Video downloader skill
Claude Code Skill for downloading videos.
npx -y skills add smarks26/video-downloader-skillAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Downloads videos and audio from YouTube, Bilibili, Twitter, and other platforms using yt-dlp. Supports quality selection, format conversion, and audio extraction.
SKILL.md
2.4 KB, 585 tokens by cl100k_base, as published. Nobody here has run it
Video Downloader Skill
This skill downloads content from major video platforms by invoking the scripts/video_download.py script.
When to Use
Use this skill when the user's intent is to download, save, or grab online video or audio. Common trigger commands include:
- "Download this Bilibili video..."
- "Extract audio from this YouTube video and convert it to MP3."
- "Save this Twitter video in 1080p."
- "Can I download the video from this link?"
Command Structure
python3 scripts/video_download.py "<URL>" [OPTIONS]
Core Parameters
| Parameter | Short | Description | Default |
|---|---|---|---|
--output | -o | Specify output directory | Current directory |
--quality | -q | Set video quality (best, 1080p, 720p...) | best |
--format | -f | Set video format (mp4, webm, mkv) | mp4 |
--audio-only | -a | Download audio only and convert to MP3 | Off |
--cookies | -c | Specify Cookies file for authentication | None |
Usage Examples
-
Basic Download (Best Quality, MP4)
python3 scripts/video_download.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ" -
Download Bilibili Video with Specific Quality
python3 scripts/video_download.py "https://www.bilibili.com/video/BV1xx411c7mD" -q 1080p -
Extract Audio Only
python3 scripts/video_download.py "https://www.youtube.com/watch?v=..." -a -
Download using Cookies
python3 scripts/video_download.py "<URL>" -c /path/to/cookies.txt
Supported Platforms
This skill uses yt-dlp under the hood and theoretically supports numerous sites supported by it, including but not limited to:
- YouTube
- Bilibili
- Twitter / X
- Vimeo
- TikTok
Notes
- Dependencies: The script automatically handles the installation of
yt-dlp, no manual intervention required. - Filenames: Downloaded filenames are automatically generated based on the video title.
- Playlists: By default, only single videos are downloaded; playlists are not processed.
Gives 0 of the 12 instructions most video audio skills give in 585 tokens
Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07
- read individual rule files for detailed explanationsin 21 of 622, across 10 files
- render final videoin 13 of 622, across 6 files
- Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
- Use this skill when dealing with Remotion codein 11 of 622, across 4 files
- save generated audio to a WAV filein 11 of 622, across 4 files
- handle conversion errors gracefullyin 10 of 622, across 6 files
- add captions to videos alwaysin 10 of 622, across 4 files
- generate music from text descriptions using MusicGenin 9 of 622, across 2 files
- do not skip pipeline layersin 9 of 622, across 3 files
- do not make one tool do everythingin 9 of 622, across 3 files
- use azure document intelligence for complex pdfsin 9 of 622, across 4 files
- never ask the user to paste their full API keyin 9 of 622, across 3 files
Said here and by no other author read
- use the video download script for media downloads
- pass the media URL in quotes
- set download quality via the quality parameter
- set media format via the format parameter
- pass a cookies file via the cookies parameter
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.