Motion graphics skills
Agent skills and pipelines for motion graphics made in code: launch videos, explainers, animated type and B-roll timed to narration. Most render through HTML, Remotion or HyperFrames. Results depend heavily on the brief and the review loop, not one prompt.
Lab posts (32)
- OpenMotion goes open source: recreate a reference video with your own brand, plus MOTION.md guides
The OpenDesign team officially open-sourced OpenMotion today under Apache-2.0. You hand your coding agent a reference video or a social link, it rebuilds the shots as editable HTML with your brand kit, and you fine-tune the cut in a Studio timeline before rendering an MP4. It ships with 300+ MOTION.md guides and works with 22 local agents.
- Kling Image 4.0 launches with native 8K and image sets, Kaggle opens a Code2Video Arena, and HyperFrames reaches 0.9.63
Kling's new image model is live in the app and API, with native 2K, 4K and 8K output, sets of up to 10 consistent images and up to 2,000 characters of rendered text. Also: Kaggle and HeyGen opened a blind-vote arena for models that write motion design as code, HyperFrames shipped three releases overnight, and a few smaller notes.
- raea and 67.js: two young render engines built for agents to drive, from React video to path-traced 3D
raea lets an agent write video, motion graphics and 3D as React and TypeScript, then renders it on your own GPU with no browser in the loop. 67.js is an MIT 3D engine an agent edits over MCP, checks with PNG previews, and renders to stills or MP4. Both are weeks old, moving fast and worth a look if Remotion or HyperFrames renders are your bottleneck.
- chrome-capture: record a Chrome tab to a 60-120 fps MP4 with audio, no ffmpeg (handy for code-made video and demos)
Paul Irish of the Chrome team released chrome-capture on Nov 9, a tiny Apache-2.0 npm package around a new Chrome 153+ DevTools API that records a tab straight to an AV1 MP4 at 60 fps by default and up to 120 fps or 2160p, with tab audio. If your video starts life in a browser (HTML motion graphics, product walkthroughs, agent-made explainers), it is a much faster way to get the pixels out.
- HyperFrames /reverse-any-video: rebuild a finished clip as an editable project (plus free music, SFX and stock)
HeyGen's open-source HTML-to-video framework added a skill that takes an existing video and rebuilds it as an editable HyperFrames project, then diffs the render against the original frame by frame. The reverse step is a Pro feature (about $25/month, per users quoting the pricing); the same refresh made a big signed-in asset library free. Update with npx hyperframes skills update.
- Claude Fable 5.2 is out: what it means for code-made video, motion graphics and Blender work
Anthropic released Claude Fable 5.2 on Nov 9 for all paid plans and the API (claude-fable-5-2). Within hours, the people who make video with code were posting motion graphics, HyperFrames edits and Blender scenes made with it, and Higgsfield put it behind a 3-day free trial of its MCP. Here is what changed and what it costs.
- #OpenSourceHiggsfield closes: five last-hour ComfyUI builds
Entries for ComfyUI's #OpenSourceHiggsfield challenge closed at 9 AM PT on Nov 3, and the hashtag filled with last-minute submissions. Winners are due Nov 10. These five stood out for working video makers: a 3D previs tool, a kinetic-type engine, a MiniMax H3 film studio, a song-sectioned music-video tool and a take-based shot manager.
- kinetograph renders Remotion and HyperFrames projects fast
A new engine renders existing Remotion projects and HyperFrames pages without a browser, using a Rust GPU compositor. Separately, HyperFrames shipped one grade for a whole camera lane, plus a way to bake that grade into a LUT.
- design-to-motion: a free agent skill that turns a static design into a looping MP4 and GIF showcase
Designer Elaya's ai-design-skills repo hit #1 on GitHub's all-languages trending list today. Its video half, design-to-motion, gets a coding agent to rebuild a Figma frame or screenshot as HTML, act out every chart and list, and record a frame-exact MP4 for X plus two GIFs.
