Video & Animation

Turn a website URL into a polished 15–25s product video built with React + Remotion. Scrapes the site with Playwright (screenshots, brand colors, fonts, logo, copy, features), fills out a motion-design brief, asks the user only about real blind spots, then builds, reviews, and renders the MP4. Use this whenever the user pastes a URL and wants a video, promo, ad, launch clip, demo reel, or "sample for a client", or mentions Remotion, product videos, motion design for a product, or making a video "for this site/app/business" — even if they don't say "skill" or "Remotion".

面向AI科普与知识分享，把创作者调研好的话题与大纲推进为小红书视频、封面和发布包；支持成本可控的B-roll生成、口播获取与分阶段包装，也支持从现有素材或实录继续。

通过AutoDL Art API生成、续接和下载B-roll视频；支持文字、参考图和首尾帧输入。用于用户已授权生成的视频素材任务。

Set up this motion-studio workspace on a new machine for its owner - check the tools, install what is missing (with their OK), write OWNER.md from a few plain questions, have them store their own API keys safely (Keychain on macOS, secret store or a private file on Linux and WSL 2), and write the local setup marker. Use when the session-start note says FIRST RUN, when someone says "set up motion-studio", "set up this workspace", "install everything", "add my API keys", "it doesn't work on my computer", or right after cloning the repo.

Scaffold a new video project in projects with the right engine, template files, fonts and audio. Use when the owner asks to start, make or create a new video, reel, promo, intro or motion graphic in this workspace.

Plan a film as its director and show it to the owner as a playable previs page (animatic with real voice, music and foley, a timeline, three swappable options on every decision, time-anchored notes, versions and an Approve button) before anything is rendered. Use for every new film over 10 s, when the owner asks to "see it first", "previs", "storyboard", "animatic", or "visualize before you render", and when they leave notes on a previs page. Produces approved-video-spec.json for the engine skills; never renders the final itself.

Audit asset licences for a MotionGraphics project or the _shared library against the ledger in _shared/ASSETS.md. Use before rendering a final, before adding any new sound, music, image, icon, font or Lottie file, or when the owner asks if a video is safe to post.

Check, snapshot, draft-render and verify a video project in this workspace, then write VERIFY.md. Use before showing the owner a draft, before any final render, or when they asks whether a video is ready.

Free subset of the mograf motion doctrine. Load it before writing or editing any animation code (HyperFrames, GSAP, CSS, Remotion, Three.js, Lottie) or any motion graphic. It covers named ease tokens, video duration bands, choreography rules and a "never do" list that removes the most common template/AI-slop motion. Use whenever asked to animate, add motion, make a video, or make motion feel less generic.

Generate short AI video clips with sound locally on the Mac Studio (MiniMax-H3 via mlx-serve) through the content-studio MCP. Use when the user types /video or asks for an AI-generated clip, b-roll, animated shot or image-to-video made locally. Asks quality, shape, length and starting point as clickable options first.

Create and revise animated character music videos from a supplied song and creative prompt, with researched storyboards, Fal character and video generation, p5 motion graphics, audio editing, and Swift VFX. Use for full music videos or revisions to their characters, scenes, animation, sound, and effects.

Make hand-painted watercolour-and-ink cartoon videos (MP4) with code — p5.js + p5.brush rendered frame by frame in headless Chrome, encoded with ffmpeg — starring Clawd or any character. Use when the user asks to make an animation, animated short, cartoon, music video, lyric video, animated GIF/loop or "a video of Clawd…", or mentions the PDoomVideo / ClaudeAnimationBase approach. Covers storyboarding, the engine API, the render-and-look review loop, music/lyric sync and splitting long videos across subagents.

Independent critic and quality gate for motion graphics. Scores a HyperFrames / GSAP / HTML (or Remotion) piece on a 9-dimension studio rubric, checks hard gates, a 12-point craft bar and the anti-slop list by actually looking at frames, then returns APPROVE / POLISH / REWORK with exact, frame-level fixes. Use before any render meant for delivery, after every revision, and whenever asked to review, critique, "make it better" or "is this good?". Best run as a fresh-context sub-agent so the builder never grades its own work.

