Use this skill to cut long static sections from screen recordings without spending tokens on video inspection. Prefer the bundled local script over manually reading screenshots or sampling video frames into the conversation.
Default policy:
ffmpeg, Pillow, and numpy15 seconds of low visual change as idle5 seconds before and after every removed static sectionUse this skill when the user wants to:
Do not use it for cinematic footage, scene-change editing, highlight detection, audio-based silence removal, or content-aware storytelling cuts.
python3 scripts/screen_idle_cutter.py input.mp4 --output output.mp4 --dry-run --report report.json --segments segments.txt
python3 scripts/screen_idle_cutter.py input.mp4 --output output.mp4 --report report.json --segments segments.txt
--min-static-seconds, lower --sample-fps, or higher --diff-threshold. If it misses obvious pauses, lower --diff-threshold or --min-static-seconds.python3 scripts/screen_idle_cutter.py input.mp4 --output output.mp4
Useful options:
--min-static-seconds 15
--guard-seconds 5
--sample-fps 1
--diff-threshold auto
--dry-run
--report report.json
--segments segments.txt
--dry-run for irreplaceable videos before rendering.The script should create:
--output unless --dry-run is set--report when requested--segments when requestedThe report includes parameters, source duration, detected static spans, removed spans, kept spans, and estimated saved duration.
共 1 个版本