Agent Skills

manim-composer

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. Transforms vague video ideas into detailed scene-by-scene plans (scenes.md). Conducts research, asks clarifying questions about audience/scope/focus, and outputs comprehensive scene specifi

Install

npx skills add https://github.com/calesthio/openmontage --skill manim-composer
SKILL.md

Workflow

Phase 1: Understand the Concept

  1. 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
  2. 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

References

Templates

Related skills

video-editgenmedia-labs715KEdit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets shai-video-generationgenmedia-labs714KGenerate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 qualitai-musicgenmedia-labs714KGenerate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model fimage-to-videogenmedia-labs713KAnimate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterat

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers