Video downloader
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.From its SKILL.md
npx -y skills add ComposioHQ/awesome-claude-skills --skill video-downloaderAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing 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.
SKILL.md
2.6 KB, 610 tokens by cl100k_base, as published. Nobody here has run it
YouTube Video Downloader
Download YouTube videos with full control over quality and format settings.
Quick Start
The simplest way to download a video:
python scripts/download_video.py "https://www.youtube.com/watch?v=VIDEO_ID"
This downloads the video in best available quality as MP4 to /mnt/user-data/outputs/.
Options
Quality Settings
Use -q or --quality to specify video quality:
best(default): Highest quality available1080p: Full HD720p: HD480p: Standard definition360p: Lower qualityworst: Lowest quality available
Example:
python scripts/download_video.py "URL" -q 720p
Format Options
Use -f or --format to specify output format (video downloads only):
mp4(default): Most compatiblewebm: Modern formatmkv: Matroska container
Example:
python scripts/download_video.py "URL" -f webm
Audio Only
Use -a or --audio-only to download only audio as MP3:
python scripts/download_video.py "URL" -a
Custom Output Directory
Use -o or --output to specify a different output directory:
python scripts/download_video.py "URL" -o /path/to/directory
Complete Examples
- Download video in 1080p as MP4:
python scripts/download_video.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ" -q 1080p
- Download audio only as MP3:
python scripts/download_video.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ" -a
- Download in 720p as WebM to custom directory:
python scripts/download_video.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ" -q 720p -f webm -o /custom/path
How It Works
The skill uses yt-dlp, a robust YouTube downloader that:
- Automatically installs itself if not present
- Fetches video information before downloading
- Selects the best available streams matching your criteria
- Merges video and audio streams when needed
- Supports a wide range of YouTube video formats
Important Notes
- Downloads are saved to
/mnt/user-data/outputs/by default - Video filename is automatically generated from the video title
- The script handles installation of yt-dlp automatically
- Only single videos are downloaded (playlists are skipped by default)
- Higher quality videos may take longer to download and use more disk space
What ships with it: 1 file
4.2 KB alongside SKILL.md, 1 of them executable
scripts/
- download_video.pyruns4.2 KB
Gives 0 of the 12 instructions most social media skills give in 610 tokens
Counted across 400 of the 422 authors here whose files we hold, read 2026-09-06
- Build content around three to five pillarsin 40 of 400, across 16 files
- Read product marketing context before asking questionsin 37 of 400, across 15 files
- Gather goals, audience, brand voice, and resourcesin 35 of 400, across 13 files
- Maintain one to two weeks of scheduled contentin 27 of 400, across 8 files
- Batch content creation in weekly sessionsin 23 of 400, across 7 files
- Review top and bottom posts weeklyin 22 of 400, across 7 files
- Run the quality gate before deliveringin 20 of 400, across 11 files
- Add subtitles to all social videoin 20 of 400, across 7 files
- Write standalone captions that work without contextin 20 of 400, across 7 files
- Prefer specificity over adjectivesin 19 of 400, across 10 files
- Respond to all comments on your postsin 18 of 400, across 6 files
- Carry one actual claim per postin 18 of 400, across 9 files
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.