What it does
A set of Claude Code and Codex skills that turn one or more videos into a finished Chinese narration recap. The steps cover scene detection, speech recognition, visual description, script writing, text-to-speech and ffmpeg assembly. The result can optionally be exported as an editable JianYing or CapCut draft. It needs local ffmpeg and one MiMo key.
Use cases
- 01Turn a long video into a short narrated recap
- 02Generate a Chinese voice-over script from scenes
- 03Export the result as an editable CapCut draft
- 04Recap several videos into one finished clip