Agent skill

Manim Video

by AlexAI-MCP in AlexAI-MCP/hermes-CCC

Create mathematical animations and explainer videos with Manim Community - code-driven animations for math, CS concepts, data visualization.

MITAuto-check passedData & Analytics

Install Manim Video

skills CLI
$ npx skills add AlexAI-MCP/hermes-CCC --skill manim-video -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AlexAI-MCP/hermes-CCC manim-video --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/manim-video .claude/skills/manim-video && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
manim-video
GitHub stars
135
Token cost
~2.3k tokens
SKILL.md length
847 words
Files
1
Skills in repo
44
Repo updated
First seen
Licence
MIT

At a glance

Create mathematical animations and explainer videos with Manim Community - code-driven animations for math, CS concepts, data visualization.

  • Works in 5 steps: Create a Python file such as scene.py. → Define one or more scene classes. → Render the desired scene by name. → …
  • Tasks that involve Data visualization
  • SKILL.md covers Purpose, Install, Mental Model and Minimal Scene Structure, plus 25 more sections
  • Calls pip

What it does

Manim Video is an agent skill from AlexAI-MCP/hermes-CCC. Create mathematical animations and explainer videos with Manim Community - code-driven animations for math, CS concepts, data visualization.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Data visualization and Video production. It works with Manim. The repository describes itself as: Hermes Agent ported to Claude Code Channel — 46 native skills, no OAuth, no external process. The licence is MIT.

When your agent uses it

  • Tasks that involve Data visualization
  • Tasks that involve Video production

Example prompts

  • “/manim-video”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Create a Python file such as scene.py.
  2. Define one or more scene classes.
  3. Render the desired scene by name.
  4. Inspect the output video.
  5. Revise the code and rerender.

What it can do on your machine

Read from SKILL.md and the folder at commit 8107e89. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Manim Video loads about 2.3k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 847 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AlexAI-MCP/hermes-CCC at commit 8107e89, republished under its MIT licence (© AlexAI-MCP). 847 words, ~2,327 tokens.

Download SKILL.mdSave it as .claude/skills/manim-video/SKILL.md (or your agent's skills folder).
name
manim-video
description
Create mathematical animations and explainer videos with Manim Community - code-driven animations for math, CS concepts, data visualization.
version
1.0.0
author
hermes-CCC (ported from Hermes Agent by NousResearch)
license
MIT

Manim Video

Purpose

  • Use this skill to create precise, code-driven animations for mathematics, computer science, algorithms, and data visualization.
  • Prefer Manim when the content is structural, symbolic, or instructional rather than cinematic live-action editing.
  • Manim is especially strong for equations, graphs, geometric constructions, and animated explanations of abstract systems.

Install

bash
pip install manim
  • On some systems you may also need FFmpeg and LaTeX-related dependencies for full math rendering support.
  • Verify the installation with manim --version.

Mental Model

  • A Manim scene is a Python class.
  • You place visual objects into the scene.
  • You animate transitions between states.
  • The render command converts the scene into a video file.
  • The code is the asset, which makes revisions reproducible.

Minimal Scene Structure

python
from manim import *

class MyScene(Scene):
    def construct(self):
        text = Text("Hello, Manim")
        self.play(Write(text))
        self.wait()

Basic Workflow

  1. Create a Python file such as scene.py.
  2. Define one or more scene classes.
  3. Render the desired scene by name.
  4. Inspect the output video.
  5. Revise the code and rerender.

Render Command

bash
manim -pql scene.py MyScene
  • -pql means preview plus quality low.
  • Use -pqh when you want a higher-quality render for export or sharing.
  • Low-quality previews are much faster during iteration.

Core Objects

  • Circle
  • Square
  • Text
  • MathTex
  • Axes
  • NumberPlane
  • Arrow

These cover a large fraction of introductory math and CS explainer work.

