analyze-video

SKILL.md

Add visual descriptions to audio transcripts by extracting JPG frames with ffmpeg and analyzing them. Never read video files directly - extract frames first.

Videos must have audio transcripts. Run transcribe-audio skill first if needed.

Don't read the audio transcript, just copy it and then prepare it by using the preparevisualscript.rb file. This removes word-level timing data and prettifies the JSON for easier editing:

通过使用 ffmpeg 提取和分析视频帧，向文字记录添加视觉描述。使用视频剪辑的定期视觉描述创建视觉记录。当所有文件都存在音频转录本 (transcript) 但尚未创建视觉转录本 (visual_transcript) 时使用。 来源：barefootford/buttercut。

查看原文