manim-composer
Skill33 starsChanged 6 months agoMITView on GitHub
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization.
We split this skill into the rules it gives an agent
5 rules. 5 are common, 0 are distinctive, and 0 are very specific to this project.
5
Common
Most of the 5 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 16
Use web search to understand the core concepts
- Common: line 28
Ask targeted questions (not all at once - adapt based on responses):
- Common: line 33
Should this be self-contained or part of a series?
- Common: line 111
Show, don't just tell: - Every concept needs a visual representation
- Common: line 123
Embrace abstraction gradually: - Start concrete, then generalize
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Workflow
Phase 1: Understand the Concept
- Research the topic deeply before asking questions
- Use web search to understand the core concepts
- Identify the key insights that make this topic interesting
- Find the "aha moment" - what makes this click for learners
- Note common misconceptions to address
- Identify the narrative hook
- What question does this video answer?
- Why should the viewer care?
- What's the surprising or counterintuitive element?
Phase 2: Clarify with User
Ask targeted questions (not all at once - adapt based on responses):
Audience & Scope
- What math/science background should I assume? (e.g., "knows calculus" or "high school algebra")
- Target video length? (short: 5-10min, medium: 15-20min, long: 30min+)
- Should this be self-contained or part of a series?
Focus & Depth
- Any specific aspects to emphasize or skip?
- Proof-heavy or intuition-focused?
- Real-world applications to include?
Style Preferences
- Color scheme preferences?
- Narration style? (casual, formal, playful)
- Any specific visual metaphors you have in mind?
Phase 3: Create scenes.md
Output a comprehensive scenes.md file with this structure:
# [Video Title]
## Overview
- **Topic**: [Core concept]
- **Hook**: [Opening question/mystery]
- **Target Audience**: [Prerequisites]
- **Estimated Length**: [X minutes]
- **Key Insight**: [The "aha moment"]
## Narrative Arc
[2-3 sentences describing the journey from confusion to understanding]
---
## Scene 1: [Scene Name]
**Duration**: ~X seconds
**Purpose**: [What this scene accomplishes]
### Visual Elements
- [List of mobjects needed]
- [Animations to use]
- [Camera movements]
### Content
[Detailed description of what happens, what's shown, what's explained]
### Narration Notes
[Key points to convey, tone, pacing notes]
### Technical Notes
- [Specific Manim classes/methods to use]
- [Any tricky implementations to note]
---
## Scene 2: [Scene Name]
...
---
## Transitions & Flow
[Notes on how scenes connect, recurring visual motifs]
## Color Palette
- Primary: [color] - used for [purpose]
- Secondary: [color] - used for [purpose]
- Accent: [color] - used for [purpose]
- Background: [color]
## Mathematical Content
[List of equations, formulas, or mathematical objects that need to be rendered]
## Implementation Order
[Suggested order for implementing scenes, noting dependencies]3b1b Style Principles
Apply these principles when composing scenes:
Visual Storytelling
- Show, don't just tell - Every concept needs a visual representation
- Progressive revelation - Build complexity gradually, don't show everything at once
- Visual continuity - Transform objects rather than replacing them when possible
Pacing & Rhythm
- Pause for insight - Give viewers time to absorb key moments
- Vary the pace - Mix quick sequences with slower explanations
- End scenes with resolution - Each scene should feel complete
Mathematical Beauty
- Emphasize elegance - Highlight when math is surprisingly simple or beautiful
- Connect representations - Show the same concept multiple ways (algebraic, geometric, intuitive)
- Embrace abstraction gradually - Start concrete, then generalize
Engagement Techniques
- Pose questions - Make viewers curious before revealing answers
- Acknowledge difficulty - "This might seem confusing at first..."
- Celebrate insight - Make the "aha moment" feel earned
Anti-Patterns
- Writing Manim code before the scene plan exists — compose first (this skill), then hand off to
manimce-best-practicesormanimgl-best-practicesfor implementation. - Mixing ManimCE and ManimGL APIs in one plan — pick one engine per video and say which in the plan.
- Explaining with text walls instead of motion — every scene needs a visual transformation, not a slide.
- Not closing the loop — run
mktg run manim-composer --complete --writes <plan path> --result success --jsonwhen the plan is written.
References
- references/narrative-patterns.md - Common 3b1b narrative structures
- references/visual-techniques.md - Effective visualization patterns
- references/scene-examples.md - Example scenes.md excerpts
Templates
- templates/scenes-template.md - Blank scenes.md template
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 5
- calesthio/OpenMontage★ 74k99% same
- adithya-s-k/manim_skill★ 1.1k99% same
- LinHao-city/StoryMind★ 1099% same
- Littlpinguin/marketing-cockpit-template★ 872% same
- Gopyr/gopyr-skills-hub★ 084% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository79 other files it gives its agents.
- AGENTS.mdAGENTS.md
- studio/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- studio/CLAUDE.mdCLAUDE.md
- agent-email-inboxSkill
- ai-seoSkill
- app-store-screenshotsSkill
- audience-researchSkill
- axiSkill
- brainstormSkill
- brand-kit-playgroundSkill
- brand-voiceSkill
- build-with-exaSkill
- churn-preventionSkill
- cmo-remotionSkill
- cmoSkill
- company-researchSkill
- competitive-intelSkill
- competitor-alternativesSkill
- content-atomizerSkill
- conversion-flow-croSkill
- create-skillSkill
- creativeSkill
- deepen-planSkill
- direct-response-copySkill
- document-reviewSkill
- email-sequencesSkill
- exa-contentsSkill
- exa-searchSkill
- firecrawlSkill
- free-tool-strategySkill
- frontend-slidesSkill
- higgsfield-generateSkill
- higgsfield-product-photoshootSkill
- higgsfield-soul-idSkill
- image-genSkill
- keyword-researchSkill
- landscape-scanSkill
- launch-strategySkill
- lead-generationSkill
- lead-magnetSkill
- manimce-best-practicesSkill
- manimgl-best-practicesSkill
- marketing-demoSkill
- marketing-psychologySkill
- mktg-setupSkill
- mktg-xSkill
- newsletterSkill
- off-page-seoSkill
- openseo-coachSkill
- openseo-competitive-landscapeSkill
- openseo-competitor-analysisSkill
- openseo-keyword-clusteringSkill
- openseo-keyword-researchSkill
- openseo-link-prospectingSkill
- openseo-project-setupSkill
- openseoSkill
- page-croSkill
- paper-marketingSkill
- positioning-anglesSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