Shapes Example

python
from manim import *

class Shapes(Scene):
    def construct(self):
        circle = Circle(color=BLUE)
        square = Square(color=GREEN).shift(RIGHT * 2)
        arrow = Arrow(circle.get_right(), square.get_left(), color=YELLOW)

        self.play(Create(circle), Create(square))
        self.play(Create(arrow))
        self.wait()

Text and Labels

  • Use Text for plain words, labels, titles, and UI-like annotations.
  • Use MathTex for equations and symbolic math.
  • Keep labels short and readable.
  • Position text relative to objects with helpers like .next_to() and .to_edge().

Math Rendering

python
from manim import *

class Derivative(Scene):
    def construct(self):
        expr = MathTex(r"\frac{d}{dx} x^2 = 2x")
        self.play(Write(expr))
        self.wait()
  • Use raw strings for LaTeX-heavy expressions.
  • Split long formulas into chunks if you want to animate parts independently.
  • MathTex is one of Manim's highest-value primitives for educational video.

Graphs

python
from manim import *

class PlotExample(Scene):
    def construct(self):
        ax = Axes()
        graph = ax.plot(lambda x: x**2, color=BLUE)
        label = ax.get_graph_label(graph, label="x^2")

        self.play(Create(ax))
        self.play(Create(graph), FadeIn(label))
        self.wait()
  • Use Axes() for standard 2D coordinate systems.
  • Use NumberPlane() when you want a visible grid.
  • Use .plot() for function graphs.
  • Add labels only when they clarify the message.

Coordinate Grid Example

python
from manim import *

class PlaneExample(Scene):
    def construct(self):
        plane = NumberPlane()
        point = Dot(plane.c2p(2, 3), color=RED)
        note = Text("Point (2, 3)").scale(0.5).next_to(point, UP)

        self.play(Create(plane))
        self.play(FadeIn(point), Write(note))
        self.wait()

Common Animations

  • Create
  • Write
  • Transform
  • FadeIn
  • FadeOut
  • MoveAlongPath

These are enough to build most educational sequences.

Animation Example

python
from manim import *

class AnimateBasics(Scene):
    def construct(self):
        circle = Circle(color=BLUE)
        square = Square(color=GREEN)

        self.play(Create(circle))
        self.play(Transform(circle, square))
        self.play(FadeOut(circle))

Move Along Path

python
from manim import *

class AlongPath(Scene):
    def construct(self):
        path = Circle(radius=2, color=WHITE)
        dot = Dot(color=YELLOW).move_to(path.point_from_proportion(0))

        self.add(path, dot)
        self.play(MoveAlongPath(dot, path), run_time=3)
        self.wait()
  • MoveAlongPath is useful for state machines, orbital motion, and process flow visuals.
  • Use it for conceptual journeys, packets moving through systems, or points moving across graphs.

Layout Helpers

  • .shift()
  • .move_to()
  • .next_to()
  • .align_to()
  • .to_edge()
  • .to_corner()
  • VGroup(...) for grouping and arrangement

Good layout discipline saves time during revision.

Colors

  • RED
  • BLUE
  • GREEN
  • YELLOW
  • WHITE
  • ORANGE
  • PURPLE
  • TEAL

Use consistent semantic coloring across the scene.

Color Strategy

  • Use one color for inputs, another for transformations, and another for outputs.
  • Keep background contrast in mind.
  • Avoid using too many unrelated colors in the same explanation.
  • Use WHITE or light tones for neutral reference geometry.

Camera Control

python
from manim import *

class CameraExample(Scene):
    def construct(self):
        plane = NumberPlane()
        self.add(plane)
        self.play(self.camera.frame.animate.scale(0.5))
        self.wait()
  • Camera animation helps when zooming into local detail.
  • Use it sparingly so viewers do not lose context.
  • Zooming is most useful for dense graphs, local geometry, or multi-part explanations.

Output

  • Manim writes rendered video outputs under media/videos/.
  • Preview renders and partial intermediates also appear under the media/ tree.
  • Treat the Python source as canonical and the rendered MP4 as generated output.
  • Final videos are typically MP4 files.

