Menu
Skills How it works Pricing
Free Video skillKnowledge videos

Math Process Video

Turn a mathematical relationship into an editable Python animation with inspectable geometry, formulas and local MP4 export.

Silent math insert: triangle area from a rectangle. Local ManimGX render, normalized to 30 fps. 16:9 · 0:06

What you get

  • Editable Python scenes and a locally rendered MP4
  • Layout inspection frames and mathematical checks

You will need

  • Python 3.13+, uv and pinned ManimGX 0.1.1
  • First use downloads the engine and dependencies
  • FFmpeg and FFprobe for output verification
  • An explicit mathematical claim and variables

Good fit

  • Geometry, functions and step-by-step mathematical relationships
  • Visual inserts for a larger knowledge video

Not for

  • Automatically verified scientific claims
  • A narrated film without supplying an audio workflow

You say

“Use the installed Skill to animate my mathematical claim. Define variables and the visual explanation, inspect the layout, render a local MP4 and verify the formula independently.”

After installing, say something like this to your agent with your own topic and assets. It asks only for what is missing.

FAQ

Do I need an account?

No. Copy the install prompt into your agent, or download the free ZIP.

What does it cost to run?

The Skill is free. It needs the tools listed under “You will need”. Any voice, model or media service you choose bills you directly; FeedSkills does not include provider credits.

Can I use the videos commercially?

Videos you make are yours to use, including commercially. The Skill package is licensed as: MIT; bundled dependency notices retained. Fonts, music, footage and services you add keep their own terms.

Which agents does it work with?

Agents that read SKILL.md files, such as Codex or Claude Code. What FeedSkills has actually tested is listed under Tested scope below.

Tested scope

Version
0.1.1
Acceptance
Acceptance for this version is still pending. It remains installable; check what has been tested before relying on it.
Tested
Three real local ManimGX renders cover two concepts and one parameter revision. Formula fixtures, frame counts and full decode checks pass. Silent 5–7 second inserts; complete visual acceptance and a fresh operating system remain unverified.
Runs on
Codex · macOS · Python 3.13+
License
MIT; bundled dependency notices retained

Details

Show the relationship, then the formula

Start with a precise claim: how changing a function shifts its graph, why a triangle has half a rectangle’s area, or how a process changes one state into another. Your Agent names the variables, builds an editable ManimGX scene and checks that the geometry supports the claim.

The deliverable is Python source and an actually rendered MP4. The included examples are silent animations that can stand alone as short visual explanations or be inserted into a larger knowledge video.

Inspect, render and check

Install the pinned engine in a separate Python environment. Inspect the scene’s layout, fix formula size and clipping, then render with an explicit resolution and frame rate. Check both the numerical result and the actual frames: a correct formula can still be unreadable on screen.

For a local revision, change the named parameter or scene and save a new output. Reuse starts with a different mathematical claim, not a new title over the same animation. The package includes example source, upstream API guidance and license notices.

Runtime and boundaries

ManimGX runs locally after its engine and dependencies are downloaded. No video-generation API key is needed for this rendering path. Narration, subtitles, music and external source verification are separate steps; the package does not silently supply them or certify every scientific topic.