skills/find-golden-segments/SKILL.md
Find naturally clean, coherent video segments worth keeping (selection over repair)
npx skillsauth add nuva-lab/vibecut find-golden-segmentsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to identify the best moments in raw footage - segments that are already clean and don't need repair.
Selection over Repair: Instead of trying to fix broken footage by cutting out fillers, find the moments that are naturally good.
python skills/find-golden-segments/find_golden.py <video_path>
# Examples
python skills/find-golden-segments/find_golden.py video.MOV
python skills/find-golden-segments/find_golden.py video.MOV --min-duration 15
{
"golden_segments": [
{
"start": "02:15",
"end": "02:38",
"duration_sec": 23,
"score": 9,
"speaker": "Speaker Name",
"topic": "Brief topic",
"quote_preview": "First few words...",
"quality_notes": "Why this segment is good"
}
],
"summary": {
"total_duration": 140,
"golden_duration": 45,
"segments_found": 3
}
}
Only segments scoring 7/10 or higher are included. Lower-quality sections are skipped entirely.
tools
Generate voiceover scripts in Joyce's style for video clips
tools
Clone a voice using qwen3-tts and generate speech from text
development
# Validate Media Skill Pre-flight media validation and diagnostics using ffprobe. ## Purpose Check video/audio files for common issues before rendering: - Duration mismatches between video and audio tracks - Missing audio tracks - Codec compatibility - Volume levels - Potential freeze points ## Usage ```bash python skills/validate-media/validate.py <video_file> [--verbose] ``` ## Output JSON report with issues and recommendations: ```json { "file": "video.mp4", "video_duration": 35.1
tools
Transcribe a video clip using Gemini to get timestamped segments for captions