Breaks down videos into component frames and narration through scene-detection-based keyframe extraction, audio transcription via OpenAI Whisper, and per-frame visual analysis using Claude Vision. Produces shot-by-shot storyboard output and computes 8-field stylistic fingerprints covering rendering class, world type, character strategy, narrative structure, and more.
Cognium trust score
84%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-19.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.