Video & Animation

The ultimate YouTube creator skill. Covers channel audits, video SEO, retention-engineered scripts, hook writing, thumbnail briefs, content strategy, content calendars, Shorts optimisation, analytics interpretation, monetisation planning, competitor research, cross-platform repurposing, upload metadata packages, and data-driven video idea generation. Triggers on: "youtube", "channel", "video", "views", "subscribers", "watch time", "shorts", "thumbnail", "CTR", "retention", "monetize", "script", "hook", "upload", "youtube audit", "video ideas", "content calendar", "competitor analysis", "repurpose video", "youtube seo", "youtube strategy", "youtube analytics".

Download, transcribe, cut, subtitle, document, verify, and upload course videos when reusable processing rules or custom merged and non-merged outputs are needed.

Draft and refine prompts for video generation models (including text-to-video, image/keyframe-to-video, and reference-driven generation), and create character-sheet prompts for image models when the goal is character consistency before image-to-video. Use when a user asks for a "video prompt", a model-specific prompt such as MiniMax H3, Seedance 2.0, Seedance 2.5, Ovi, Veo 3, Wan 2.2, Wan Animate 2, LTX-2, LTX-2.3, or LTX-2.5, or a consistent-character prompt such as "character sheet prompt", "character turnaround", "character reference sheet", or "photographic identity sheet".

Build and edit animations in WeDo Claude Motion (the Motion Studio editor on localhost:3000), and answer the requests a designer sends from its Ask Claude tab. Use for any request in this workspace to make or change a video, animation, motion graphic, promo, teaser, intro, title card or reel (the user wants these created as layer-based Motion Studio scenes, not rendered video files), for "check Claude Motion" / «کلاد موشن رو چک کن», for "listen to Motion Studio" / "به موشن استودیو گوش بده", and whenever a `motion-bridge wait` background task finishes.

Turn raw footage into a finished, postable video in Adobe Premiere Pro — both talking-head/screen-recording clips AND no-dialogue montage/B-roll (room tours, walkthroughs, trip footage, property/product showcases). Use whenever the user has recorded video and wants it edited, cleaned up, color graded, cut together, or made ready to post — even if they just say "edit this video," "cut this together," "make this postable," or hand over a raw clip/folder of clips without further instruction. Drives the premiere-pro MCP tools directly (project/sequence creation, cutting, transitions, color, captions, export) plus claude-video-vision for audio analysis and clip review — do not attempt this by hand-waving through Premiere's GUI.

>- Use this skill when automating Blender via Python, configuring high-performance Cycles GPU renders (OptiX, denoising, Fast GI), resolving Blender 5.2+ API changes (compositing node groups, media_type VIDEO), and rendering animations to MP4/H.264.

Construit et rend la vidéo HyperFrames d'Oba à partir du storyboard, dans la charte verre et Apple du studio. À utiliser après le storyboard et la voix.

Make a motion-design video for a SaaS product that shows the real, working UI in motion. Use when the user asks for a product video, launch film, demo reel, promo or explainer for a software product. Covers planning and the shot list, the script, theming from the product's own UI, motion and easing rules, UI choreography, camera, transitions, sync, optional voice-over, a pre-render quality check, and a stills review with the user before rendering.

為老師將教材與素材製作成教學動畫影片，涵蓋需求訪談、分鏡、配音字幕、實拍整合、Canvas 與 Three.js 運鏡、HyperFrames 合成。適用教學 Shorts、概念解說與課堂影片，可先做樣片或直接完成。

Use when building, editing, retiming, or rendering HyperFrames compositions or frame sub-compositions — especially multi-frame promo/launch videos, when a frame "passed checks" but hasn't been looked at, when retiming GSAP tweens, or when output quality feels below a previous run. Also use when debugging blank frames, dead-air gaps, buried/overlapping cards, or timelines that never register.

(Also dubs the video into another language with a new voice and lip-synced mouth.) Turn a talking-head / spoken video into a polished, high-retention Reel/TikTok/Short - word-synced captions (Arabic/RTL and English), animated key-word callouts, infographics/diagrams/UI cards timed to what is said, camera punch-ins, brand logo placement, subtle synthesized SFX, loudness-normalized audio. Use when the user attaches a video and asks to edit it professionally, add captions/motion graphics/infographics/SFX/logo, or make a reel/short from it. Works fully offline in the cloud sandbox (ffmpeg + headless Chromium + GSAP + sherpa-onnx Whisper).

Build a Tatakye-style data-explainer short video as a self-contained HTML page (Canvas + Web Audio, no deps). Use when the user wants to turn an article/essay into a short video (3-6 min), especially minimal black-gold aesthetic with particle fields, animated curves, big-number reveals, sparse ambient audio, and subtitle-driven narration. Produces a single HTML file the user plays in-browser and screen-records.

Build an mp4 cover/teaser video from a folder of numerically named stills (01.jpg, 02.jpg, ... up to 200 and beyond). Use when the user asks to turn a folder of numbered images into a video, make an image-flip reel or slideshow, add soft crossfade transitions between images, or export a "cover" video from jpgs in a folder — ignoring non-numbered images such as logo.jpg, discord.jpg or cover.mp4.

