Download videos and audio from 1500+ websites including YouTube, Bilibili, TikTok, Twitter/X, Instagram, Vimeo, and more using yt-dlp. Use when the user wants to download videos, save media from social platforms, download with specific resolution (720p/1080p/4K), get subtitles, or download entire playlists. Triggers on requests like 'download this video', 'save this YouTube video', 'download in 1080p', 'download with subtitles', 'download this playlist'.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Download video/audio from 1500+ websites using yt-dlp. Supports format selection, subtitles, playlists, and custom output naming.
# Basic download (best quality)
yt-dlp "URL"
# Specific resolution
yt-dlp -f "bestvideo[height<=1080]+bestaudio/best[height<=1080]" "URL"
# With subtitles
yt-dlp --write-subs --sub-langs "en,zh" "URL"
# Audio only
yt-dlp -f "bestaudio" "URL"
| Request | Command |
|---|---|
| Best quality | -f "bestvideo+bestaudio/best" |
| 4K | -f "bestvideo[height<=2160]+bestaudio/best" |
| 1080p | -f "bestvideo[height<=1080]+bestaudio/best" |
| 720p | -f "bestvideo[height<=720]+bestaudio/best" |
| 480p | -f "bestvideo[height<=480]+bestaudio/best" |
yt-dlp -F "URL" # Show all formats with codes
# Prefer MP4 container
yt-dlp -f "bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best" "URL"
# Specific format code (from -F output)
yt-dlp -f 137+140 "URL"
# Merge to specific container
yt-dlp --merge-output-format mkv "URL"
# Manual subtitles (human-created)
yt-dlp --write-subs --sub-langs "en,zh,ja" "URL"
# Auto-generated subtitles
yt-dlp --write-auto-subs --sub-langs "en" "URL"
# Both manual and auto
yt-dlp --write-subs --write-auto-subs --sub-langs "en,zh" "URL"
# Embed subtitles in video (MP4/MKV/WebM)
yt-dlp --write-subs --embed-subs "URL"
yt-dlp --list-subs "URL"
# Convert to SRT
yt-dlp --write-subs --sub-format srt "URL"
# Available: srt, ass, vtt, lrc
| Variable | Description | Example |
|---|---|---|
%(title)s | Video title | My Video |
%(id)s | Video ID | dQw4w9WgXcQ |
%(ext)s | File extension | mp4 |
%(upload_date)s | Upload date | 20231215 |
%(uploader)s | Channel name | Rick Astley |
%(playlist)s | Playlist name | Best Songs |
%(playlist_index)s | Position in playlist | 01 |
%(resolution)s | Video resolution | 1920x1080 |
# Default: title + extension
yt-dlp -o "%(title)s.%(ext)s" "URL"
# Date prefix
yt-dlp -o "%(upload_date)s - %(title)s.%(ext)s" "URL"
# Organized by uploader
yt-dlp -o "%(uploader)s/%(title)s.%(ext)s" "URL"
# Playlist with numbering
yt-dlp -o "%(playlist)s/%(playlist_index)02d - %(title)s.%(ext)s" "URL"
# Sanitize title (remove special chars)
yt-dlp -o "%(title).100B.%(ext)s" "URL" # Limit to 100 bytes
# Download entire playlist
yt-dlp "PLAYLIST_URL"
# Only video (not playlist)
yt-dlp --no-playlist "URL"
# Specific items (1-indexed)
yt-dlp -I 1:5 "PLAYLIST_URL" # First 5
yt-dlp -I 1,3,5 "PLAYLIST_URL" # Items 1, 3, 5
yt-dlp -I -3: "PLAYLIST_URL" # Last 3
# Skip already downloaded
yt-dlp --download-archive downloaded.txt "PLAYLIST_URL"
--cookies-from-browser for premium content--write-subs --sub-langs "zh-Hans"--cookies-from-browser for private content--cookies-from-browser firefox or --cookies cookies.txt# Browser cookies (recommended)
yt-dlp --cookies-from-browser firefox "URL"
yt-dlp --cookies-from-browser chrome "URL"
# Cookie file
yt-dlp --cookies cookies.txt "URL"
# Username/password (limited support)
yt-dlp -u USERNAME -p PASSWORD "URL"
| Issue | Solution |
|---|---|
| "Video unavailable" | Try --cookies-from-browser |
| Slow download | Add --concurrent-fragments 4 |
| Format merge fails | Install ffmpeg |
| Geo-blocked | Use --geo-bypass or proxy |
yt-dlp -U # Update to latest stable
Download YouTube video in 1080p with Chinese subtitles:
yt-dlp -f "bestvideo[height<=1080]+bestaudio/best" \
--write-subs --sub-langs "zh" \
-o "%(title)s.%(ext)s" \
"https://youtube.com/watch?v=..."
Download TikTok video:
yt-dlp -o "%(uploader)s - %(title)s.%(ext)s" \
"https://tiktok.com/@user/video/..."
Download Bilibili playlist:
yt-dlp --cookies-from-browser chrome \
-o "%(playlist)s/%(playlist_index)02d - %(title)s.%(ext)s" \
"https://bilibili.com/video/BV..."
Download Twitter video:
yt-dlp --cookies-from-browser firefox \
"https://twitter.com/user/status/..."
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Web search using curl + multiple search engines (Baidu, Google, Bing, DuckDuckGo). Activates when user asks to search, look up, or query something online. Includes security enhancements: input sanitization, command injection protection, and URL encoding.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
日本語の概要は準備中です。原文の説明を表示しています。
Play board games on ShellGames.ai — Chess, Poker, Ludo, Tycoon, Memory, and Spymaster. Use when the agent wants to play games against humans or other AI agents, join tournaments, chat with players, check leaderboards, or manage a ShellGames account. Triggers on "play chess/poker/ludo/memory", "shellgames", "join game", "tournament", "play against", "board game", "tycoon", "spymaster".
日本語の概要は準備中です。原文の説明を表示しています。
Find the most relevant external agent skills for the current task, then submit grounded feedback about which skills were actually used and useful in the same session. Whenever you start a task, use this skill first.
日本語の概要は準備中です。原文の説明を表示しています。
Use when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
日本語の概要は準備中です。原文の説明を表示しています。