/ Directorio / Playground / manim-skill
← Todos los servidores ↗ GitHub
● Comunidad Yusuke710 ⚡ Instantáneo

manim-skill

por Yusuke710 · Yusuke710/manim-skill

Claude autonomously plans, writes, renders, and refines Manim animations — go from 'explain this concept' to a video file without touching Python.

A skill that runs the full Manim loop inside Claude Code. You describe a concept; Claude drafts scene code, invokes manim to render, inspects the result, and iterates until it matches your intent. Built for 3Blue1Brown-style math/CS explanations.

▶ Ver demo 📦 Instalar 💡 Casos de uso

Por qué usarlo

Características clave

Demo en vivo

Cómo se ve en la práctica

manim-skill.replay ▶ listo
0/0

Instalación

Repositorio del autor · Documentación oficial de Skills de Claude

Casos de uso

Usos del mundo real: manim-skill

Animate the intuition behind a math or CS concept

👤 Educators, YouTubers, students explaining to themselves ⏱ ~45 min intermediate

Cuándo usarlo: A concept is easier with motion than with words (gradient descent, sorting, Fourier).

Flujo
  1. State the concept
    Use manim-skill. Animate gradient descent on a 2D loss surface — ball rolling, learning rate visibly affects step size.✓ Copiado
    → Scene plan + code + low-q preview rendered
  2. Iterate
    Slower at first, faster once it's in the valley. Label the axes.✓ Copiado
    → Code updated, re-rendered preview
  3. Final render
    Looks good — render at 1080p60.✓ Copiado
    → High-q mp4 produced

Resultado: An explainer video you can embed in a blog post.

Errores comunes
  • Manim code has breaking changes across versions — Pin your manim version in requirements; the skill's prompts assume recent Community Edition
Combinar con: filesystem

Build a series of scenes for a longer explainer

👤 Video creators working on a single concept over multiple shots ⏱ ~180 min advanced

Cuándo usarlo: You have a 5-minute script and need 10+ scenes to go with it.

Flujo
  1. Feed the script
    Use manim-skill. Here's my script. Break into scene beats and propose a Manim scene per beat.✓ Copiado
    → Ordered scene plan
  2. Render in batches
    Render scenes 1-3 at preview quality; show me.✓ Copiado
    → Three low-q mp4s
  3. Consolidate
    Ok, lock scenes 1-3. Move to 4-6.✓ Copiado
    → Work proceeds; locked scenes untouched

Resultado: A full scene library ready for final render.

Errores comunes
  • Rendering high-q for every iteration wastes time — Iterate at -ql (low) and only go -qh once locked

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

manim-skill + filesystem

Organize a project's scenes, renders, and drafts

Keep scenes in project/scenes/, renders in project/renders/preview or /final.✓ Copiado

Herramientas

Lo que expone este MCP

HerramientaEntradasCuándo llamarCoste
plan_scenes concept or script First step on any new project 0
write_scene scene spec Per-scene code generation 0
render_manim scene file, quality Preview and final renders local CPU/GPU
refine_scene scene + feedback Iterating on animation 0

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API
None
Tokens por llamada
Moderate — code iterations
Monetario
Free; local compute only
Consejo
Always iterate at low quality. Final render once.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: None
Salida de datos: None from skill

Resolución de problemas

Errores comunes y soluciones

manim import errors

Manim CE vs GL — make sure you're on Community (pip install manim), not the legacy 3b1b version

Verificar: python -c 'import manim; print(manim.__version__)'
Render hangs or is very slow

Use -ql for iteration; -qh only at end. Check ffmpeg presence.

Verificar: ffmpeg -version
Weird layout — objects overlap

Use positioning primitives (next_to, align_to) rather than raw coords

Alternativas

manim-skill vs otros

AlternativaCuándo usarlaContrapartida
After Effects / Motion CanvasYou want visual timeline toolsNot code; not LLM-friendly
paperbanana-skillStatic academic diagrams rather than animationsDifferent output

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills