QA frame-level per video generati da video-factory. Attiva quando l'utente menziona "verifica video", "controlla video", "freeze detect", "QA video", o ha appena…
Add chapters to videos by transcribing, analyzing, and generating structured markdown documents with YouTube chapter markers. Optionally generate highlight videos.
Query video analytics data and metrics from Elastic search via the VA-MCP server (port 9901). This includes incidents, alerts, sensor data, and metrics.
Tách audio track từ file video sang WAV hoặc MP3 để dùng cho transcript, khử lặp lời nói, hoặc map nhạc nền trong render plan.
Start a video call with a real-time AI avatar using the Runway Characters API. The agent sends the user a call invite link — for standups, urgent alerts, check-ins, or any…
Generates short videos on the filmmaking canvas via the local generate_video.js CLI, following canvas-aware conventions for prompt composition, reference attachment, and…
Use when planning video content strategy, writing video scripts, optimizing YouTube channels, building short-form video pipelines (Reels, TikTok, Shorts), or repurposing long-form…
Polish demo or marketing video frames, pacing, captions, and audio. Use when the user wants to polish a video, do an edit pass, or improve video quality.
Biến yêu cầu video mới (kèm Video Design Specification tùy chọn) thành creative plan, kịch bản, scene intents, overlay text và asset requirements ở mức sẵn sàng đưa vào pipeline…
智能视频创作助手，使用 Remotion 框架生成专业级动画视频。 触发场景: (1) 用户需要创建产品演示、教程、数据可视化视频 (2) 用户需要制作营销宣传、社交媒体短视频 (3) 用户需要将论文、报告、概念转化为动画视频 (4) 用户询问"帮我做个视频"、"创建动画"、"制作演示视频" 支持: 产品演示、教程、数据可视化、营销宣传、原理解释、科普内容
Convert screen recording videos (Loom, mp4) into structured keyframes + transcript for LLM consumption.
Xây dựng Video Design Specification (VDS) tái sử dụng được từ video gốc, giữ nguyên DNA phong cách và xóa thông tin nhận diện cá nhân.
Use when turning a scene idea into the 11-block cinematic prompt for live-action AI video — lens, lighting, blocking, motion, negatives.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai,…
Автоматизация видео-продакшна: субтитры, монтаж, сборка проектов для Final Cut Pro. Активируется на: 'субтитры', 'subtitles', 'монтаж', 'видео', 'auto-subs', 'auto-cut',…
Video Editor Deutsch - KI Video Bearbeiten, Schneiden und Exportieren. Videos schneiden, zusammenfuegen, Hintergrundmusik hinzufuegen, Farbkorrektur anwenden, Untertitel einfuegen…
AI Video Enhancement - Upscale video resolution, improve quality, denoise, sharpen, enhance low-quality videos to HD/4K.
视频制作全链路：素材入库 → 剧本冻结 → 全局配音 → 对齐 → 渲染 → 审查 → 交付。 Use when: 做视频、做 showcase、做教程视频、录屏剪辑、video review、节奏审查。 Not for: 纯代码开发（用 worktree/tdd）、纯文档写作（直接写）、PPT（用 ppt-forge）。 Output: schema…
Extract frames or the audio track from a local video file via ffmpeg. Pairs with openai-whisper for audio→text.
Extract frames and short clips from videos. Core Capabilities Process audio and video files using ffmpeg for transcription and analysis Extract text, timestamps, and speaker…
بايبلاين إنتاج فيديو قصير (60-90 ثانية) بالكامل بالذكاء الاصطناعي. المستخدم يعطي فكرة أو عنوان → يولّد سكريبت مقسّم لمشاهد (كل مشهد 10 ثوانٍ) → يولّد فيديو كل مشهد بـ Wan2.6 →…
AI video generation via Replicate — 17 models, editing, and production workflows
Design video concepts, scripts, shotlists, transitions, and editing notes for VEO, Gemini, and Nano Banana-based pipelines.
Use when user needs to transform or edit images using AI. Independent image-to-image command for converting reference images to different styles or content.
Tạo và quản lý các video job sản xuất biệt lập, gồm metadata yêu cầu, asset đầu vào, artifact theo stage, status, theo dõi stale, và path chuẩn cho pipeline video.
Từ scenes-with-timing.json → xác định content shape → viết visual_brief chi tiết → output video-plan.json. Dùng ở Bước 4, SAU KHI generate-audio đã chạy.
