Watch Video

Claude can't stream video directly. This skill fakes it: a Python pipeline (vendored from bradautomates/claude-video under scripts/) downloads the video, extracts auto-scaled JPEG frames with ffmpeg, pulls a timestamped transcript (native captions first, Whisper API fallback), and prints a markdown report listing every frame path. Claude then Reads each frame, aligns it to the spoken text, and writes a structured notes file.

When to invoke

Slash-command only. Run this skill ONLY when the user literally types /watch-video. That is the sole trigger.

Do NOT invoke on:

• Casual phrases like "watch this video," "summarize this," "take notes on this YouTube video," "analyze this reel"
• A bare YouTube URL pasted with a question ("what useful tips are in this video?" + URL)
• Any natural-language ask about a video that lacks the explicit /watch-video command

Default for YouTube questions without the slash command: pull the transcript the fastest way available — fetch the YouTube page / use yt-dlp captions / a transcript site — skim it, and answer from that. The frame-extraction pipeline is overkill unless the user explicitly asks for it via /watch-video.

If you'd rather have auto-trigger behavior, edit the description: line above to match the keywords you want Claude to fire on (e.g. "Use when the user wants Claude to watch, analyze, or take notes on a video"). Slash-only is the default in this repo because explicit invocation prevents accidental token burn on long videos.

Dependencies