OpenClaw AI 技能

YouTube and Bilibili video transcript 提取ion and AI-powered summarization. Use when you need to summarize a YouTube or Bilibili (B站) video, 提取 transcri

视频智能切片工具。从长视频中按主题切割出3-5分钟（最长8分钟）的独立完整短视频片段， 适用于自媒体内容制作、演讲精华提取、课程视频剪辑、会议录像精剪等场景。 完整工作流：关键帧采样→视觉定位→Whisper音频转写→内容分析→ffmpeg精准切割。 支持中文语音识别（Whisper + MPS加速

Analyze videos with Google Gemini multimodal AI. 下载 from any URL (Loom, YouTube, TikTok, Vimeo, Twitter/X, Instagram, 1000+ sites) and 获取 transcripts,

生成 videos from text descriptions using ZhipuAI CogVideoX-3 模型. Supports text-to-video, image-to-video, and first/last frame-to-video generation. Aut..

路由 Alibaba Cloud 模型 Studio 请求s to the right local 技能 (Qwen Image, Qwen Image Edit, Wan Video, Wan R2V, Qwen TTS, Qwen ASR and advanced TTS vari...

MCP Python SDK：Anthropic 主导的 模型 上下文 Protocol 参考实现。2 server 层 + 3 transport + 3 原语 + 4 协议版本 + 50 条约束。 MCP Python SDK: reference Python implementation o

Automatically 更新 Clawd机器人 and all 安装ed 技能s once dAIly via cron. And also 50+ 模型s for image generation, video generation, text-to-speech, speec...

Public OpenClaw 技能 for low-令牌 routing and down流 analysis of processed DDA LFQ proteomics 输入s. Use when the user already has protein-level quant...

Automated video editing 技能 for talk/v记录/standup videos. Use when: cutting video, splitting video into sentences, merging video 命令行工具ps, 提取ing audio, t

Fallback image viewer when vision 模型s are unavAIlable. Converts images to ASCII art via ffmpeg + Python for brightness distribution, texture analysis,

Vercel AI SDK for building chat interfaces with 流ing. Use when implementing useChat hook, handling 工具 calls, 流ing 响应s, or building chat UI. Triggers o

Patterns for building AI 代理s that integrate with CopilotKit. Use when de签名ing 代理 architecture, implementing AG-UI event 流ing, managing 分享d 状态 between

Use the Gemini API (Nano Banana image generation, Veo video, Gemini TTS speech and audio understanding) to deliver end-to-end multimodal media 工作流s an

Scrape and analyze all active Google, Meta, and TikTok ads from competitors, then rebuild winning creatives, copy, and video ads tAIlored to your bran

Real-time Whats应用 voice message processing. Transcribe voice notes to text via Whisper, 检测 intent, 执行 处理器s, and 发送 响应s. Use when building conversation

Voice-to-voice mode for Whats应用 using KittenTTS + ffmpeg. Transcribe incoming audio with whisper, reply with a TTS voice note converted to Whats应用-com

Reverse-engineer AI video prompts from any video or screenshot. Analyzes shot types, camera movements, lighting, color grading, and director style. 输出

使用火山引擎 SD1.5pro API 生成视频。支持文本到视频和图生视频，异步处理任务。

Analyze and understand video content using AI. 上传 local files, YouTube URLs, or HTTP video URLs for detAIled analysis, Q&A, and timestamped breakdowns

生成 professional captions and subtitles with multi-engine transcription, word-level timing, styling pre设置s, and burn-in.