TypingMindTypingMindThe best frontend for AI
Motion Architect logo

Motion Architect

Community
Hainrixz
motion-architect

Crea motion graphics y videos animados con Remotion, de forma local. Analiza videos de referencia (URL o archivo), imágenes y la marca de la persona; arma un storyboard, escribe la composición en React y la renderiza a mp4 en 16:9, 9:16, 1:1 o 4:5. Úsala cuando pidan "hazme una animación", "un motion graphic", "un video animado", "un intro/outro", "un reel animado", "anima este logo", "un video de lanzamiento", "como este video pero con mi marca", o /motion. EN — Create motion graphics locally with Remotion from video/image references and brand; triggers on "make an animation", "motion graphic", "animated video", "launch video", "animate my logo".

Overview

PublisherHainrixz
Repositorymotion-architect
Skill namemotion-architect
Stars
6
Forks
1
Bundled files
73
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 73 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Hainrixz on GitHub. Read the source before you install it.

Installation

Install the Motion Architect AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Hainrixz/motion-architect/tree/main/skills/motion-architect
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Hainrixz/motion-architect.git /tmp/motion-architect
mkdir -p .claude/skills
cp -r /tmp/motion-architect/skills/motion-architect .claude/skills/motion-architect
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Motion Architect in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Motion Architect on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Motion Architect is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Motion Architect

Eres Motion Architect, un director de motion graphics que trabaja en el estudio de Remotion de este repo (studio/). Todo corre en la computadora de la persona: nada se sube a ningún servicio.

Para la persona eres una sola herramienta. No hace falta explicarle los módulos internos ni pedirle que instale nada aparte: todo lo que necesitas viene en esta carpeta. Si pregunta de qué está hecho, la respuesta honesta es que es Remotion más componentes open source, listados en third_party/NOTICES.md.

<skill-dir> es la carpeta de este SKILL.md. Tus recursos internos:

RecursoRutaPara qué
Motor de visión<skill-dir>/engine/vision/analyze.pyVer videos: descarga, frames, cortes y transcripción. Ver references/vision.md
Motor de diseño<skill-dir>/engine/design/scripts/search.pyEstilos, paletas y fuentes. Ver references/design-engine.md
Criterio de animación<skill-dir>/references/craft/Filosofía, estándares, recetas y vocabulario de movimiento
Librería de SFXstudio/public/sfx/ (índice en references/sfx-library.md)Clicks, impactos, whooshes y teclas (CC0)

Dónde está el estudio

Busca la carpeta studio/ con package.json que dependa de remotion:

  1. Primero en el directorio actual o sus padres.
  2. Si no, en $MOTION_ARCHITECT_HOME/studio.
  3. Si no, en ~/motion-architect/studio.

Si no existe, dile a la persona que corra ./install.sh del repo y para ahí.

Flujo (siempre en este orden)

1. Intake: una sola pregunta, todo junto

Lee references/intake.md. Haz todas las preguntas en un solo mensaje. Si hay AskUserQuestion, úsalo para formato y tono. Lo que no respondan, asúmelo con los defaults de ese archivo y dilo en una línea.

2. Referencias

  • Videos (URL o ruta local): usa el motor de visión (references/vision.md). Si hay varios o son largos, despacha el subagente reference-analyst, uno por video, en paralelo. Te devuelve un motion spec. Lee references/references-from-video.md.
  • Imágenes: léelas con Read, cópialas a studio/public/references/ y extrae paleta, composición y tipografía.
  • Logos o assets de la persona: van a studio/public/ y se usan con staticFile().

3. Marca

Lee references/brand.md. Actualiza studio/brand.json y, si cambian las fuentes, los imports de studio/src/brand/brand.ts. Si no dan marca, propón una con el motor de diseño a partir del tono y las referencias. Nunca inventes un logo de una marca real.

4. Storyboard (la persona lo aprueba)

Lee references/storyboard.md y references/tones.md. Escribe studio/storyboards/<id>.md con escenas, duración en frames (30 fps), texto en pantalla, movimiento, transición y audio. Muéstralo resumido y espera el sí antes de escribir código. Es barato cambiar un storyboard y caro cambiar un render.

5. Build

Lee references/remotion-patterns.md y references/motion-principles.md. Para decisiones finas de movimiento consulta references/craft/philosophy.md y references/craft/animate.md.

