#67 by GitHub stars

browser-use/video-use

Edit videos with coding agents

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

43cfc5668335 → 43cfc5668335

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 43cfc5668335

No earlier version was observed for comparison.

Compare on GitHub

`skills/manim-video/SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Network or broad shell

43cfc5668335 → 43cfc5668335

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 43cfc5668335

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 43cfc566833548093455c9d4a46bd69913b7e552

30.7kGitHub stars

409stars in 7 days

2skills in this repository

1commit in 30 days

Heat

7.2

Star growth, last 7 daysAhead of 87% of tracked repositories
Star growth, last 24 hoursAhead of 90% of tracked repositories
Rank movement, last 7 daysAhead of 87% of tracked repositories
Commits, last 30 daysAhead of 54% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

video-use /
manim-video skills/manim-video

How it works

Choose a skill

video-use

When your agent uses it

Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.

What it loads into context

Frontmatter

74 tokens

Always available to the agent

SKILL.md

6,455 tokens

When the skill is activated

Reference documents

3,349 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Principle
Hard Rules (production correctness — non-negotiable)
Directory layout
Setup
Helpers
The process
Cut craft (techniques)
The packed transcript (primary reading view)
Editor sub-agent brief (for multi-take selection)
Color grade (when requested)
Subtitles (when requested)
Animations (when requested)
Music and sound effects (when requested)
Output spec
EDL format
Memory — `project.md`
Anti-patterns

Scripts executed separately

helpers/grade.py
helpers/pack_transcripts.py
helpers/render.py
helpers/timeline_view.py
helpers/transcribe.py
helpers/transcribe_batch.py
tests/test_render_captions.py
tests/test_render_fps.py
tests/test_render_orientation.py

Files

.env.exampleasset20 bytes
.gitignoreasset790 bytes
LICENSEasset1,068 bytes
README.mddoc5,632 bytes
SKILL.mdcore26,098 bytes
SKILL.mdcore26,098 bytes
SKILL.mdcore26,098 bytes
SKILL.mdcore26,098 bytes
SKILL.mdcore26,098 bytes
SKILL.mdcore26,098 bytes
SKILL.mdcore26,098 bytes
helpers/grade.pyruns13,244 bytes
helpers/pack_transcripts.pyruns7,207 bytes
helpers/render.pyruns29,462 bytes
helpers/timeline_view.pyruns13,748 bytes
helpers/transcribe.pyruns8,027 bytes
helpers/transcribe_batch.pyruns3,970 bytes
install.mddoc7,739 bytes
poster.htmlasset19,975 bytes
pyproject.tomlasset450 bytes
static/timeline-view.svgasset12,329 bytes
static/video-use-banner.pngasset511,869 bytes
tests/test_render_captions.pyruns4,339 bytes
tests/test_render_fps.pyruns5,347 bytes
tests/test_render_orientation.pyruns2,313 bytes

Read SKILL.md


# Video Use

## Principle

1. **LLM reasons from raw transcript + on-demand visuals.** The only derived artifact that earns its keep is a packed phrase-level transcript (`takes_packed.md`). Everything else — filler tagging, retake detection, shot classification, emphasis scoring — you derive at decision time.
2. **Audio is primary, visuals follow.** Cut candidates come from speech boundaries and silence gaps. Drill into visuals only at decision points.
3. **Ask → confirm → execute → iterate → persist.** Never touch the cut until the user has confirmed the strategy in plain English.
4. **Generalize.** Do not assume what kind of video this is. Look at the material, ask the user, then edit.
5. **Artistic freedom is the default.** Every specific value, preset, font, color, duration, pitch structure, and technique in this document is a *worked example* from one proven video — not a mandate. Read them to understand what's possible and why each worked. Then make your own taste calls based on what the material actually is and what the user actually wants. **The only things you MUST do are in the Hard Rules section below.** Everything else is yours.
6. **Invent freely.** If the material calls for a technique not described here — split-screen, picture-in-picture, lower-third identity cards, reaction cuts, speed ramps, freeze frames, crossfades, match cuts, L-cuts, J-cuts, speed ramps over breath, whatever — build it. The helpers are ffmpeg and PIL. They can do anything the format supports. Do not wait for permission.
7. **Verify your own output before showing it to the user.** If you wouldn't ship it, don't present it.

