manim-explainer-animation
Provider-independent production workflow for creating Manim-based explainer animations. Use when an agent must plan, code, render, QA, or hand off precise math, science, data, diagram, algorithm, or concept animations with Manim, including storyboard, scene architecture, formulas, coordinate systems, voiceover timing, accessibility, reproducibility, provenance, and delivery decisions.
Profile →npx skills add calesthio/generative-media-skills --skill manim-explainer-animation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
This skill guides an agent to produce explainer animations using Manim as a programmable explanation tool, covering planning, coding, rendering, QA, and handoff for precise math, science, data, diagrams, algorithms, or concepts. It emphasizes storyboard creation, scene architecture, formulas, coordinate systems, voiceover timing, accessibility, provenance, and delivery decisions. It instructs the agent to start with a production brief and a concept breakdown before building storyboard beats and a detailed scene architecture, including code structure, constants, and helper functions. It also prescribes methods for coordinate systems, typography, and symbol continuity, and outlines how to handle voiceover timing, accessibility, provenance, and asset custody. The workflow includes a project skeleton, a theme pattern for formulas, and detailed guidance on coordinates, layout, and animation sequencing. It also dictates escalation when medical, legal, financial, safety, or educational correctness matters beyond style.
How it works
- Begin with a production brief covering audience, objective, core facts, runtime, aspect ratio, narration style, delivery platform, and constraints.
- Build a concept breakdown detailing Objects, Symbols, Actions, Cognitive load, and Verification.
- Create a storyboard with fields: time, narration, visual_state, animation, learning_purpose, assets_or_data, qa_checks.
- Develop scene architecture guidelines: one class per chapter, named constants for palette and dimensions, helper functions, a symbol ledger, and explicit coordinate handling using axes and c2p/coords_to_point helpers.
- Apply typography and formulas rules: use Text for labels, MathTex/Tex for math, and a symbol ledger for color and meaning. Ensure accessibility by narrating formulas.
- For graphs, diagrams, and algorithms, follow movement, labeling, and stepwise transformations with a focus on continuity and pedagogy.
- Employ voiceover timing approaches via a dedicated plugin path (Code-led with voiceover plugin) and align visuals to narration; export final captions from the timed script.
- Maintain accessibility and safety: provide captions, transcripts, and checks for color contrast and motion sensitivity.
- Track asset provenance, conform to C2PA when required, and store all inputs and outputs in the handoff bundle.
- Render settings: render fast previews first, then full renders, noting that Manim renders scene classes from files into a media directory and can leverage PyAV/FFmpeg considerations.
When to use it
Use when the deliverable requires precise mathematical or diagrammatic motion with repeatable and revisable animations, where render-in-the-loop iteration and provenance are important, and when a structured production flow from brief to handoff is desired. Escalate if medical, legal, financial, safety, or highly claim-specific correctness matters beyond style.
What it can touch
- Tools: claude-code, codex, copilot, cursor.
- It prescribes creating production artifacts: a concept brief, storyboard beats, scene skeletons, and a project skeleton with directories like scenes/assets/renders and a theme module for colors and typography.
- It references using Manim concepts such as
Scene,construct(),Scene.play(),Axes,NumberPlane,MathTex,Tex,Text, and aVoiceoverScenewithRecorderServicefor timing alignment.
Caveats
- Escalation rules apply for claims with high stakes (medical/legal/financial/educational correctness).
- It emphasizes provenance and C2PA, noting that provenance data is not a truth value judgment.
- It requires careful management of accessibility, captions, and motion sensitivity without overpromising final delivery outcomes.
# Manim Explainer Animation Use this skill to produce explainer animations where the explanation depends on precise symbolic, geometric, graphical, algorithmic, or diagrammatic motion. Treat Manim as a programmable explanation instrument, not as a generic video renderer. ## Evidence labels - **Documented fact** means behavior or requirements grounded in official documentation or standards listed i
What does the manim-explainer-animation skill do?
Provider-independent production workflow for creating Manim-based explainer animations. Use when an agent must plan, code, render, QA, or hand off precise math, science, data, diagram, algorithm, or concept animations with Manim, including storyboard, scene architecture, formulas, coordinate systems, voiceover timing, accessibility, reproducibility, provenance, and delivery decisions.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill manim-explainer-animation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.