You don't have a video input; this skill gives you one. Anything a user hands you — a YouTube link, a TikTok, a lecture, a meeting recording, a screen capture, an .mp4 on disk — goes through the same pipeline: frames (scene-aware, deduplicated), OCR, transcript (captions first, local Whisper offline fallback), all persisted into one index.

watch-skill list

If the video was already analyzed — this session or any earlier one — do NOT watch it again. Ask it directly (see the skill):

watch-skill ask <video_id> "<question>"

watch-skill watch "<url-or-path>" [--start T --end T] [--max-frames N] [--transcript-only]

The report prints , frames with timestamps, OCR text, and the transcript. Read every frame path listed — in a single message, parallel Read calls — then answer from frames + OCR

watch-skill batch "<playlist-url-or-folder>" [--limit N]

Everything lands in the same index; one broken video never stops the rest. Afterwards a single spans the whole batch.

If any command fails with a dependency error, run once — it installs missing ffmpeg/yt-dlp itself. No API key is required for any of this; transcription is local by default and the video file never leaves the machine.