youtube-fetch

## Overview This skill retrieves YouTube video content (metadata and transcripts) using yt-dlp. WebFetch does not work reliably for YouTube (dynamic content, SSL issues). yt-dlp is the reliable alternative. **Prerequisite:** `yt-dlp` must be installed (`pip install yt-dlp`). ## Workflow 1. Ensure yt-dlp is available (install if needed): ``` which yt-dlp || pip install yt-dlp ``` 2. Fetch metadata for each video: ``` yt-dlp --skip-download --print '%(title)s|||%(uploader)s|||%(description)s' 'VIDEO_URL' ``` 3. Fetch the auto-generated transcript: ``` mkdir -p /tmp/yt-transcripts yt-dlp --write-auto-sub --skip-download --sub-lang en -o '/tmp/yt-transcripts/%(id)s' 'VIDEO_URL' ``` The transcript lands at `/tmp/yt-transcripts/VIDEO_ID.en.vtt`. 4. Clean the VTT file into plain text (strip timestamps and tags): ``` sed '/^WEBVTT/d;/^Kind:/d;/^Language:/d;/^[0-9][0-9]:[0-9][0-9]/d;/^$/d;s/<[^>]*>//g' /tmp/yt-transcripts/VIDEO_ID.en.vtt | awk '!seen[$0]++' ``` 5. If the transcript is too large to read at once, pipe through `head -N` / `tail -n +N` to read in chunks. 6. If no English auto-subs are available, try without `--sub-lang`: ``` yt-dlp --write-auto-sub --skip-download -o '/tmp/yt-transcripts/%(id)s' 'VIDEO_URL' ``` Then check `ls /tmp/yt-transcripts/VIDEO_ID.*.vtt` for available languages. 7. If SSL errors occur, add `--no-check-certificate`. ## Output Format Present results per video as: ``` ### Video: [Ti...