## Hard Rules (production correctness — non-negotiable)

View the complete source on GitHub

manim-video

When your agent uses it

Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.

What it loads into context

Frontmatter

100 tokens

Always available to the agent

SKILL.md

3,055 tokens

When the skill is activated

Reference documents

23,760 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Creative Standard
Prerequisites
Modes
Stack
Pipeline
Project Structure
Creative Direction
Workflow
Critical Implementation Notes
Performance Targets
References
Creative Divergence (use only when user requests experimental/creative/unique output)

Scripts executed separately

scripts/setup.sh

Files

README.mddoc886 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
SKILL.mdcore11,983 bytes
references/animation-design-thinking.mddoc7,205 bytes
references/animations.mddoc8,836 bytes
references/camera-and-3d.mddoc4,132 bytes
references/decorations.mddoc5,006 bytes
references/equations.mddoc6,086 bytes
references/graphs-and-data.mddoc4,628 bytes
references/mobjects.mddoc9,739 bytes
references/paper-explainer.mddoc9,333 bytes
references/production-quality.mddoc5,904 bytes
references/rendering.mddoc5,375 bytes
references/scene-planning.mddoc2,751 bytes
references/troubleshooting.mddoc4,319 bytes
references/updaters-and-trackers.mddoc8,500 bytes
references/visual-design.mddoc4,762 bytes
scripts/setup.shruns921 bytes

Read SKILL.md


# Manim Video Production Pipeline

## Creative Standard

This is educational cinema. Every frame teaches. Every animation reveals structure.

**Before writing a single line of code**, articulate the narrative arc. What misconception does this correct? What is the "aha moment"? What visual story takes the viewer from confusion to understanding? The user's prompt is a starting point — interpret it with pedagogical ambition.

**Geometry before algebra.** Show the shape first, the equation second. Visual memory encodes faster than symbolic memory. When the viewer sees the geometric pattern before the formula, the equation feels earned.

**First-render excellence is non-negotiable.** The output must be visually clear and aesthetically cohesive without revision rounds. If something looks cluttered, poorly timed, or like "AI-generated slides," it is wrong.

**Opacity layering directs attention.** Never show everything at full brightness. Primary elements at 1.0, contextual elements at 0.4, structural elements (axes, grids) at 0.15. The brain processes visual salience in layers.

View the complete source on GitHub

Skills included

video-use
manim-video

Repository facts

License: MIT
Created: Apr 12, 2026
Last pushed: Oct 8, 2026
Forks: 3,553
Open issues: 35
Project activity: Active

Rank over the last 12 weeks

Now #67 · best #67 · same as 30 days ago

#69 from Oct 14 to Oct 24
#70 on Oct 25
#68 from Oct 28 to Oct 29
#69 from Oct 30 to Oct 31
#68 on Nov 1
#67 since Nov 2

23 earlier periods

#78 on Aug 2
#75 on Aug 8
#76 from Aug 9 to Aug 10
#77 on Aug 11
#78 from Aug 12 to Aug 14
#79 from Aug 15 to Aug 17
#80 from Aug 18 to Aug 23
#81 from Aug 24 to Aug 26
#82 from Aug 27 to Aug 29
#80 from Aug 30 to Aug 31
#79 from Sep 1 to Sep 3
#78 on Sep 4
#77 from Sep 5 to Sep 10
#76 from Sep 11 to Sep 13
#77 from Sep 14 to Sep 19
#76 from Sep 20 to Sep 21
#75 on Sep 22
#72 from Sep 23 to Sep 24
#70 on Sep 25
#69 on Sep 26
#68 from Sep 27 to Oct 1
#67 from Oct 2 to Oct 11
#68 from Oct 12 to Oct 13