Standard für JEDES TikTok-Video des Users. Erzählt Geschichte, Ereignisse und Gedankenexperimente in stilisierten 3D-Szenen mit Three.js in HyperFrames, im Stil der Referenzen (Tsunami 2004, Titanic 1912, Fehlalarm 1983). Immer auf Deutsch und in der Du-Form, mit Countdown-Titel oben links, kursiven Wort-für-Wort-Untertiteln mit blauen Schlüsselwörtern und einem Erklärteil („Warum?“) als flache Schemagrafik. Gilt für jede Video-, Themen- oder Skriptanfrage für seinen Kanal.

NUR verwenden, wenn der User ausdruecklich den Karten-/Geopolitik-Stil (Satellitenkarte, eingefaerbte Laender, geomania99) verlangt. Standard fuer neue Videos ist doku-3d-video.

为任意 GitHub 账号生成一条 ≤28 秒的简历宣传视频：真实主页截图做封面（横切面平躺、由远到近动态立起）+ GitHub 白色仓库卡片（Star 数字滚动计数、README 总结逐条滑入）+ 纸条式结尾。全部文字本地渲染，零 AI 生成文字、零拼写错误。适用于"给这个 GitHub 做个宣传视频/简历视频/同款视频"类请求。

Standing rules for making and editing video with the video-studio plugin — free tools only (free DaVinci Resolve 21.0.x, HyperFrames local render, ffmpeg, the local media toolbox), never touch raw recordings, work non-destructively, keep project files in the studio folder, plus the user's own house rules from their studio profile. Read before any DaVinci Resolve, HyperFrames, animation, audio, color, render or Shorts task, and before suggesting any tool, upgrade or paid feature.

Edit a long-form screen or camera recording in DaVinci Resolve with Claude: transcribe the mic, map the transcript to the timeline, propose cuts (filler, long pauses, retakes), apply the approved ones, add HyperFrames overlays timed to spoken words, mix SFX, and render. Use when the user runs /edit-recording or asks to edit, tighten or add graphics to a recording or Resolve timeline.

Adds motion-graphics effects to a vertical talking-head video with Remotion. Use it when the user wants to edit a 9:16 reel or short, add zooms, cut-outs, chat windows, headlines, charts or other effects to their own footage, or assemble a cut list of effects timed to what they say.

Pull the slides out of a recorded seminar, lecture or conference talk (YouTube, Vimeo, Panopto, Zoom recording or a local video file) as one PNG per slide change, timestamped and built into a PDF. Use this whenever the user wants the slides, figures or a slide deck from a talk video, e.g. "grab the slides from this seminar", "get the figures from this YouTube talk", "make a PDF of the slides in this recording", "I only have the video, not the slides", even if they never say "crawl", "extract" or "frames".

把任意主题做成视频，按内容形态自动选择渲染后端。黑底 MG 概念科普（Remotion）、连续公式推导证明（Manim）、真终端操作教学（asciinema，V2）、产品宣传短视频（Hyperframes，V3）。内含渲染器无关的公共层（调研规范、口播文案原则、TTS 配音时间轴、分镜令牌系统、读帧 QC 脚本）、后端路由判据树、可插拔渲染后端、多 agent 并行构建协议与 QC 判据。Turn any topic into a narrated video — routes by content shape to the right renderer: motion-graphics concept explainers (Remotion), continuous formula derivations and proofs (Manim), real terminal recordings for command-line teaching (asciinema, V2), and product promos (Hyperframes, V3). Includes a renderer-agnostic core (research brief, narration principles, TTS timeline builder, storyboard tokens, frame-reading QC scripts), a routing decision tree, pluggable backends, and multi-agent build/QC protocols.

Read public YouTube data with the YouTube Data API v3 and an API key: search videos, channels and playlists; get video details and statistics; resolve a channel from a @handle or URL and list its uploads and playlists; list playlist items; read comments; get trending videos and categories. Use when a task needs facts or numbers from YouTube (research, competitor or channel reports, finding videos, collecting comments). Don't use to upload, edit, delete, like or comment (those need OAuth, not an API key), to read private or unlisted data or YouTube Analytics (watch time, revenue), or to download videos or captions.

A-to-Z video editing from a plain-language brief, for creators (Facebook, Instagram, YouTube, TikTok), ads/OVC and any everyday edit. Analyses the footage, asks the user option-based questions, then cuts, reframes, colour grades, captions (incl. Bangla), adds music, SFX, voice-over, motion graphics (Remotion) and 3D titles (Blender), cleans voice (Demucs), transcribes (Whisper), finds music by description (CLAP) and exports per platform. Use whenever a video, clip, reel, short, ad, slideshow or footage edit is requested. Not for generating new footage from text.

Edit video and audio with local FFmpeg from natural-language requests: cut, trim, join, resize/reframe (9:16, 1:1), speed change, captions and subtitles (SRT/ASS, animated, karaoke), logos and text overlays, lower-thirds and titles, silence removal, multicam and external-mic sync, loudness normalisation, HDR/Dolby Vision to SDR, LUTs, background music with ducking, platform exports (YouTube, Reels, TikTok, X), compliance checks, scene detection and highlight reels, contact sheets to inspect results, and whole-edit project files. Use this skill whenever the user mentions a video or audio file (mp4, mov, mkv, wav, m4a), footage, a clip, captions, subtitles, a reel or short, YouTube/Instagram/TikTok delivery, LUFS, sync, transcoding, ffmpeg, or asks to make something "60 seconds", "vertical", "louder", "captioned" — even when they do not say "edit". Python 3.10+ standard library only (3.9 deprecated), no cloud, no API keys.