This takes a video file and gives you a timestamped breakdown of what happens in it. The clever bit is the sub-agent architecture: instead of jamming dozens of frame images into your main context window, it spawns disposable agents that each analyze a batch of 8-10 frames and write text descriptions to markdown files. The main agent only reads those lightweight text files and synthesizes the final timeline, cutting context usage by roughly 90%. Works for screen recordings, tutorials, presentations, whatever. It handles duration intelligently, using scene detection for short videos and keyframe extraction for longer ones, with fallbacks when strategies fail. You need ffmpeg installed locally.
npx skills add https://github.com/fabriqaai/ffmpeg-analyse-video-skill --skill ffmpeg-analyse-video