AI · GitHub repo
manim_skill
AI agent skills and rules for generating Manim math animations
manim_skill provides structured rules, best practices, and code examples for both Manim Community Edition and ManimGL. Installed via skills.sh, it gives AI coding assistants the context needed to write accurate 3Blue1Brown-style mathematical animations from prompts without hallucinating framework-specific syntax.
What it's for
- Equip AI agents like Claude Code or Cursor to write valid Manim scripts
- Generate visual explainer animations for math and machine learning concepts via natural language prompts
- Reference tested patterns and API differences between ManimCE and ManimGL
Features
- Supports both Manim Community Edition (ManimCE) and Grant Sanderson's ManimGL
- Modular rules covering animations, scene structure, mobjects, 3D rendering, and camera movement
- One-command installation into AI coding tools using the skills.sh CLI (`npx skills add`)
- Tested working code examples and automated test suites to verify syntax across versions
- Comprehensive comparison guides outlining class, import, and CLI differences between both frameworks
Pricing
Open source
Details
- Type
- GitHub repo
- Category
- AI
- Topic
- Agent Skills
- Open source
- Yes
- Platforms
- Command line, Code library, macOS, Linux, Windows
- For
- Developers, educators, and researchers using AI coding tools to produce mathematical video animations.
- Tags
- manim, agents, claude, animation, python, skills
Why it was saved
- @adithya_s_k: Lets the user generate explainer animations (e.g. multi-head attention visualizations) without hand-writing Manim code.
Related
Prompt template for generating bounded Manim animation code with Claude
Directory and consulting hub for AI tools, skills, and automations
A Python multi-agent pattern pairing Opus orchestration with Haiku worker instances.
Open-source platform and framework for building autonomous AI agents
Open-source Python library enabling AI agents to control web browsers.
Folder structure as agent architecture for multi-stage AI workflows
Updated