highlight-scanner
Combined analysis skill to find viral-worthy highlights from videos. Scans transcripts, detects laughter, analyzes sentiment/emotion, and uses scene changes to identify the most engaging moments for TikTok/Shorts/Reels. Produces ranked list of highlight segments with virality scores.
npx skills add majiayu000/claude-skill-registry --skill highlight-scanner --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Highlight Scanner This skill combines all detection methods to find viral-worthy highlights from videos. It's the core analysis component for the autocut-shorts workflow. ## When to Use - User wants to find the best moments from a video - Identifying viral-worthy segments for short-form content - Creating highlight reels from long videos - Analyzing podcast, vlog, gaming, or tutorial content - Preparing content for autocut workflow ## Detection Signals ### 1. Transcript Analysis - Identifies hooks and attention-grabbing phrases - Detects story beats and important points - Finds question/answer patterns - Keyword matching for viral phrases ### 2. Laughter Detection - Finds humorous moments - Detects audience reactions - Identifies funny segments ### 3. Sentiment/Emotion Analysis - Positive emotions (excitement, joy) - Surprise moments - Negative emotions (controversy, drama) - Emotional peaks and intensity ### 4. Scene Detection - Scene changes as natural cut points - Topic transitions - Visual changes ## Scoring System Each highlight is scored based on: ```python virality_score = ( transcript_score * 0.35 + laughter_score * 0.25 + sentiment_score * 0.25 + scene_score * 0.15 ) ```
- When to Use
- Detection Signals
- 1. Transcript Analysis
- 2. Laughter Detection
- 3. Sentiment/Emotion Analysis
- 4. Scene Detection
- Scoring System
- Available Scripts
- scripts/findhighlights.py
- scripts/analyzeviralpotential.py
- Output Format
- Scoring Weights
- Viral Phrases/Keywords
- High-Viral Potential Phrases
python skills/highlight-scanner/scripts/find_highlights.py <video_path> [options] python skills/highlight-scanner/scripts/find_highlights.py video.mp4 --transcript-path video.srt python skills/highlight-scanner/scripts/find_highlights.py video.mp4 \ python skills/highlight-scanner/scripts/analyze_viral_potential.py <video_path> [options] python skills/highlight-scanner/scripts/analyze_viral_potential.py video.mp4 --transcript-path video.srt
What does the highlight-scanner skill do?
Combined analysis skill to find viral-worthy highlights from videos. Scans transcripts, detects laughter, analyzes sentiment/emotion, and uses scene changes to identify the most engaging moments for TikTok/Shorts/Reels. Produces ranked list of highlight segments with virality scores.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill highlight-scanner --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.