manim-skill
Create mathematical animations with Manim Community Edition(manimce). Generates distinctive, production-grade animations that avoid generic "AI slop" aesthetics. Use when user wants to animate concepts, equations, illustrate proofs, visualize algorithms, create math explainers, or produce 3Blue1Brown-style videos.
git clone https://github.com/Yusuke710/manim-skill
T=$(mktemp -d) && git clone --depth=1 https://github.com/Yusuke710/manim-skill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/manim-skill" ~/.claude/skills/yusuke710-manim-skill-manim-skill && rm -rf "$T"
skills/manim-skill/SKILL.mdProject Structure
Create a dedicated folder for each animation project in the user's current working directory (NOT in this skill's base directory). Use this flat structure:
<project-name>/ ├── plan.md # Planning document (Phase 1) ├── script.py # Manim code (Phase 2) ├── concat.txt # ffmpeg scene list (Phase 3) ├── final.mp4 # Stitched output (Phase 3) └── media/ # Auto-generated by manim └── videos/ └── script/ └── 480p15/ # or 1080p60 ├── Scene1_Name.mp4 ├── Scene2_Name.mp4 └── ...
Before starting: Create the project folder and work from within it. All commands should be run from the project directory.
mkdir -p <project-name> && cd <project-name>
Workflow Overview
Plan → Code → Render → Iterate
Phase 1: Plan
If the user has already used plan mode in claude code or provided detailed requirements, write that in
and skip to Phase 2. Otherwise, you MUST carefully plan the video structure before writing code.plan.md
Before writing any Manim code, wrtie
plan.md:
# [Video Title] ## Overview - **Topic**: [Core concept] - **Hook**: [Opening question/mystery] - **Target Audience**: [Prerequisites] - **Estimated Length**: [X minutes] - **Key Insight**: [The "aha moment"] - **Resolution**: [480p(default), 1080p] - **Aspect Ratio**: [16:9(default) / 9:16 / 1:1] ## 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] ### Voiceover - **Text**: "[Exact script or key points]" - **Sync Points**: "[phrase]" → syncs with [animation] ### 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] ## Shared Elements - [Recurring mobjects across scenes, e.g., "coordinate axes reappear in scenes 2, 4, 6"] - [Visual motifs, e.g., "blue highlight for key terms"] ## Color Palette - Primary: [color] - used for [purpose] - Secondary: [color] - used for [purpose] - Accent: [color] - used for [purpose] - Background: [color]
Phase 2: Code
BEFORE writing any code, you MUST invoke the
skill using the Skill tool, then read the relevant rule files it references (e.g., manimce-best-practices
, rules/scenes.md
) based on what your video needs.rules/animations.md
Write Manim Community Edition code in
script.py.
Code Structure
- One class per scene - Name scenes descriptively:
,Scene1_IntroductionScene2_DerivePDE - Always add subtitles to your animations with
add_subcaption()- Manim generates a
file automatically.srt - The viewer handles subtitle display and lets users toggle/resize them
- Manim generates a
from manim import * ## Scene1_Introduction class Scene1_Introduction(Scene): def construct(self): ## Scene1_Introduction.title title = Text("My Topic", font_size=48, color=BLUE) self.add_subcaption("Introducing our topic", duration=2) self.play(Write(title)) self.wait(1) ## Scene1_Introduction.fadeout self.play(FadeOut(title), subcaption="Let's begin", subcaption_duration=1)
Phase 3: Render
Use
manim CLI to render scenes. Multiple scenes can be rendered in parallel with one command.
manim -q<quality> [--media_dir <output_dir>] <script.py> Scene1 Scene2 Scene3 ...
Quality flags:
- Low quality (480p15, fastest for testing. Use by default)-ql
- High quality (1080p60, only when user explicitly requests)-qh
Output location:
/media/videos/<script_name>/<quality>/SceneName.mp4
Default
/media is located in current directory.
If any scene fails: Read the error, fix the code, re-render only the failed scenes.
Stitch scenes with ffmpeg
Once all scenes render successfully, combine them. All paths are relative to the project folder:
# Create concat list (run from project folder) cat > concat.txt << 'EOF' file 'media/videos/script/480p15/Scene1_Intro.mp4' file 'media/videos/script/480p15/Scene2_Main.mp4' file 'media/videos/script/480p15/Scene3_Conclusion.mp4' EOF # Combine videos ffmpeg -y -f concat -safe 0 -i concat.txt -c copy final.mp4
Result:
final.mp4 is created in the project folder alongside script.py and concat.txt.
Phase 4: Iterate on User Feedback
Launch the viewer for user to review and provide feedback (run from project folder):
python3 ../tools/video_viewer.py final.mp4 --order concat.txt [--script script.py]
: Video order file (concat.txt, required for chapters)--order
: Manim script (enables high-quality download option)--script
When user provides feedback:
- Identify which scenes need changes
- Modify the code
- Re-render only affected scenes
- Re-stitch the final video
- Run the viewer command again