Agent skill

Manim

by autonomous-ai in autonomous-ai/openharness

Animate explanations with Manim Community — proofs, transforms, algorithms, graphs, data — as Python scenes rendered to MP4, and keep the pane playing the latest render.

MITAuto-check passedMedia & Creative

Install Manim

skills CLI

$ npx skills add autonomous-ai/openharness --skill manim -a claude-code

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

GitHub CLI

$ gh skill install autonomous-ai/openharness manim --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/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/manim/skills/manim .claude/skills/manim && 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/

Paste into Claude Code

Install the "manim" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/manim/skills/manim into .claude/skills/manim/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manim", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/autonomous-ai/openharness/tree/main/store/agents/manim/skills/manim

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add autonomous-ai/openharness --skill manim -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install autonomous-ai/openharness manim --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/manim/skills/manim .agents/skills/manim && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "manim" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/manim/skills/manim into .agents/skills/manim/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manim", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add autonomous-ai/openharness --skill manim -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install autonomous-ai/openharness manim --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/manim/skills/manim .cursor/skills/manim && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "manim" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/manim/skills/manim into .cursor/skills/manim/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manim", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/autonomous-ai/openharness.git --path store/agents/manim/skills/manim

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add autonomous-ai/openharness --skill manim -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install autonomous-ai/openharness manim --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/manim/skills/manim .gemini/skills/manim && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "manim" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/manim/skills/manim into .gemini/skills/manim/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manim", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install autonomous-ai/openharness manim

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add autonomous-ai/openharness --skill manim -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/manim/skills/manim .github/skills/manim && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "manim" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/manim/skills/manim into .github/skills/manim/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manim", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add autonomous-ai/openharness --skill manim -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install autonomous-ai/openharness manim --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/manim/skills/manim .opencode/skills/manim && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "manim" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/manim/skills/manim into .opencode/skills/manim/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manim", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: manim
GitHub stars: 1.1k
Token cost: ~1.1k tokens
SKILL.md length: 464 words
Files: 1
Skills in repo: 100
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Animate explanations with Manim Community — proofs, transforms, algorithms, graphs, data — as Python scenes rendered to MP4, and keep the pane playing the latest render.

Any request that ends in an animation
SKILL.md covers Render (the verdict comes with…, Chapters, Writing scenes and Rules
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
An explainer video

What it does

Manim is an agent skill from autonomous-ai/openharness. Animate explanations with Manim Community — proofs, transforms, algorithms, graphs, data — as Python scenes rendered to MP4, and keep the pane playing the latest render. Use for any request that ends in an animation or an explainer video.

Its SKILL.md is about 1.1k 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 Media & Creative, covering Video production. It works with Manim and Python. The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.

When your agent uses it

Any request that ends in an animation
An explainer video

Example prompts

“/manim”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 50da5db. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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 loads about 1.1k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 464 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~61
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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 autonomous-ai/openharness at commit 50da5db, republished under its MIT licence (© autonomous-ai). 464 words, ~1,050 tokens.

Download SKILL.mdSave it as .claude/skills/manim/SKILL.md (or your agent's skills folder).

name: manim
description: Animate explanations with Manim Community — proofs, transforms, algorithms, graphs, data — as Python scenes rendered to MP4, and keep the pane playing the latest render. Use for any request that ends in an animation or an explainer video.

manim

Manim (Manim Community edition) renders animations from Python: a Scene subclass whose construct() plays animations on mobjects. The render lands as MP4 under out/. Tools: $MANIM (the pinned CLI), $MANIM_PYTHON (its interpreter). Never install another.