- Same script, same footage: a creator rebuilt his talking-head graphics in Remotion and HyperFrames, then retired Remotion
Guney Topcu had Claude Code build motion graphics for one talking-head video twice. Remotion got his months-refined workflow; HyperFrames got the script, the voice track and no revisions. He liked the HyperFrames cut more and says why, and HyperFrames itself moved house today.
- Motion2Code: let a video model design the motion, then have your agent rebuild it as editable SVG + GSAP
An MIT skill for Claude Code, Codex, Cursor and about 70 other agents. It studies a motion-design clip frame by frame, rebuilds it as one looping HTML file on a single GSAP timeline, then scores the code against the source.
- Code-video engines this week: Remotion adds shatter() and curves(), HyperFrames gets GIF export and a Windows app
Remotion's Oct 26 release grows @remotion/effects again with 3D fragment breakups and colour curves you can edit in Studio. HeyGen's HyperFrames shipped four patch releases the same day, with GIF export, a Windows app offer and faster scrubbing on long films.
- EffectCraft: an open-source, After Effects-style compositor in pure Rust that agents can drive over MCP
The ArtCraft team, which also makes FilmCraft and PhotoCraft, has a motion graphics app with compositions, layers, keyframes, 300+ effects, expressions, 3D cameras and lights, Lottie import/export, and a render queue. Every action goes through one command registry, so a CLI, a JSON channel or an MCP server can drive it. It is alpha, Apache-2.0, and passed 7,700 stars in three weeks.
- OpenAI's devrel cut a launch video in HyperFrames with an agent that picks up 'feedback ready' notes and re-edits on its own
Romain Huet's 2-minute Decisions API GA video was edited entirely in the cloud with HyperFrames. Brent Schooley's agent watched an internal review app: when Romain marked an edit 'feedback ready', the agent started the next revision. It is a pattern you can copy with any review tool.
- Don't start an Opus 5.5 film from a blank prompt: the open repos that show their prompts and code
@RoundtableSpace rounded up eight repos where every Opus 5.5 video comes with its prompt and source. Four of them are worth cloning: a 51-style film skill, a 15-style motion kit with a review rubric, a hand-painted cartoon base, and a 4K60 karaoke music video.
- Framefields: code-first video for agents that renders on the GPU, with no headless Chrome
Most agent video stacks have a browser screenshot every frame. Framefields skips that: your agent writes TypeScript, and Dawn/WebGPU renders compositing, After Effects-style type, shaders and 3D straight to a hardware-encoded MP4.
- huashu-motion: an open skill that writes the launch film, scores it, and lets you point at the frame to fix it
Anthropic's Claude Motion is still a Team and Enterprise beta. Two days after 花叔 open-sourced his own take, it had more than 1,100 stars: a skill that pitches three directions, builds the film as one HTML page, writes a score that real sampled instruments play, and opens an editor where a click on the frame becomes a precise fix.
- BaoCut: an AI video agent where every caption, dub and cut stays editable
Most AI video tools render once and hand you a file. BaoCut makes the timeline the source of truth: transcripts, translations, subtitle layers, voice-overs and code-made motion graphics all live in one editable video that you and your agent edit through the same undo stack.
- motion-prompt: a clickable dictionary of motion names your agent can build from
144 named motion, camera, UI, web and photo-look effects, each with a moving sample and an example ask. Pick the ones you want in a browser gallery, press Send to AI, and the agent builds them into your video.
- Remotion 4.0.536–537: a real editing timeline, then After Effects–style effects
Two releases in four days moved Remotion closer to an editor you can share with your agent: rolling edits and interlocking transitions on Oct 16, then projections, page turns, fractal noise, turbulent displacement, lens blur and bevels on Oct 19.
- OpenDesign Motion: open-source code-to-video without the Claude Motion lock-in
Codename OpenDesign Motion: ask an agent for a video, get editable source plus an MP4. Desktop is free OSS; Cloud is paid. About 101.5k GitHub stars when we checked.
- Two Skillry video skills: ASCII glitch launch and paper-cutout story
Membership skills on Skillry: an 18s 60fps glitch hype film, and a 35–50s clay/felt storybook explainer. Both are editable browser films that also export MP4.
- Claude Motion, explained, plus the Remotion route if you're on Pro or Max
Anthropic's new Motion artifact writes animation as code, so you can fix one word or one sun without regenerating. It's Team and Enterprise only for now, but Claude Code plus Remotion gets you most of the way.
- 'One prompt' motion graphics is mostly a myth. Here's what the good ones actually did
Nikandr Surkov went through about a hundred of the most-shared Opus 5.5 motion videos and the replies under them. The 'one prompt' turned out to be a brief, references, a spec and several rounds of notes.
- HyperFrames: HeyGen's bet that agents should write video as HTML
An Apache-2.0 renderer that turns plain HTML, CSS and GSAP into frame-exact MP4, with a skill router that picks the workflow for you.
- claude-motion teaches an agent taste, then makes it check its own frames
Motion rules with actual numbers, a contact-sheet review loop, and a sound engine written in plain Python.
- A two-layer launch video: code motion over a Seedance plate
Recreate a reference launch video's style for your own product, then layer that motion over cinematic footage built in a strict four-step order.
- Remotion + remotion-dev/skills: React video your agent can write
The most established code-to-video framework now ships official agent skills. Check the license before you build a business on it.
- The 15-repo motion design stack, sorted by job
A viral list of motion-design repos, which we checked one by one and grouped by what you're actually trying to ship.
- What 418 shared prompts teach about one-shot code video
Skillry collects creators' prompts and remakes each video side by side. The prompts that work share a structure.
- Pull a brand from a URL, then animate it: Jack Roberts' Claude Design levels
Scrape the real logo, colours and fonts with Firecrawl first, so the agent animates the brand instead of inventing one.
- Six motion styles clients pay for, according to Higgsfield
A vendor's map of sellable formats, with the workflow tips worth keeping: storyboard first, HTML design sheets, and a credit tally that includes failed takes.
Skills, repos & workflows in the directory (51)
- OpenMotion Repo
OpenDesign (nexu-io) Apache-2.0 agentic video studio, open-sourced Nov 17 2026 (v0.1.0): give your agent a reference video or social link and it rebuilds the shots as editable HTML with your Brand Kit, then refine in a Studio timeline and render MP4; 300+ MOTION.md shot/timing/transition guides, 150+ brand kits, 22 local agents (Claude Code, Codex, OpenCode, Hermes, Gemini CLI and more), MCP server, ChatGPT plugin, BYOK image/video/music/voice providers; imports HyperFrames projects. Install only from the official repo.
- brief2mp4 Skill
Qualixar's MIT skill for Claude Code and Codex (macOS, Windows, Linux): paste a written brief (length, size, exact words, beats, a 'done when' list) → SPEC.md → each beat routed to HyperFrames (type/2D), Three.js (stylised 3D), an optional 3D pack (CAD, materials, baked Jolt physics) or Blender (photoreal), ffmpeg for sound and loudness → measured render, contact-sheet stills, up to three fix rounds → final.mp4 + REPORT.md with evidence per brief line. Optional edit pack; agent-run SETUP.md.
- Scarlet Repo
Matthew Berman / Forward Future's MIT desktop AI video editor (macOS, Windows, Ubuntu preview) for dialogue-heavy footage: connect your Claude Code or Codex plan, type or speak edits ('remove false starts, keep the pauses before answers'), hear each cut in context and approve suggestions; skills for /dialogue-pass, fit-length, make-shorts, screen framing, punch-ins, captions, motion graphics; local transcription; exports MP4 or FCPXML/OTIO + SRT for Resolve, Final Cut, Premiere. Telemetry on by default (can be turned off).
- Pixelbolt Skill
skulitom's MIT agent-first pixel art and sprite animation toolkit: editable JSON recipes render deterministically to PNG sheets, atlases, APNG, GIF and numbered frames for video editors; CLI, local MCP server, browser studio and a Claude Code skill (npx -y pixelbolt@latest skill install); Node 20+, no API key or image model.
