Skill

scenelens

Watch a video (URL or local path). Picks frames at scene changes, OCRs each frame so on-screen text is read as text not pixels, pulls a timestamped transcript (captions or Whisper, auto-chunked for long audio), and hands it all to Claude.

Claim this listing

Connect your GitHub to prove you own or maintain this listing. We verify repo access automatically — most publishers are confirmed in seconds.

1Connect GitHub

2Submit your claim

3Auto-verified, or reviewed within 48h