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 2, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 15 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/manim-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
3 dangerous shell commandsin 1 file: install.md:61
28 network referencesin 6 files: README.md:11 poster.html:5 install.md:36 and 3 more
No hidden or obfuscated text
No instruction overrides
10 executable scriptsin 10 files: helpers/grade.py:1 helpers/pack_transcripts.py:1 helpers/render.py:1 and 7 more
26 references to secretsin 7 files: helpers/transcribe.py:36 install.md:100 helpers/transcribe_batch.py:23 and 4 more
No requests to vote in Hot

Show all 67 signals by file

`.env.example`

Access to secretsline 1
```
[Credential-related source omitted]
```

`.gitignore`

Access to secretsline 2
```
[Credential-related source omitted]
```

`README.md`

Network accessline 11

Cloud-hosted video-use is coming. [Join the waitlist at video-use.com](https://video-use.com?utm_source=github).

Network accessline 17

- **30ms audio fades** at every cut so you never hear a pop - **Burns subtitles** in your style — 2-word UPPERCASE chunks by default, fully customizable - **Generates animation overlays** via [HyperFrames](https://github.com/heygen-com/hype

Network accessline 18

- **Burns subtitles** in your style — 2-word UPPERCASE chunks by default, fully customizable - **Generates animation overlays** via [HyperFrames](https://github.com/heygen-com/hyperframes), [Remotion](https://www.remotion.dev/), [Manim](htt

Network accessline 19

- **Generates animation overlays** via [HyperFrames](https://github.com/heygen-com/hyperframes), [Remotion](https://www.remotion.dev/), [Manim](https://www.manim.community/), or PIL — spawned in parallel sub-agents, one per animation

Network accessline 28

Set up https://github.com/browser-use/video-use for me.

Network accessline 33

The agent handles the clone, dependencies, skill registration, and prompts you once for your ElevenLabs API key (grab one at [elevenlabs.io/app/settings/api-keys](https://elevenlabs.io/app/settings/api-keys)).

Network accessline 42

For always-on editing from your own VPS or Telegram, run the agent through [Browser Use Box](https://browser-use.com/bux). [Watch the 15-second demo](https://www.tiktok.com/@browser_use/video/7639824093721758989).

Network accessline 55

# 1. Clone and symlink into your agent's skills directory git clone https://github.com/browser-use/video-use ~/Developer/video-use

Network accessline 56

git clone https://github.com/browser-use/video-use ~/Developer/video-use

Access to secretsline 67
```
[Credential-related source omitted]
```
Access to secretsline 68
```
[Credential-related source omitted]
```

`SKILL.md`

Access to secretsline 62
```
[Credential-related source omitted]
```

`helpers/grade.py`

Executable scriptline 1
```
Executable file
```

`helpers/pack_transcripts.py`

Executable scriptline 1
```
Executable file
```

`helpers/render.py`

Executable scriptline 1
```
Executable file
```

`helpers/timeline_view.py`

Executable scriptline 1
```
Executable file
```

`helpers/transcribe.py`

Executable scriptline 1
```
Executable file
```

Network accessline 33

SCRIBE_URL = "https://api.elevenlabs.io/v1/speech-to-text"

Access to secretsline 36
```
[Credential-related source omitted]
```
Access to secretsline 37
```
[Credential-related source omitted]
```
Access to secretsline 44
```
[Credential-related source omitted]
```
Access to secretsline 46
```
[Credential-related source omitted]
```
Access to secretsline 48
```
[Credential-related source omitted]
```
Access to secretsline 86
```
[Credential-related source omitted]
```

Network accessline 101

with open(audio_path, "rb") as f:         resp = requests.post(

Network accessline 102
```
resp = requests.post(
```
Access to secretsline 104
```
[Credential-related source omitted]
```
Access to secretsline 131
```
[Credential-related source omitted]
```
Access to secretsline 178
```
[Credential-related source omitted]
```
Access to secretsline 228
```
[Credential-related source omitted]
```
Access to secretsline 233
```
[Credential-related source omitted]
```