Render (the verdict comes with it)

bash

"$MANIM_PYTHON" "$MANIM_TOOLCHAIN/render.py" scenes/intro.py Intro            # quick: 480p15, the default
"$MANIM_PYTHON" "$MANIM_TOOLCHAIN/render.py" -qm scenes/intro.py Intro        # medium: 720p30
"$MANIM_PYTHON" "$MANIM_TOOLCHAIN/render.py" -qh scenes/intro.py Intro        # final: 1080p60
"$MANIM_PYTHON" "$MANIM_TOOLCHAIN/render.py" --format gif scenes/x.py Name    # a gif instead

render.py is manim render with the same flags, output and tracebacks, plus what the pane needs: --media_dir out --save_sections, a live progress file (the pane plays each animation as it is written and shows a failure with its line), a record of the render's animations and chapters, and the verdict at the end. Use it for every render; plain $MANIM render still works but the pane sees less. Renders go to out/videos/<file>/<quality>/<Scene>.mp4. Render at -ql while iterating (fast), -qh once at the end.

Chapters

The pane shows a scene's sections as chapters — on the timeline, in a list, as 1…9 keys. Mark every beat of the storyboard with a section, named the way a chapter title reads:

python

def construct(self):
    self.next_section("The question")
    ...
    self.next_section("Squares on the sides")
    ...
    self.next_section("9 + 16 = 25")

Three to eight sections for a 20–60 s scene; a name is two to five words; the first call comes before the first play. A section with no animation is dropped. Keep names stable between renders: the pane marks a chapter "changed" or "new" by its name.

Writing scenes

One file per scene under scenes/; class name = the scene's name; a docstring says what it shows.
Mobjects: Text, MathTex (needs LaTeX — check command -v latex first; without it, formulas are Text(...) with Unicode superscripts and the render still lands), Circle, Square, Rectangle, Line, Arrow, Dot, Axes, NumberPlane, VGroup, Table, BarChart, ImageMobject.
Animations: Create, Write, FadeIn/FadeOut (with shift=), Transform, ReplacementTransform, MoveToTarget, Indicate, Circumscribe, LaggedStart, AnimationGroup, .animate (e.g. self.play(dot.animate.shift(RIGHT * 2))), run_time=, rate_func=.
Layout: .next_to(other, DOWN, buff=0.3), .to_edge(UP), .move_to(ORIGIN), .scale(), .arrange(RIGHT) on groups. The frame is 14.2 × 8 units; keep text within ±6 horizontally.
Timing: 0.6–1.2 s per beat, self.wait(0.5) between ideas, never more than one new idea on screen at a time. A 60-second explainer is 8–12 beats.
Look: dark background (self.camera.background_color = "#0b0b0c"), one accent colour, a sans-serif via Text(..., font="Helvetica Neue"), big type (scale 0.8–1.4).
Graphs and data: Axes(x_range=[0, 10, 1], y_range=[0, 5, 1]), axes.plot(lambda x: ...), axes.get_graph_label, BarChart(values, bar_names=...).
Camera moves: subclass MovingCameraScene and animate self.camera.frame.

Show full SKILL.md (100 more words)Show less

Rules

Save early: a first render within the first minute (title + one beat), then add beats.
Every beat is a section (see Chapters): a proof or an explainer arrives chaptered.
Every request that says "explain" is a sequence: what it is, why it matters, the mechanism, the result. One scene, or one scene per section for long ones.
Assets (images, data) live under assets/; reference them relatively.
A render that fails prints a Python traceback (and the pane shows the error and its line); fix the line it names, render again. The pane keeps playing the last good render meanwhile.

Files

Just SKILL.md in store/agents/manim/skills/manim of autonomous-ai/openharness.

Open the folder on GitHubat commit 50da5db

Compare with similar skills

Manim 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 compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Manim this skillautonomous-ai/openharness	1.1k	—	~1.1k	Automated safety check: Pass	MIT	today
Remotionzhuzhaoyun/Molio	432	—	~4k	Automated safety check: Pass	Custom licence	today
Concept To VideoMathews-Tom/armory	328	—	~4.9k	Automated safety check: Pass	MIT	2 days ago
Manim Video Productionbrowser-use/video-use	28k	6 repos	~3k	Automated safety check: Pass	MIT	6 days ago
Manim Explainer VideosPrismer-AI/PrismerCloud	1.6k	2 repos	~3.1k	Automated safety check: Pass	MIT	8 days ago
Vox DirectorAlisa0808/vox-director	2.2k	—	~5.6k	Automated safety check: Pass	MIT	3 days ago

