← ClaudeAtlas

video-noteslisted

Turn a narrated screen recording, a product demo or any video the user points at into a timestamped, numbered punch list with stills, all on this machine. Use when the user says "check the video file", "I left feedback as a video", "I recorded feedback", "watch this video", "analyze this demo", or drops a .mov, .mp4 or .webm path.
weeeha/video-notes · ★ 0 · Code & Development · score 70
Install: claude install-skill weeeha/video-notes
# Video Notes The user records feedback as a screen recording while talking through it: one pass, a few minutes, often repeating a point when the cursor lags. The deliverable is a punch list another session can execute without watching the video. Whisper and ffmpeg run locally; no video or audio is sent to a cloud speech or vision API. ## Steps 1. **Run the helper** (it sits next to this file). ```bash python3 "<this skill's folder>/video-notes.py" "<video>" ``` It reuses `<video>.srt` when one sits next to the file, otherwise runs `whisper --model base.en` on CPU (about 2.5 min per 5 min of video on an Apple Silicon laptop). Output lands in `<stem>.notes/`: `transcript.md` (one row per merged segment with a frame name) and 1600px stills. When `<stem>.notes/` is already newer than the video it is reused as is; `--force` rebuilds, `--model turbo` when the base transcript is garbled, `--every 10` for a demo with no narration, `--sheet` for 2x2 contact sheets, `--max-row 5` for more frames when talk and screen move fast (rows are capped at 8 s, one frame per row), `--max-frames 40` default. 2. **Read `transcript.md`, then the frames.** With `--sheet`, skim `sheet_NN.jpg` first (four frames per read; tiles run left to right, top to bottom, in frame order, so sheet 01 holds frames 1 to 4 and its top-left tile is the earliest), then read the single frame for every row whose words point at the screen ("this area", "here", "these two icons")