`helpers/transcribe_batch.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 23
```
[Credential-related source omitted]
```
Access to secretsline 87
```
[Credential-related source omitted]
```
Access to secretsline 99
```
[Credential-related source omitted]
```

`install.md`

Network accessline 36

test -d ~/Developer/video-use || git clone https://github.com/browser-use/video-use ~/Developer/video-use

Dangerous shell operationline 61

# sudo apt-get update && sudo apt-get install -y ffmpeg

Dangerous shell operationline 65
```
# sudo pacman -S ffmpeg yt-dlp
```

Dangerous shell operationline 68

If `brew` / `apt` / `pacman` requires a sudo prompt, tell the user the exact command and wait. Do not invent a password.

Access to secretsline 100
```
[Credential-related source omitted]
```
Access to secretsline 101
```
[Credential-related source omitted]
```
Access to secretsline 102
```
[Credential-related source omitted]
```
Network accessline 107
```
[Credential-related source omitted]
```
Access to secretsline 107
```
[Credential-related source omitted]
```
Access to secretsline 112
```
[Credential-related source omitted]
```
Access to secretsline 113
```
[Credential-related source omitted]
```

Network accessline 120

```bash     curl -s -o /dev/null -w '%{http_code}\n' \

Network accessline 121

curl -s -o /dev/null -w '%{http_code}\n' \

Access to secretsline 122
```
[Credential-related source omitted]
```
Network accessline 123
```
https://api.elevenlabs.io/v1/user
```

`poster.html`

Network accessline 5

<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>How an LLM Understands Video</title> <script src="https://cdn.tailwindcss.com"></script>

Network accessline 6

<title>How an LLM Understands Video</title> <script src="https://cdn.tailwindcss.com"></script> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800;900&family=JetBrains+Mono:wght@400;500;600;700&display=swap"

Network accessline 7

<script src="https://cdn.tailwindcss.com"></script>

Network accessline 8

<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800;900&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet">

Network accessline 70

<div class="p-5">         <svg viewBox="0 0 1100 460" class="w-full" xmlns="http://www.w3.org/2000/svg">

Network accessline 71

<svg viewBox="0 0 1100 460" class="w-full" xmlns="http://www.w3.org/2000/svg">

Network accessline 249

<div class="px-10 pb-8">     <div class="text-[10px] font-extrabold uppercase tracking-[3px] text-stone-400 mb-4">How it gets there</div>     <svg viewBox="0 0 1100 100" class="w-full" xmlns="http://www.w3.org/2000/svg">

Network accessline 250

<div class="text-[10px] font-extrabold uppercase tracking-[3px] text-stone-400 mb-4">How it gets there</div>     <svg viewBox="0 0 1100 100" class="w-full" xmlns="http://www.w3.org/2000/svg">       <defs>

Network accessline 251

<svg viewBox="0 0 1100 100" class="w-full" xmlns="http://www.w3.org/2000/svg">

`skills/manim-video/README.md`

Network accessline 3

Production pipeline for mathematical and technical animations using [Manim Community Edition](https://www.manim.community/).

`skills/manim-video/scripts/setup.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`static/timeline-view.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1140 540" font-family="Inter, system-ui, sans-serif">

`tests/test_render_captions.py`

Executable scriptline 1
```
Executable file
```

`tests/test_render_fps.py`

Executable scriptline 1
```
Executable file
```

`tests/test_render_orientation.py`

Executable scriptline 1
```
Executable file
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 55 facts