Similar skills

Remotion
zhuzhaoyun/Molio
Molio's builtin skill for MAKING a video from any source — wiki notes, articles, scripts, product info, or a brief — and rendering it to MP4.
432 GitHub stars~4k tokensUpdated today
Media & CreativeAuto-check passed
Concept To Video
Mathews-Tom/armory
Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition.
328 GitHub stars~4.9k tokensUpdated 2 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.
28k GitHub starsUsed in 6 repos~3k tokens
Media & CreativeAuto-check passed
Manim Explainer Videos
Prismer-AI/PrismerCloud
Produces 3Blue1Brown-style explainer animations with Manim Community Edition for math, algorithms, equations and architecture diagrams, with planning and rendering references.
1.6k GitHub starsUsed in 2 repos~3.1k tokens
Media & CreativeAuto-check passed
Vox Director
Alisa0808/vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all…
2.2k GitHub stars~5.6k tokensUpdated 3 days ago
Media & CreativeAuto-check passed
Cap Cinematic Demo Generator
CapSoftware/Cap
Turns any URL into a short cinematic product-demo video on macOS, scouting the page, recording it with virtual input, then treating the clip with Cap's 3D camera and music.
23k GitHub stars~2.4k tokensUpdated today
Media & CreativeAuto-check passed

Questions about Manim

What does Manim do?

Animate explanations with Manim Community — proofs, transforms, algorithms, graphs, data — as Python scenes rendered to MP4, and keep the pane playing the latest render. Manim is an agent skill from autonomous-ai/openharness. Animate explanations with Manim Community — proofs, transforms, algorithms, graphs, data — as Python scenes rendered to MP4, and keep the pane playing the latest render.

When should I use Manim?

Manim fits situations like: any request that ends in an animation; an explainer video.

How do I install Manim in Claude Code?

Run `npx skills add autonomous-ai/openharness --skill manim -a claude-code`. Or copy the skill folder (store/agents/manim/skills/manim in autonomous-ai/openharness) into .claude/skills/manim in your project. Claude Code loads it when a task matches its description.

How do I install Manim in Codex?

Run `npx skills add autonomous-ai/openharness --skill manim -a codex`. Or copy the skill folder (store/agents/manim/skills/manim in autonomous-ai/openharness) into .agents/skills/manim in your project. Codex loads it when a task matches its description.

Can I use Manim 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 autonomous-ai/openharness --skill manim -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, .gemini/skills/manim, .github/skills/manim and .opencode/skills/manim in your project.

What does Manim need to run?

SKILL.md names no scripts, command-line tools or credentials: Manim is instructions for the agent only. Our summary lists: Python 3.

Does Manim access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Manim 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 use?

Manim is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Manim use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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?

Skills that share tags, products or a category with Manim: Remotion (zhuzhaoyun/Molio, 432 stars), Concept To Video (Mathews-Tom/armory, 328 stars), Manim Video Production (browser-use/video-use, 28k stars) and Manim Explainer Videos (Prismer-AI/PrismerCloud, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Manim?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,149 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 8, 2026.

Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Manim

Install Manim

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

manim

Render (the verdict comes with it)

Chapters

Writing scenes

Rules

Files

Compare with similar skills

Similar skills

Remotion

Concept To Video

Manim Video Production

Manim Explainer Videos

Vox Director

Cap Cinematic Demo Generator

More from autonomous-ai/openharness

G-code Slicer Tool

Home Assistant Automation Builder

Score Music Composer

OrcaSlicer 3MF and G-code Workflow

Sheets and Docs Report Builder

Bambu Labs

Questions about Manim

Install Manim

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

manim

Render (the verdict comes with it)

Chapters

Writing scenes

Rules

Files

Compare with similar skills

Similar skills

More from autonomous-ai/openharness

Related

Questions about Manim