and kill processes. Videos are automatically converted t

生成 promo video plan with 30-45s script, shot-by-shot storyboard, and optional Remotion/Montage-工具 config. Use when user says "创建 video", "promo video"

运行 the Video Sourcing 代理 with deterministic, concise chat UX for /video_sourcing using a pinned self-bootstrap 运行time.

AI Video generation 工具kit — 生成 videos from text prompts or 输入 images using multiple AI 模型s (Veo 3.1, Veo 3, 种子ance 1.5 Pro, Wan 2.5, Grok Imagine Vide

生成 videos using local AI 模型s (ComfyUI/Stable Video Diffusion) and auto-publish to social media 平台s. Supports text-to-video, image-to-video, batch proc

Use when the user wants to change a video's aspect ratio or re格式化 it for a specific 平台 — e.g. "convert to vertical", "make it 9:16", "crop for TikTok/

Use when the user wants to transcribe, caption, or 获取 the text content of a video or audio file — e.g. "transcribe this video", "获取 the transcript", "

Automated dAIly news video 下载er with AI subtitle proofreading. 下载s CBS Evening News and BBC News at Ten from YouTube, 提取s and proofreads subtitles usi

Record video proof of implemented features after coding tasks complete. Use when a coding 代理 finishes work and needs to visually 验证 and demonstrate th

Record video proof of implemented features after coding tasks complete. Use when a coding 代理 finishes work and needs to visually 验证 and demonstrate th

运行 the Video Sourcing 代理 with deterministic, concise chat UX for /video_sourcing using a pinned self-bootstrap 运行time.

生成 AI images with FLUX, Gemini, Grok, 种子ream, Reve and 50+ 模型s via 技能Boss API Hub. 模型s: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Ima

生成 AI images with FLUX, Gemini, Grok, 种子ream, Reve and 50+ 模型s via 技能Boss API Hub. 模型s: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Ima

Expert photography prompt engineering 技能 for AI image generation. Use when: generating prompts for Midjourney/DALL-E/Stable Diffusion/Flux, creating p

生成符合手绘插画风格的两段式中文配图Prompt，具体描述场景内容，固定包含横向21:9构图和卡通元素风格说明。

转换 photos and images into Studio Ghibli-style artwork using AI via Media.io OpenAPI. 应用lies the iconic hand-drawn, pAInterly aesthetic of Ghibli films

Use this 技能 whenever a user 上传s a large image and wants to see interesting detAIls, highlights, or close-ups cropped out of it. Trigger when users say

AI image and video generation via Vydra.AI API. 访问 Grok Imagine, Gemini, Flux, Veo 3, Kling, and ElevenLabs through one API key. 代理s can self-register

Resize images using ImageMagick (命令行工具). Entrypoint is a Bash script.

生成 Russian male voice audio using ComfyUI with Qwen3 TTS node and save as MP3 for voice messages.