Network access in prose of documentationREADME.md:11Low confidence
Network access in prose of documentationREADME.md:17Low confidence
Network access in prose of documentationREADME.md:18Low confidence
Network access in prose of documentationREADME.md:19Low confidence
Network access in code of documentationREADME.md:28Low confidence
Network access in prose of documentationREADME.md:33Low confidence
Network access in prose of documentationREADME.md:42Low confidence
Network access in code of documentationREADME.md:55Low confidence
Network access in code of documentationREADME.md:56Low confidence
Access to secrets in code of documentationREADME.md:67Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueREADME.md:68Low confidence
Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueSKILL.md:62Low confidence
Executable script in prose of a file that runshelpers/grade.py:1Low confidence
Executable script in prose of a file that runshelpers/pack_transcripts.py:1Low confidence
Executable script in prose of a file that runshelpers/render.py:1Low confidence
Executable script in prose of a file that runshelpers/timeline_view.py:1Low confidence
Executable script in prose of a file that runshelpers/transcribe.py:1Low confidence
Network access in code of a file that runshelpers/transcribe.py:33High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehelpers/transcribe.py:36Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehelpers/transcribe.py:37Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehelpers/transcribe.py:44Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehelpers/transcribe.py:46Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehelpers/transcribe.py:48Low confidence
Access to secrets in code of a file that runshelpers/transcribe.py:86High confidence
Network access in code of a file that runshelpers/transcribe.py:101High confidence
Network access in code of a file that runshelpers/transcribe.py:102High confidence
Access to secrets in code of a file that runshelpers/transcribe.py:104High confidence
Access to secrets in code of a file that runshelpers/transcribe.py:131High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehelpers/transcribe.py:178Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehelpers/transcribe.py:228Low confidence
Access to secrets in code of a file that runshelpers/transcribe.py:233High confidence
Executable script in prose of a file that runshelpers/transcribe_batch.py:1Low confidence
Access to secrets in code of a file that runshelpers/transcribe_batch.py:23High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehelpers/transcribe_batch.py:87Low confidence
Access to secrets in code of a file that runshelpers/transcribe_batch.py:99High confidence
Network access in code of documentationinstall.md:36Low confidence
Dangerous shell operation in code of documentationinstall.md:61Low confidence
Dangerous shell operation in code of documentationinstall.md:65Low confidence
Dangerous shell operation in prose of documentationinstall.md:68Low confidence
Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valueinstall.md:100Low confidence
Access to secrets in prose of documentationinstall.md:101Low confidence
Access to secrets in prose of documentationinstall.md:102Low confidence
Network access in prose of documentationinstall.md:107Low confidence
Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valueinstall.md:107Low confidence
Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valueinstall.md:112Low confidence
Access to secrets in prose of documentationinstall.md:113Low confidence
Network access in prose of documentationinstall.md:120Low confidence
Network access in prose of documentationinstall.md:121Low confidence
Access to secrets in prose of documentationinstall.md:122Low confidence
Network access in prose of documentationinstall.md:123Low confidence

and 5 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![browser-use/video-use on hotskills](https://hotskills.dev/badge/browser-use-video-use.svg)](https://hotskills.dev/skill/browser-use-video-use/)

browser-use/video-use

History

SKILL.md

skills/manim-video/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

video-use

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

manim-video

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

.env.example

.gitignore

README.md

SKILL.md

helpers/grade.py

helpers/pack_transcripts.py

helpers/render.py

helpers/timeline_view.py

helpers/transcribe.py

helpers/transcribe_batch.py

install.md

poster.html

skills/manim-video/README.md

skills/manim-video/scripts/setup.sh

static/timeline-view.svg

tests/test_render_captions.py

tests/test_render_fps.py

tests/test_render_orientation.py

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

NousResearch/hermes-agent

multica-ai/andrej-karpathy-skills

anthropics/skills

DietrichGebert/ponytail

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`skills/manim-video/SKILL.md`

`.env.example`

`.gitignore`

`README.md`

`SKILL.md`

`helpers/grade.py`

`helpers/pack_transcripts.py`

`helpers/render.py`

`helpers/timeline_view.py`

`helpers/transcribe.py`

`helpers/transcribe_batch.py`

`install.md`

`poster.html`

`skills/manim-video/README.md`

`skills/manim-video/scripts/setup.sh`

`static/timeline-view.svg`

`tests/test_render_captions.py`

`tests/test_render_fps.py`

`tests/test_render_orientation.py`