@Gorden_Sun: Open-sourcing another skill: One-click generation of visual math explanation videos. Prompt: Install this Skill: https://github.com/GordenSun/mathVideoMaker… Then use this Skill to explain to elementary school students: Explain □+28=□x5 to elementary school students. Below are 2…

X AI KOLs Timeline Tools

Summary

Gorden_Sun open-sourced the mathVideoMaker skill, which can generate visual math explanation videos and interactive webpages with one click in Cursor Agent. It supports scenarios like explaining math problems to elementary school students, and includes an auto-check mechanism to ensure quality.

Another open-sourced skill: One-click generation of visual math explanation videos Prompt: Install this Skill: https://t.co/otI2ZDfdlf Then use this Skill to explain to elementary school students: Explain □+28=□x5 to elementary school students Below are 2 videos I generated. https://t.co/wffOzXxrMb
Original Article
View Cached Full Text

Cached at: 06/03/26, 03:41 AM

Another open-source skill: one-click generation of visualized math explanation videos

Prompt: Install this Skill: https://t.co/otI2ZDfdlf Then use this Skill to explain to elementary school students: □+28=□×5

The two videos below are the results I generated. https://t.co/wffOzXxrMb


GordenSun/mathVideoMaker

Source: https://github.com/GordenSun/mathVideoMaker

mathVideoMaker

A Cursor Agent Skill: simultaneously generates a “math explanation video” (rendered as MP4 via Manim) and an “interactive webpage” (self-contained HTML), with carefully polished implementation details to ensure even weaker models, or those without visual capabilities, can produce accurate, engaging content consistently.

Reference implementation: ManimCommunity/manim (https://github.com/ManimCommunity/manim) (based on Manim Community v0.20+).

What it can do

  • Explanation video: Uses Manim to animate the derivation process of a math/physics concept, rendered to MP4.
  • Interactive webpage: A self-contained single-file HTML (KaTeX formulas + canvas interaction) that lets the audience drag parameters and see changes in real-time.
  • Both share the same design (concepts, notation, parameters, colors), complementing each other: the video explains, the webpage lets you explore.

Design highlights (why this Skill is different)

  • Explains “why”: Forces demonstration of derivation/proof, not just the conclusion (includes a self-check of “can you understand even with the narration covered”).
  • Quality assurance without vision: Replaces “look at the picture and find errors” with text-based checks:
    • SafeScene automatically prints [layout] warnings during rendering (out-of-bounds/overlap);
    • check_text.py statically checks for missing glyphs (prevents empty boxes □);
    • check_web.py statically checks the webpage (formulas/ids/sliders/canvas/layout/JS syntax).
  • Mechanized layout + liveliness: Safe zone + fit_content to prevent clipping; dark color theme + glow + emphasis animations; subtitles with background.

Demo

Elementary problem “□ + 28 = □ × 5” explanation video (GIF preview):

Demo: □ + 28 = □ × 5

See the full high-definition version (including original speed): examples/BoxDivide.mp4. The same topic also generates a companion interactive webpage (drag □ to balance the scale).

Installation

Place the skills/math-explainer/ folder from this repo into your project (or personal directory) under .cursor/skills/:

git clone https://github.com/GordenSun/mathVideoMaker.git

# Option 1: as a project skill (active for the project)
cp -R mathVideoMaker/skills/math-expliner   your-project/.cursor/skills/

# Option 2: as a personal skill (available for all projects)
cp -R mathVideoMaker/skills/math-expliner  ~/.cursor/skills/

Environment (only needed for video generation; pure webpage can skip)

macOS / Linux:

bash .cursor/skills/math-explainer/scripts/setup_manim.sh   # install manim + ffmpeg + system libs + fonttools
python3 .cursor/skills/math-explainer/scripts/check_env.py  # health check

macOS key dependencies: cairo, pango, pkg-config (required for building pycairo via pip; script includes these). LaTeX is optional; if absent, Text/frow can be used instead of formulas.

Usage

In Cursor, simply tell the Agent something like:

  • “Make a video explaining the Pythagorean theorem”
  • “Explain to elementary school students: 5×□ = 4×□ + 7”
  • “Explain how y=n·x² changes with n”

The Agent will read SKILL.md and follow the phased workflow to produce both the video and the companion webpage. The final output will be placed in the topic folder root (<topic>/<scene-name>.mp4 and <topic>/index.html).

Directory structure

mathVideoMaker/
├── skills/math-explainer/         # Copy this to .cursor/skills/ for use
│   ├── SKILL.md                   # Main scheduling: phases + checkpoints
│   ├── references/                # Pedagogy/storyboard, Manim guide, recipes, web guide
│   ├── scripts/                   # setup / check_env / check_text / check_web / render
│   └── templates/                 # Scene skeleton, mathviz guardrails, golden examples, webpage & storyboard templates
└── examples/                      # Demo videos

Thanks to the LinuxDO (https://linux.do) community for support

Similar Articles

@XAMTO_AI: Remember the frustration of tinkering with math and physics teaching animations? Manim needed to be written by hand, LaTeX had to be configured, camera movements had to be adjusted frame by frame, and just setting up the environment would discourage half the people. Now there's an open-source tool that clears that path entirely — Math-To-Manim: describe it in one sentence, and it automatically generates a complete interactive animation. …

X AI KOLs Timeline

Math-To-Manim is an open-source tool that automatically generates complete math and physics teaching animations from a single sentence description, including LaTeX formulas and camera design, and comes with 55+ examples, significantly lowering the production barrier.

@GitTrend0x: Claude Code can now edit videos too! This SKILL is 100% free and open source. ✓ Automatically create animations ✓ Generate subtitles in different styles ✓ Remove silence, errors, and filler words https://github.com/browser-use/video-us…

X AI KOLs Timeline

video-use is a 100% open-source tool that lets Claude Code edit videos automatically by removing filler words, adding subtitles, color grading, and generating animations. It integrates with Claude Code via a skill and uses ElevenLabs for transcription.

@Easycompany333: Compiled 6 Claude Skills for video that you can try directly: 1. HyperFrames – generate animated video with one sentence. Articles, tweets, product intros can all become MP4. Suitable for product promotion, tutorial openers, short social videos. https://github.com/heyg…

X AI KOLs Timeline

Compiled 6 Claude Skills for video that can be used directly, covering auto-generated animated videos, AI-assisted rough cuts, React component rendered videos, multimedia generation toolbox, Chinese editing agent, and video prompt writing open-source tools.

@akokoi1: Open-source education skills — edulab adds analytic geometry problem types: Also supports random problem generation, text problems, and solving by uploading problem screenshots. Uses 2D Canvas to draw dynamic geometry boards (curves + moving lines/points + vectors + annotations), with built-in pen doodle markers. Includes dynamic console (sliders +...

X AI KOLs Timeline

edulab adds analytic geometry problem type, supports random problem generation, dynamic geometry board (2D Canvas drawing curves, moving lines, moving points, vectors, etc.) and KaTeX step-by-step parsing. It is an update to the open-source education skill tool.

@cevenif: Recently stumbled upon a pretty interesting open-source tool on GitHub: AetherViz Master. Give it a teaching topic, and it automatically generates a set of 3D interactive teaching web pages that you can use directly in your browser. Under the hood, it uses a hybrid rendering of Three.js and SVG, and can auto-detect subjects—…

X AI KOLs Timeline

Introduces an open-source tool called AetherViz Master, which uses AI to automatically transform teaching topics into immersive 3D interactive web pages, supporting multiple subjects such as physics, chemistry, mathematics, and more.