- Markerboard Skill
arifbuildsai's MIT agent skill (Claude Code or any command-running agent) for dry-erase whiteboard explainers: asks whether you supply voiceover/timings, writes a beat-numbered script and waits for approval, makes VO (ElevenLabs, MCP voice tool or local) + word timestamps, then renders one continuous board where a marker draws each mark on its spoken word as the camera follows; eight automated checks; Node + Chromium + ffmpeg on macOS/Windows/Linux.
- Tesseract by Mirage Skill
Mirage's (Captions) agent skills + native tsrct CLI for macOS/Windows/Linux: agents build one editable .tsrct project mixing footage edits, motion graphics, sound, designs and 3D scenes (Blender/glTF import, PBR, keyframed cameras, GPU path tracing), with critic review passes; partial Premiere/After Effects round-trip. Free local engine per Mirage; proprietary terms.
- cangshu koubo video skills Skill
QQTangBa's Apache-2.0 pair of Claude Code skills for Chinese talking-head edits on Apple silicon: cut flubs/retakes/pauses with optical-flow cut smoothing, breathing zoom, keyword captions, 9:16 render with lip-sync drift check; motion version alternates speaker with hand-written Remotion scenes in 3:4. Local mlx-whisper; Chinese docs.
- raea Repo
shinyobjectz's Render Anything Engine: video, motion graphics, 3D and games written as React + TypeScript (Remotion-style compositions) and drawn on your own GPU by a Rust/Bevy engine, no browser; single-frame PNG renders for agent review, 'raea check' QC (clipped text, contrast, safe areas, freezes, loudness), Claude Code skills + plugin, desktop app for Mac/Windows/Linux. Young (v0.1.x); FSL-1.1-ALv2 source-available licence.
- HyperFrames reverse-any-video Skill
HeyGen HyperFrames skill that rebuilds an existing video as an editable HTML project (cuts measured to the frame, components rebuilt, people re-shot with HeyGen) and diffs the render against the original. Pro feature; use only on footage you have rights to.
- Screenplay (agent-screenplay) MCP
MIT MCP server + CLI by gmpetrov: your agent explores a site or desktop app, writes a scenario, and Screenplay films it Screen Studio-style (smooth cursor, auto zooms, callouts, captions, optional voice-over) to MP4. No model key needed.
- MOTNGRFX ComfyUI
Apache-2.0 ComfyUI node pack + browser app by okkazoo: open-weights kinetic-type motion graphics where Gemma 4 plans, LTX 2.5 shoots with subject mattes so type passes in front of and behind the subject, and ACE-Step scores; 12/16/24 GB graphs.
- Papermorph Skill
MIT Claude Code/OpenCode skill by DozenTwelve that turns textbook PDFs into narrated animated web lessons, stories into paper-puppet films and books into documentaries plus vertical shorts; SVG engine, free Edge TTS or Kokoro narration, optional paid voices and images.
- Claude Animated Shorts Skill
MIT Claude skill by mromidev that turns a topic into a 55-70 s vertical cartoon story short (2D characters in a painted 3D town) rendered with three.js in Remotion, with synthesized music, SFX and frame QA; no video model.
- video-editor-skills Skill
12 Claude Code skills for a first-pass edit in DaVinci Resolve Studio: cut retakes and dead air, B-roll, voice cleanup, music ducking, captions, Remotion overlays timed to your words, YouTube export. Needs Resolve Studio, ffmpeg and a word-timestamp STT API; raw footage untouched. CC BY-NC 4.0 (no commercial use).
- rossark-motion-skill Skill
MIT agent skill for animating SVG characters, creatures, logos, icons and scenes at 60 fps the way animators do: one scene clock, real pivots, follow-through, idle motion. Motion engine and live-face templates for React Native and SwiftUI, plus contact-sheet and motion-tracking tools.
- YouTube AI Motion Graphics Repo
Sirio's (TEIN AI) library of 74 HTML/GSAP explainer boards (diagrams, charts, workflows) for YouTube videos, synced to Whisper word-level timings and exported frame-exact to MP4 with Chrome and FFmpeg, plus every prompt from the build and three Claude skills (board brief, board system, board sync).
