Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Download videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp. Use when the user provides a video URL and wants to download it, extract audio (MP3), download subtitles, or select video quality. Triggers on phrases like "下载视频", "download video", "yt-dlp", "YouTube", "B站", "抖音", "提取音频", "extract audio".
Download videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp. Use when the user provides a video URL and wants to download it, extract audio (MP3), download subtitles, or select video quality. Triggers on phrases like "下载视频", "download video", "yt-dlp", "YouTube", "B站", "抖音", "提取音频", "extract audio".
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Download videos from thousands of websites using yt-dlp.
Before downloading, verify dependencies are installed: # Check yt-dlp which yt-dlp || echo "yt-dlp not installed. Install with: pip install yt-dlp" # Check ffmpeg (required for audio extraction and format merging) which ffmpeg || echo "ffmpeg not installed. Install with: brew install ffmpeg" If not installed, install them first: pip install yt-dlp brew install ffmpeg # macOS
yt-dlp -P "~/Downloads/yt-dlp" "VIDEO_URL"
YouTube often blocks direct downloads with 403 errors. Always use browser cookies for YouTube: yt-dlp -P "~/Downloads/yt-dlp" --cookies-from-browser chrome "YOUTUBE_URL" Supported browsers: chrome, firefox, safari, edge, brave, opera
yt-dlp -P "/path/to/save" -o "%(title)s.%(ext)s" "VIDEO_URL"
yt-dlp -P "~/Downloads/yt-dlp" "VIDEO_URL"
yt-dlp -P "~/Downloads/yt-dlp" -x --audio-format mp3 "VIDEO_URL"
yt-dlp -P "~/Downloads/yt-dlp" --write-subs --sub-langs all "VIDEO_URL"
720p: yt-dlp -P "~/Downloads/yt-dlp" -f "bestvideo[height<=720]+bestaudio/best[height<=720]" "VIDEO_URL" 1080p: yt-dlp -P "~/Downloads/yt-dlp" -f "bestvideo[height<=1080]+bestaudio/best[height<=1080]" "VIDEO_URL" Best available: yt-dlp -P "~/Downloads/yt-dlp" -f "bestvideo+bestaudio/best" "VIDEO_URL"
yt-dlp -F "VIDEO_URL" Then download specific format by ID: yt-dlp -P "~/Downloads/yt-dlp" -f FORMAT_ID "VIDEO_URL"
# Download entire playlist yt-dlp -P "~/Downloads/yt-dlp" -o "%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s" "PLAYLIST_URL" # Download specific range (e.g., items 1-5) yt-dlp -P "~/Downloads/yt-dlp" -I 1:5 "PLAYLIST_URL"
yt-dlp -P "~/Downloads/yt-dlp" --write-thumbnail "VIDEO_URL"
When user provides a video URL: Identify the platform: YouTube/YouTube Music → Always use --cookies-from-browser chrome Other sites → Try without cookies first Ask what they want (if not specified): Just download the video? Extract audio only? Need subtitles? Specific quality? Construct the command based on requirements Execute the download using Shell tool with required_permissions: ["all", "network"] Handle errors: 403 Forbidden → Retry with --cookies-from-browser Connection issues → yt-dlp auto-resumes, just retry Format unavailable → Use -F to list formats, then select Report the result - file location and any errors
User: "帮我下载这个视频 https://www.youtube.com/watch?v=xxx" Response: # YouTube - use cookies to avoid 403 errors yt-dlp -P "~/Downloads/yt-dlp" --cookies-from-browser chrome "https://www.youtube.com/watch?v=xxx" User: "下载这个视频的音频 https://www.bilibili.com/video/xxx" Response: # Bilibili - extracting audio as MP3 yt-dlp -P "~/Downloads/yt-dlp" -x --audio-format mp3 "https://www.bilibili.com/video/xxx" User: "下载这个 Twitter 视频 https://twitter.com/xxx/status/123" Response: # Twitter/X - direct download usually works yt-dlp -P "~/Downloads/yt-dlp" "https://twitter.com/xxx/status/123"
yt-dlp supports thousands of sites including: YouTube, YouTube Music Bilibili (B站) Twitter/X TikTok, Douyin (抖音) Vimeo Twitch And many more... Full list: https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md
ErrorCauseSolutionHTTP 403 ForbiddenYouTube blocks unauthenticated requestsUse --cookies-from-browser chromeVideo unavailableGeo-restricted or privateUse cookies or VPNDownload interruptedNetwork issuesRetry - yt-dlp auto-resumesFormat not availableRequested format doesn't existUse -F to list formats
pip install yt-dlp
brew install ffmpeg # macOS
This is the most common YouTube error. Always use cookies for YouTube: # Recommended approach for YouTube yt-dlp -P "~/Downloads/yt-dlp" --cookies-from-browser chrome "YOUTUBE_URL" Supported browsers: chrome, firefox, safari, edge, brave, opera
# Try with cookies from browser yt-dlp --cookies-from-browser chrome "VIDEO_URL" # Or use a specific format yt-dlp -F "VIDEO_URL" # List formats first yt-dlp -f FORMAT_ID "VIDEO_URL"
# Update yt-dlp to latest version pip install -U yt-dlp # Force IPv4 (sometimes helps with connection issues) yt-dlp -4 "VIDEO_URL"
YouTube downloads: Always use --cookies-from-browser chrome Large files: yt-dlp auto-resumes, just retry if interrupted Keep yt-dlp updated: pip install -U yt-dlp Check formats first: Use -F before downloading if unsure
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.