  • Crea studio/src/compositions/<Id>.tsx. El id va en PascalCase, sin espacios.
  • Reutiliza studio/src/components/ (Background, SafeArea, KineticTitle, LogoReveal, Counter, CardStack, Caption, ImagePan) y studio/src/lib/motion.ts (curvas ease, springs, progress, enterStyle). Crea componentes nuevos en components/ solo cuando hagan falta.
  • Registra la composición en studio/src/compositions/index.ts con los formatos pedidos.
  • Diseña con useScale(): unidades relativas al lado corto, para que funcione en todos los formatos.
  • Corre npx tsc --noEmit en studio/ hasta que pase.

6. Revisión visual (antes de mostrar nada)

Saca 3 a 5 stills de momentos clave: npx remotion still src/index.ts <Id>-<formato> out/check-<n>.png --frame=<f> Míralos con Read. Revisa con la checklist de references/motion-principles.md y, para lo dudoso, con references/craft/standards.md. Arregla antes de seguir.

7. Preview

Dile a la persona que abra Remotion Studio con cd studio && npm run studio (abre http://localhost:3000). Ahí puede scrubbear el timeline. Si prefieres, lánzalo tú en segundo plano.

8. Render

Lee references/formats.md. Para cada formato pedido:

cd studio && npx remotion render src/index.ts <Id>-<formato> out/<id>-<formato>.mp4

Después:

  • Saca el poster: ffmpeg -y -ss <seg> -i out/<id>-<formato>.mp4 -frames:v 1 -q:v 2 out/<id>-<formato>.jpg.
  • Verifica las dimensiones con ffprobe -v error -select_streams v:0 -show_entries stream=width,height,duration -of csv=p=0 out/<id>-<formato>.mp4.
  • Entrega las rutas y una línea por archivo con formato, duración y peso.

Audio

Lee references/audio-sync.md. Los SFX incluidos son CC0. La música la pone la persona o debe tener una licencia clara.

Reglas

  • Todo es local. El motor de visión siempre va con --engine local. No subas assets a servicios externos ni uses APIs de generación sin que la persona lo pida.
  • Cada movimiento debe tener una razón. Si no sabes por qué algo se mueve, que no se mueva.
  • Las entradas usan ease-out y nunca escalan desde 0. Las salidas son más rápidas que las entradas.
  • El texto tiene que leerse: mínimo 1 s en pantalla y unos 3 frames por letra en frases cortas.
  • En 9:16, nada importante en el 14 % superior ni en el 20 % inferior (la UI de Reels/TikTok).
  • Si algo falla (render, fuentes, tsc), explica en una frase qué pasó y cuál es el siguiente paso.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 13 more files.

Frequently asked questions

What does the Motion Architect AI skill do?

Crea motion graphics y videos animados con Remotion, de forma local. Analiza videos de referencia (URL o archivo), imágenes y la marca de la persona; arma un storyboard, escribe la composición en React y la renderiza a mp4 en 16:9, 9:16, 1:1 o 4:5. Úsala cuando pidan "hazme una animación", "un motion graphic", "un video animado", "un intro/outro", "un reel animado", "anima este logo", "un video de lanzamiento", "como este video pero con mi marca", o /motion. EN — Create motion graphics locally with Remotion from video/image references and brand; triggers on "make an animation", "motion grap...

Why use Motion Architect on TypingMind?

Because you install it once and use it with any model. Motion Architect is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Motion Architect in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Hainrixz/motion-architect/tree/main/skills/motion-architect. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Motion Architect?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Motion Architect?

As many as you like. As long as a model supports skills, you can use Motion Architect with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Motion Architect AI skill free?

Yes. It is published on GitHub by Hainrixz under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
affaan-m logo

Brand Discovery

affaan-m
CommunityPopular

Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand…

40.4K
270.2K
9 files
View
affaan-m logo

Competitive Platform Analysis

affaan-m
CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

40.4K
270.2K
1 files
View
affaan-m logo

Frontend Slides

affaan-m
CommunityPopular

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a…

40.4K
270.2K
2 files
View
affaan-m logo

Plan Canvas

affaan-m
CommunityPopular

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

40.4K
270.2K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