- OpenKatana ComfyUI
Apache-2.0 agent-driven editing engine (Studio, ComfyUI apps, CLI and MCP): photos, footage and music in, a finished edit with cuts, transitions, motion type and music out. On the Comfy Registry; standard editing needs no dedicated GPU, per the FAQ.
- claude-video-effects Skill
Vibha's Claude Code skill with 45 face-tracked talking-head effects called by name (/effects orbit from 3 to 6 seconds): reels orbiting your head, backdrop words, receipts, tier lists, iMessage pop-ins, magazine cover, profile-grid reveal. YuNet + MediaPipe keep graphics behind your head; renders 1080p next to the original, audio untouched. Starter looks, no captions or sound. MIT.
- design-to-motion (ai-design-skills) Skill
Elaya's MIT agent skill (Claude Code, Cursor, Codex): rebuilds a Figma frame or screenshot pixel-exact in HTML, then every visual acts out a looping story (lists receive items, charts get scrubbed, prompts retype). Deterministic Playwright fake-clock capture to an MP4 for X plus 960px and 800x500 GIFs, or a scroll-triggered website mode. Repo #1 on GitHub trending Oct 27; the skill is moving to its own repo (elayadesign/Design-to-motion, not public yet). Companion: landing-page-design.
- SenseNova 6.8 Code2Video Repo
Apache-2.0 27B open model (Qwen3.8-27B fine-tune, 512K context) for code-written video: motion graphics, explainers, stylized 2D/3D, procedural audio. Ships a code-video skill for Claude Code-style harnesses, prompt enhancement and trajectories; serve via vLLM/SGLang/LightLLM. README says it trails top proprietary models and runs take hours.
- OpenFilm Skill
MIT open-source video agent: your coding agent writes a film.html where each shot is a web page drawn by frame(t) (three.js, canvas, SVG, GSAP, video), then you edit by hand in a local browser Studio with a timeline. npx skills add openfilm/openfilm, or desktop app for macOS/Windows; bring your own keys for voice, music and generation.
- motion2code Skill
Rebuilds an AI-generated motion-design clip (or fake app screen recording) as one self-contained HTML page: inline SVG on a single seekable GSAP timeline, seamless loop, vector-sharp at any size. Scripts study the video (frames, cuts, palette), frame-diff source vs code, check the loop seam and render frame-exact MP4/GIF. Claude Code plugin or npx skills add; Python 3.9+, ffmpeg, Playwright. MIT.
- EffectCraft Repo
ArtCraft's open-source After Effects-style compositor in pure Rust: compositions, layers, keyframes, 300+ effects, expressions, 3D cameras/lights, Lottie import/export, render queue. Versioned JSON projects (.ecproj); every action reachable from a CLI, JSON control channel or MCP server. No FFmpeg. Alpha (team says not for client work yet). Apache-2.0.
- ffmpeg-skill Skill
Local video editor for coding agents: 42 FFmpeg/ffprobe tools (cut, join, silence and filler removal, captions/karaoke, reframe, loudness, multicam sync, HDR→SDR, platform exports) with a probe → edit → verify workflow and an MCP server (12 core tools listed by default). `npx ffmpeg-skill` for Claude Code, --cursor / --codex. No cloud or API keys. MIT.
- huashu-motion Skill
Launch films by your coding agent: three directions, a rhythm sheet, one-file HTML/GSAP film, a score in ABC notation played by sampled instruments, SFX on the beats, and a browser studio where you click the frame to request a precise fix. MP4/MOV-alpha/WebM/GIF. Node 22+, Chrome, FFmpeg; macOS-tested. MIT.
- BaoCut MCP
Desktop AI video agent (macOS Apple Silicon, Windows) with an editable timeline: local transcription, subtitles, translation, dubbing with vocal separation, filler/retake cuts, HTML motion graphics (baocut/1 and hyperframes/1). Drive it from Claude Code/Codex via skill, MCP or CLI. Source-available Community License (content use free; commercializing the software needs a licence).