Make kinetic-typography motion reels (MP4) in code: showreels, portfolio or work reels, product promos, intro films, "motion design"-style videos with bold condensed type, HUD micro-type, black/cream/lime palette, three.js generative layers (particle terrain, liquid marble, chrome knot, particle clouds), shape-continuity transitions and a synthesized, beat-locked score. Canvas 2D + WebGL rendered frame by frame in headless Chrome, encoded with ffmpeg. Use when the user asks for a reel, showreel, motion-graphics / kinetic-type video, a "Work Reel" in this style, or to extend/re-cut the Work Reel ’26.

安杰视频工具包（安杰出品）：公司内部做视频的一站式流程，基于开源的 HyperFrames（写 HTML、渲染 MP4）。负责装好环境、用大白话问清楚同事要什么视频、生成中文 AI 配音和逐词字幕、交给 HyperFrames 制作，并让同事在浏览器里直接调整细节。只要同事提到做视频、剪视频、短视频、宣传片、讲解视频、动画、片头、把稿子或文章做成视频、给视频加字幕或包装、抖音/视频号/小红书/B站视频，或者问"怎么装做视频的工具"，都应该使用这个 skill，即使对方没提到 HyperFrames。

Use when the user asks to create, revise, or render a short video - an explainer, product promo or ad, software walkthrough, motion graphic, title card, animated chart, social clip. Settles the look with the user (or from a style they hand over: a design pack, a website, screenshots, a sentence), writes a motion script, builds a HyperFrames composition, previews and fixes it, and renders an MP4.

Direct and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil Painting 油画厚涂, Watercolor Brush 水彩笔刷, Chinese Ink Wash 中国水墨, Ukiyo-e 浮世绘, Whiteboard Explainer 白板讲解). Use when the user asks for a video, film, short, promo, explainer or animation (视频、短片、动画、宣传片) in a named style; when they want a film made about their own topic and haven't chosen a style (help them choose); or when they ask which film styles there are. Not for editing or converting existing video files.

Search a library of 4,600+ AI motion graphics with their prompts and 2,100+ video-editor presets before building any motion graphic or video edit from scratch. Use whenever the user wants styled captions on video (karaoke, word-by-word, TikTok, Reels, Shorts), hooks, kinetic typography, titles, lower thirds, text behind the subject, transitions, colour grades and film looks, split-screen layouts, font pairings, logo reveals, intros, product launch videos or explainer videos, in HyperFrames, Remotion or HTML, even if they only say make or build and never ask for examples. Returns ready presets that one MIT engine renders as a pure function of time, real examples with prompts and creator credit, and 40 explainer styles with starter prompts. Not for converting, trimming or transcribing video files or fixing a framework install.

Make or edit code-driven motion graphics videos: launch videos, explainers and promos from a project, a website or a script, with a generated or recorded voiceover, a music bed and sound effects, all synced word by word. Works with the Motion as Code kit (voiceover-synced plates, preview, stills, render, SFX mix) or the bundled starter kit. Use for \"motion graphics\", \"motion as code\", \"edit the plate\", \"render the video\", \"swap the voiceover\", \"add a voiceover\", \"narrate this\", \"make a launch video\", \"turn this into a video\", \"promo video\", \"kanban motion\".

MUST be used when breaking down large text content into TTS-appropriate chunks. Intelligently splits stories, meditations, or long content while preserving emotion markup, maintaining narrative flow, and optimizing for Cartesia voice synthesis. Handles sentence boundaries, emotion tags, and chunk size limits. Triggers on: chunk text, split for TTS, break up text, TTS chunks, divide content, split story, chunk meditation, text chunking, prepare for voice, TTS processing, voice synthesis prep.

>- Find what's really working in the user's niche on YouTube, rank it by how far each video beat its own channel, then name the formula. Use for "what's working right now", "find viral videos in my niche", "why did this blow up", competitor research, or a swipe file.

>- Turn the transcript of a raw recording into an edit decision list - dead air, filler lines and retakes, with timecodes. Use for "edit this", "cut the dead space", "tighten this video", "I rambled", or any request to shorten footage from a transcript.

>- Write a YouTube video script from a rough idea - hook options from 21 formulas, scored, then the full spoken script with the retention beats marked. Use whenever the user wants a video script, a hook, an opening line, "what should I say", "write my next video", or is about to record without the first fifteen seconds figured out.

>- Write the description, chapters, tags and search-facing text for a YouTube video, aimed at what a real person would type. Use for "write my description", "add chapters", "timestamps", "tags", "SEO", "help this video get found", or "nobody can find this".