Process video files with ffmpeg automation. Use when: compressing videos for upload; extracting audio from video; resizing for social formats; clipping segments; merging multiple…
Process video files with audio extraction, format conversion (mp4, webm), and Whisper transcription. Use when user mentions video conversion, audio extraction, transcription, mp4,…
Điều phối toàn bộ pipeline video short-form dài hạn từ video mẫu, yêu cầu sáng tạo mới, raw asset, sinh voice, transcribe, semantic mapping, render plan, đến render cuối cùng.
Optimize prompts for AI video generation platforms including Sora, Runway, Pika, and Kling
Draft and refine prompts for video generation models (text-to-video and image-to-video). Use when a user asks for a "video prompt" or a model-specific prompt such as Ovi, Sora,…
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies.
Audit code-first cho Remotion source và render plan (ưu tiên overlay readability + safe-area), gom toàn bộ lỗi mỗi pass rồi áp dụng batch fix một thể, lặp tối đa 3 pass và xuất…
Chuyển VDS, creative plan, transcript, và semantic asset mapping thành TOML edit decision list chi tiết với crop, timing, text overlay, subtitle, motion, audio, transition, và chỉ…
Render video short-form cuối cùng từ TOML render plan, voice audio, source asset, subtitle, overlay, và quy tắc style VDS bằng renderer của project (Remotion hoặc FFmpeg).
Tự động tìm kiếm, tải về stock resources (video, image, music, sfx), tạo ảnh AI, và tìm ảnh trên web cho video project.
Use when the user needs to write a video script, create video content for YouTube, TikTok, Instagram Reels, LinkedIn video, product demo script, explainer video, testimonial…
Reference skill for Zoom Video SDK. Use after routing to a custom-session workflow when the user needs full control over the video experience rather than an actual Zoom meeting.
Search video archives using natural language — find events, objects, actions, and people across recorded video using fusion search (Cosmos Embed1 semantic search + CV attribute…
Short-form video generation skill — 3-10 second clips for product reveals, motion teasers, ambient loops.
Use when the user asks to create or edit videos end-to-end (script→video, auto-cut/jumpcut, captions/subtitles, polishing for Shorts/Reels/TikTok).
동영상에서 자막을 자동 생성하고 발표자료 기반으로 교정하는 스킬. "자막 생성", "영상 자막", "STT", "subtitle" 요청에 사용. mlx-whisper로 추출 → 중복 정리 → 발표자료 기반 교정까지 자동화.
Translates video subtitles across 100+ languages using DeepL API and Google Cloud Translation v3. Handles SRT/VTT timing preservation, character limit enforcement, and subtitle…
Extracts embedded subtitles from video containers using FFmpeg's subtitle stream extraction, translates SRT/VTT files through DeepL API or Google Cloud Translation v3, and…
Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly.
Use when user needs to generate images from text prompts. Independent text-to-image command for creating single images outside of video creation workflow.
Capture authentic customer testimonials through guided self-recording workflows, from outreach and briefing to recording and publishing.
Generate a folder of low-resolution frame snapshots at evenly spaced timestamps so Claude (or you) can "see" a video without ingesting the full file.
Watch a tutorial or demo video and generate a Claude Code skill from it. Activated when user says "create a skill from this video" or similar.
Create professional videos autonomously using AI -- voiceovers (Qwen3-TTS with voice cloning), image generation (FLUX.2), background music (MusicGen), talking head animation…
Video/audio transcription, visual frame analysis, Groq Whisper long-form transcripts, timestamped Obsidian notes, and keyframe-based visual summaries.
Extract full transcripts from video content for analysis, summarization, note-taking, or research. Use when the user wants a written version of video content, asks to "transcribe…
Download, transcribe, inspect, summarize, or convert video and audio sources. Use when the user wants transcripts, subtitles, audio extraction, or media downloads from a video…
Translate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact.
Call the vss agent to run video understanding on video to answer a text question. Use when the user asks about video content, or about visual details that cannot be answered from…
Upload video tự động lên TikTok, YouTube, Facebook, Instagram bằng browser automation (Playwright). Vì các nền tảng này không có public API cho upload, phải dùng browser…
Video-Verhandlung beim SG nach § 110a SGG. Wer kann teilnehmen Technik Vorbereitung Verlauf. Praktische Hinweise für Buerger mit gesundheitlichen Einschraenkungen.
Video-Verhandlung nach § 128a ZPO. Teilnahme an muendlicher Verhandlung per Bild und Ton-Übertragung. Antrag technische Voraussetzungen Einverstaendnis-Pflichten.
vLLM-Omni output-side multimodal generation — image (FLUX.1/2, Qwen-Image, GLM-Image, BAGEL, SD3.5, HunyuanImage-3.0), video (Wan2.1/2.2, LTX-2, HunyuanVideo-1.5), TTS (Qwen3-TTS,…