- lemo-opuscar Skill
Lemomo's Claude Code plugin: 51 film styles (style prompt + demo film each), all picture, score and TTS narration made in code; tuned for Opus 5.5. MIT.
- mg-styles-15 Repo
15 ten-second motion-design styles with full prompts, source, a renderAt(t) + headless Chrome + ffmpeg harness, code-synthesised audio and a second-AI review rubric. MIT.
- ClaudeAnimationBase Repo
p5.js + p5.brush starter for hand-painted cartoons: Clawd character with 31 emotions, an animation guide, contact-sheet self-checks, MP4 renderer. MIT.
- awesome-opus5-5-videos Repo
Gallery of ~700 Opus 5.5 code-video prompts linked to each creator's original post. MIT.
- claude-motion-explainer Skill
One sentence to a narrated explainer animation on HyperFrames: research, storyboard, TTS, one sub-agent per scene in parallel, captions, three-colour theme, contact-sheet self-review; includes 26 lessons and a fix_voice.py for mispronounced words. Traditional Chinese. MIT.
- whiteboard-teacher-video Skill
Turns a lecture script into a hand-drawn whiteboard explainer: rough.js strokes drawn in code, text written on as it is spoken, five styles, local Chrome render, edge-tts voice, no image-API cost; re-renders only changed segments. Chinese docs; licence not stated.
- motion-prompt Skill
Clickable dictionary of 144 named motion, camera, UI, web and photo-look effects, each with a moving sample and an example ask. Pick in the browser gallery, Send to AI, and the agent builds your picks. Works for video-model prompts too. MIT.
- free247editor Skill
Drop a raw talking-head video in the inbox, say 'edit this': cuts, word-by-word captions, HyperFrames + GSAP motion cards, zooms and sound. Plain-word notes become rules in my-rules.md so later edits follow your style. MIT.
- papercut-explainer Skill
Nine Agent Skills + a Remotion library for vertical cut-paper explainer reels: paper-cut kit, 24 backdrops, 17 camera moves, 10 transitions, 79 SFX and 8 music beds; strategy → script → storyboard → voice → build → QA. MIT.
- OpenDesign Motion Repo
OSS Claude Motion alternative (codename OpenDesign Motion): idea → editable source + MP4; five bundled examples; Desktop free, Cloud paid. Apache-2.0. Site: open-design.ai.
- ASCII Glitch Launch Video Skill
Skillry membership skill: 18s 60fps glitch hype; editable browser film + MP4. Node 20+, FFmpeg, Playwright. v1.0.1.
- Paper Cutout Story Video Skill
Skillry membership skill: 35–50s clay/felt storybook explainer. Editable browser film + MP4. v1.0.0.
- claude-motion Skill
Taste rules with numbers, contact-sheet self-review, Python sound engine, web sims → 60 fps.
- heditor Skill
Talking head → styled 9:16 Reel on HyperFrames: named styles, word-timed cut, voice-first mix, vision QA. MIT.
- anything2explainer Skill
Topic → sourced, narrated Remotion explainer via parallel build + QC agents. Non-commercial licence.
- animate Skill
Canvas + Playwright + FFmpeg animation in 7 styles; storyboard gates; Whisper word timing.
- product-launch-motion Skill
Launch videos from code: GSAP, word-locked VO, camera moves, film grade, loudness.
- motion-graphics-skills Skill
13 skills for launches, animated charts and reels.
- claude-motion-design Skill
HTML + Playwright + ffmpeg motion design; cuts on the beat.
- Barty-Bart motion-graphics Skill
Motion B-roll timed to your words over your own footage.
- claude-remotion-skill Skill
Remotion skill targeting flat fades and stiff motion.
- gsap-skills Skill
Official GSAP skills; the engine under many launch kits.
- LottieFiles motion-design-skill Skill
Timing, easing, choreography and Disney's 12 principles for agents.
- motion-dev-animations-skill Skill
Motion.dev web animation skill (springs, scroll, gestures).
- Skillry Skill
400+ in-house designed skills (video, slides, web, image); free + paid tiers.