Timing

  • Use self.wait() to hold the frame.
  • Adjust run_time= on animation calls to tune pacing.
  • Move slower for conceptual reveals and faster for purely decorative transitions.
  • Educational clarity depends on timing as much as layout.
Show full SKILL.md (324 more words)Show less

Narration-Oriented Design

  • Write scenes as if a narrator is speaking over them.
  • Introduce one concept at a time.
  • Avoid changing too many objects in the same beat.
  • Keep equations readable on screen long enough to be processed.
  • Use transforms to show continuity rather than replacing everything at once.

Reusable Pattern for Explainers

  1. Title the concept.
  2. Show the initial objects.
  3. Animate the transformation or derivation.
  4. Highlight the result.
  5. Pause.

This pattern works for algorithms, math derivations, and data stories.

Computer Science Use Cases

  • Sorting algorithm visualizations
  • Graph traversal animations
  • Finite-state machines
  • Distributed systems message flow
  • Complexity intuition with plotted growth curves
  • Data structure operations such as stack and queue updates

Data Visualization Use Cases

  • Plot a function or data series
  • Animate parameter changes
  • Show area under a curve
  • Reveal axes, labels, and legend in stages
  • Compare two functions through Transform

Three-Dimensional Scenes

python
from manim import *

class My3DScene(ThreeDScene):
    def construct(self):
        axes = ThreeDAxes()
        sphere = Sphere(radius=1, color=BLUE)
        self.set_camera_orientation(phi=75 * DEGREES, theta=30 * DEGREES)
        self.play(Create(axes), FadeIn(sphere))
        self.begin_ambient_camera_rotation(rate=0.2)
        self.wait(3)
  • Use ThreeDScene for surfaces, vectors, and spatial intuition.
  • Keep 3D scenes simple unless the extra dimension is genuinely explanatory.
  • Camera motion in 3D should support understanding, not distract from it.

Debugging Tips

  • Start with -pql for fast feedback.
  • Build the scene incrementally.
  • Comment out complex sections while debugging layout.
  • If math fails to render, verify the TeX environment and formula syntax.
  • Use small prototype scenes before composing a long final animation.

Production Guidance

  • Keep one concept per scene unless continuity demands otherwise.
  • Name classes clearly so render commands stay obvious.
  • Break long videos into scene modules and concatenate later if needed.
  • Use higher quality only after content and timing are stable.

Summary

  • Install with pip install manim.
  • Build scenes with class MyScene(Scene): def construct(self):.
  • Use objects like Circle, Square, Text, MathTex, Axes, NumberPlane, and Arrow.
  • Animate with Create, Write, Transform, FadeIn, FadeOut, and MoveAlongPath.
  • Render with manim -pql scene.py MyScene and switch to -pqh for higher quality.
  • Use MathTex(r"\\frac{d}{dx} x^2 = 2x") for math and Axes().plot(...) for graphs.
  • Use self.camera.frame.animate.scale(0.5) when zooming improves comprehension.
  • Expect MP4 output under media/videos/.

© AlexAI-MCP, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/manim-video of AlexAI-MCP/hermes-CCC.

Open the folder on GitHubat commit 8107e89

Compare with similar skills

Manim Video next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Manim Video compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Manim Video this skillAlexAI-MCP/hermes-CCC135—~2.3kAutomated safety check: PassMIT
Python Executorcortega26/chile-hub1132 repos~1.5kAutomated safety check: PassMIT
Concept Visualization Generatormingchen666/Reviva244—~2.8kAutomated safety check: PassNone
Plotbeat Data VideosUnclecheng-li/AI_Animation1.5k—~2.6kAutomated safety check: PassMIT
Manim Video Productionbrowser-use/video-use29k6 repos~3kAutomated safety check: PassMIT
D3 Vizcalesthio/OpenMontage66k3 repos~5.4kAutomated safety check: PassAGPL-3.0

Similar skills

  • Python Executor

    cortega26/chile-hub

    Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).

