⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
extreme-motion-design
Cria vídeos de motion design de nível de estúdio por código (Remotion/React), com trilha licenciada, SFX sincronizados, voz opcional (ElevenLabs ou modelo TTS local escolhido pelo hardware) e gates automáticos de lint e QA antes da entrega. Use quando pedirem motion design, motion graphics, vídeo animado, explainer, vídeo de produto ou lançamento, reel ou TikTok animado, tipografia cinética, logo animado, animação de UI, loop, narração ou voiceover para vídeo, ou técnicas como keyframing, zoom in e zoom out, motion smooth, morphing, rigging, frame a frame, cel animation, stop motion, rotoscopia, motion tracking, match moving, compositing, motion 3D, speed ramp, match cut, overshoot, parallax e transições. Also for animated video, kinetic typography, product launch video, explainer with voiceover, text to speech narration.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
// README
Extreme Motion Design
A motion design skill for coding agents (Claude, Claude Code, Codex and anything that reads SKILL.md). The agent writes the video as code with Remotion and React, with voice, licensed music and synced sound effects, and it is not allowed to deliver until the frames have been measured.
The film above is the 2.0 presentation, made with the skill. Every number on screen was measured and the imagery is public domain or CC0 (NASA, USGS, NPS and The Met), fetched by the skill with the licence checked per file.
What is new in 2.0
- Reference mode. Hand it a video and
reference.pybreaks it into measured structure (shots, camera moves, palette, where the visual mass sits, audio), writes a script skeleton with the same timings, and scores the new piece from 0 to 100 against the reference. Calibration: the piece against itself scores 100, using the score boundaries as cuts 86, a reel made from the same request without the reference 38, unrelated videos 23 and 24. It copies structure, rhythm and technique. It never copies frames, assets, text or sound. - A design meter.
design.pycounts the signals of the frame a model produces with no direction: near black with one accent, a giant condensed face on the left margin, decorative mono, everything in caps, the same composition in every scene. It flagged my own 1.3 reel (4 signals) and the template example (3). The 2.0 film scores 0. - A design reference.
references/design.mdcovers composition, type, colour, texture, real imagery and launch film structure, each rule with its source, plus six named art directions to propose from. - Real imagery with the licence checked.
stock.pyfetches photo and video from Wikimedia Commons (CC0 and public domain only), NASA, Openverse and The Met, and records the evidence read from the API for every file. - Face and hand tracking in
track.py, for graphics pinned to a body.
Why it exists
An agent writing video code cannot see what it renders. Left alone it ships text cut by the frame edge, captions over a face, the same card sliding into every scene, and audio that clips. I built the skill around that blind spot:
- The audio is the clock. One
roteiro.jsonproduces the voice phrase by phrase, the score and the named cues. No scene holds a hand typed frame number. - The direction is a contract. Before any scene exists the piece declares its concept, its visual law, its motif and the layout and entrance of every scene. The lint rejects a project without it, and rejects one where every scene is laid out the same way.
- The text is measured, not eyeballed. A probe reads every text box from the DOM of each still and the background from the pixels. Cut off, overlapping, too small, low contrast or outside the safe area fails.
- Someone else reviews. The contact sheet goes to a reviewer with a clean context that never saw the code.
- The final file passes a numeric gate. Codec, loudness, true peak, flashes per second, one frame pops, loop seam, contrast against the stills.
What the gates caught while making this reel and a second one built on phone footage
These are real lines from the session, not examples I wrote for the README.
| Gate | What it said | What was wrong |
|---|---|---|
layout.py | "renderizando 90%" x "milho": dois textos sobrepostos | A label sat on top of the captions |
layout.py | letra de 9 px: mínimo legível é 20 px neste formato | A chip was captured while scaling in from zero |
layout.py | "Extreme": texto cortado pela borda do quadro | A 300 px headline ran off the right edge |
layout.py | "Cor,": contraste 2.9:1 (texto #ff4b1f sobre #f3eee5) | Orange type on cream paper |
qa.py | true peak: -0.1 dBTP (máx -1.0) | AAC encoding raised the peaks of a boosted voice |
qa.py | flashes por segundo <= 3: pior janela: 4 | A five colour burst flickered |
| reviewer | "FAIL turns into PASS with the same measured value" | The checklist scene contradicted itself |
| reviewer | "EDIÇAO is missing its tilde" | The reveal mask clipped accents in a condensed font |
Every one of them was fixed before delivery, and four of them became fixes in the skill itself.
The same request without the skill
I ran the same request through the same model with the skill forbidden, plain Remotion only, and no paid voice. It is the honest comparison, so here it is with what I measured.
| Without the skill | With the skill | |
|---|---|---|
| Time to a file | about 8 minutes, 1 render | several times longer, 1 full render plus 1 scene patch |
| Look | strong, and close to the one on the right | strong |
| Voice | none | narration with real word timings, and the cuts follow it |
| Music | a raw ffmpeg synth the agent itself called the weakest point | a CC BY track with the credit recorded, ducked under the voice |
| Loudness | -12.5 LUFS, fails the -14 target | -14, true peak under -1 dBTP |
| Colour tag | none | BT.709 |
| Text and safe area | a headline cut by the right edge mid scene, the frame readout at y 118 under the app interface | measured on every still, 0 failures at delivery |
| Numbers on screen | "frame 105" in the checklist is invented | the counter shows the real frame and the checklist shows real measurements |
| Independent review | none | 16 of 21 frames sent back as FIX; the real defects were fixed, the ones that were mid transition were not |
What I take from it: a good model already makes a good looking frame without help. The skill does not buy taste. It buys sound, a clock, measured text, true numbers and a second pair of eyes, and it costs time.
Gallery
| Prompt | Notes | |
|---|---|---|
| "Something in every dimension and style, alternating between the real world and not, editing worthy of cinema, modern typography, an animated voice." | ElevenLabs voice (eleven_v4), 11 scenes, 68 s, public domain and CC0 imagery, design.py verdict: own direction, 0 signals. The music was composed with ElevenLabs Music by a script outside the skill, since music.py does not support it. 4 full renders and 1 scene patch | |
| "A very extravagant 9:16 reel, about 25 s, presenting the skill as a manifesto: this is not editing, it is code." | ElevenLabs voice, cuts on the beat of a CC BY track, 3D scene, real frame counter. Source. 1 full render and 1 scene patch | |
| "Present the skill itself in 90 s, technique by technique." | Made with version 1.1, 11 scenes | |
| none | The example that ships in the template, generated by score.py with the local voice |
Install
Claude Code (plugin)
/plugin marketplace add dev-isaacmello/extreme-motion-design
/plugin install extreme-motion-design@extreme-motion-design
Claude Code, Codex, Cursor and others (skills CLI)
npx skills add dev-isaacmello/extreme-motion-design
Claude (claude.ai and the desktop app)
git clone https://github.com/dev-isaacmello/extreme-motion-design
cd extreme-motion-design/skills
zip -r extreme-motion-design.zip extreme-motion-design/
Upload the zip in Customize > Skills. The zip must have the extreme-motion-design/ folder at the top.
Updating
- Plugin: `claude plugin update extre
// HOW IT'S BUILT
KEY FILES