菜单
Work with YouTube videos from the terminal using yt-dlp — fetch metadata, download audio/video, and pull transcripts/subtitles to summarize. Keyless. Use when asked to "summarize this YouTube video", "download audio from", "get the transcript of", or given a YouTube link.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Read and write Airtable bases via the official REST API and the user's personal access token — list/filter records, create, update, delete. Use when asked to "add a row to Airtable", "find records in my base", "update this Airtable record".
Search and retrieve academic papers from arXiv by keyword, author, category, or ID, and read abstracts or full PDFs. Free, keyless. Use when asked to "find papers on", "search arXiv", "summarize this paper", or given an arXiv ID/link.
Render ASCII/terminal art — big text banners (figlet/toilet), colorized output (lolcat), and image-to-ASCII/terminal previews (chafa/jp2a). Keyless, local. Use when asked to "make a banner", "ascii art of", "big text", "show this image in the terminal".
Create, list, and manage calendar events / meetings from the terminal using whatever native CLI is installed (gcalcli for Google Calendar, khal for CalDAV, or AppleScript Calendar on macOS). Use when asked to "schedule a meeting", "create an event", "what's on my calendar", "am I free", "book".
Send and read email from the terminal using whatever native CLI is installed (himalaya, msmtp/mutt/neomutt on Linux, or AppleScript Mail on macOS). Use when asked to "send an email", "email someone", "check my inbox", "read my email", "reply to".
Manage the full GitHub workflow from the terminal — auth, issues, pull request lifecycle (branch/commit/open/CI/merge), code review, and repo management. Uses the gh CLI when present, with a git + REST API fallback. Use when asked to "open a PR", "create an issue", "review this PR", "check CI", "list issues".
| name | youtube |
| description | Work with YouTube videos from the terminal using yt-dlp — fetch metadata, download audio/video, and pull transcripts/subtitles to summarize. Keyless. Use when asked to "summarize this YouTube video", "download audio from", "get the transcript of", or given a YouTube link. |
| allowed-tools | ["@coder","Bash","@webfetch","@read"] |
| triggers | ["youtube","summarize this video","download audio from","get the transcript","transcript of","resumir esse vídeo","baixar áudio de","transcrição do vídeo"] |
Keyless YouTube access via yt-dlp (no API key). Detect: command -v yt-dlp ffmpeg (Unix) /
Get-Command yt-dlp -ErrorAction SilentlyContinue (Windows). Install: brew install yt-dlp ffmpeg
/ pipx install yt-dlp / choco install yt-dlp.
yt-dlp --dump-json --no-warnings "URL" | python3 -c "import sys,json;d=json.load(sys.stdin);print(d['title'],'-',d['uploader'],'-',d['duration_string'])"
yt-dlp --skip-download --write-auto-subs --sub-langs "en,pt" --sub-format vtt -o "%(id)s" "URL"
This writes a .vtt; read it with @read, strip timestamps, and summarize. Prefer manual subs
(--write-subs) when available, auto-subs (--write-auto-subs) otherwise.
yt-dlp -f "bestaudio" -x --audio-format mp3 "URL" # audio only
yt-dlp -f "bv*+ba/b" -o "%(title)s.%(ext)s" "URL" # best video+audio
ffmpeg is required for audio extraction/merging — check it in Step 0.