What problem does it solve? Understanding what a video contains normally requires watching it manually or sending it to a cloud API. This Skill analyzes video content entirely locally by extracting representative frames and transcribing the audio track, producing structured JSON output without any API keys. ## Core Features & Use Cases - Frame Extraction: Pull key frames using scene-change detection, codec keyframes, or fixed intervals, with automatic subsampling to a configurable frame limit. - Local Audio Transcription: Transcribe speech with openai-whisper (Python package or CLI), with selectable model sizes from tiny to large. - Structured JSON Output: Get video metadata, frame paths with timestamps, and transcript segments in a documented schema for downstream analysis. - Use Case: Given a screen recording of a bug report, extract scene-change frames and the narrator's transcript so an AI agent can visually inspect the frames and explain what happens in the video. ## Quick Start Analyze the video file demo.mp4 by extracting its key frames and transcribing its audio, then summarize what the video contains.