    113 GitHub starsUsed in 2 repos~1.5k tokens
    Data & AnalyticsAuto-check passed
  • Design and generate concept-first learning artifacts: concept cards, visual explanations, diagrams, interactive HTML demos, Manim/math visualizations, matplotlib scientific plots, misconception…

    244 GitHub stars~2.8k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed
  • Plotbeat Data Videos

    Unclecheng-li/AI_Animation

    Turns a local CSV or JSON file, or data fetched from an approved source, into an editable data-visualization video by adapting HyperFrames templates.

    1.5k GitHub stars~2.6k tokensUpdated 6 days ago
    Media & CreativeAuto-check passed
  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    29k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed
  • D3 Viz

    calesthio/OpenMontage

    Creating interactive data visualisations using d3.js. An agent skill from calesthio/OpenMontage.

    66k GitHub starsUsed in 3 repos~5.4k tokens
    Data & AnalyticsAuto-check passed
  • Qiaomu Cut

    joeseesun/qiaomu-cut-skill

    把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频:介绍…

    372 GitHub stars~6.8k tokensUpdated 13 days ago
    Media & CreativeAuto-check: notes

More from AlexAI-MCP/hermes-CCC

All 44 skills in this repo
  • GitHub Code Review

    AlexAI-MCP/hermes-CCC

    Review GitHub pull requests with a findings-first engineering mindset.

    135 GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed
  • GitHub PR Workflow

    AlexAI-MCP/hermes-CCC

    Run a disciplined GitHub pull request workflow from branch creation through merge.

    135 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Hermes Memory

    AlexAI-MCP/hermes-CCC

    Manage durable project memory for Claude Code. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Hermes Route

    AlexAI-MCP/hermes-CCC

    Route Claude Code work by complexity, risk, and tool needs. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed
  • Hermes Skill

    AlexAI-MCP/hermes-CCC

    Create, improve, inventory, and audit Claude Code skills. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Hermes Traj

    AlexAI-MCP/hermes-CCC

    Capture Claude Code interaction trajectories in training-friendly formats.

    135 GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Manim Video

What does Manim Video do?

Create mathematical animations and explainer videos with Manim Community - code-driven animations for math, CS concepts, data visualization. Manim Video is an agent skill from AlexAI-MCP/hermes-CCC. Create mathematical animations and explainer videos with Manim Community - code-driven animations for math, CS concepts, data visualization.

When should I use Manim Video?

Manim Video fits situations like: tasks that involve Data visualization; tasks that involve Video production.

How do I install Manim Video in Claude Code?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill manim-video -a claude-code`. Or copy the skill folder (skills/manim-video in AlexAI-MCP/hermes-CCC) into .claude/skills/manim-video in your project. Claude Code loads it when a task matches its description.

How do I install Manim Video in Codex?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill manim-video -a codex`. Or copy the skill folder (skills/manim-video in AlexAI-MCP/hermes-CCC) into .agents/skills/manim-video in your project. Codex loads it when a task matches its description.

Can I use Manim Video in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlexAI-MCP/hermes-CCC --skill manim-video -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/manim-video, .gemini/skills/manim-video, .github/skills/manim-video and .opencode/skills/manim-video in your project.

What does Manim Video need to run?

Going by SKILL.md and its folder, Manim Video needs the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Manim Video access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Manim Video safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Manim Video use?

Manim Video is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Manim Video use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Manim Video?

Skills that share tags, products or a category with Manim Video: Python Executor (cortega26/chile-hub, 113 stars), Concept Visualization Generator (mingchen666/Reviva, 244 stars), Plotbeat Data Videos (Unclecheng-li/AI_Animation, 1.5k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Manim Video?

AlexAI-MCP (a GitHub user) maintains it in AlexAI-MCP/hermes-CCC, which has 135 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on April 8, 2026.

Source: AlexAI-MCP/hermes-CCC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.