ffmpeg-analyse-video

Extract frames from video files with ffmpeg. Delegate frame reading to sub-agents to preserve the main context window. Synthesise a structured timestamped summary from text-only sub-agent reports.

Problem: Reading dozens of images into the main conversation context consumes most of the context window, leaving little room for synthesis and follow-up.

Images only ever exist inside sub-agent contexts. The main agent only reads lightweight text files. This cuts context usage by 90%.

透過使用 ffmpeg 提取幀並使用 AI 視覺生成帶有時間戳的分步摘要來分析影片內容。當使用者提供影片檔案並想要了解其視覺內容（螢幕錄製、教學課程、簡報、鏡頭或動畫）時使用。觸發「分析此影片」、「此影片中發生了什麼」、「總結此錄音」或任何涉及理解視訊檔案內容的請求。 來源：fabriqaai/ffmpeg-analyse-video-skill。