Skip to main content
Run any Skill in Manus
with one click

read-any-video

Stars2
Forks0
UpdatedJune 26, 2026 at 02:33

LLM 读不了视频 —— 本 skill 帧间差分分析 把视频拆成模型能读的关键帧 + 带时间戳的运动时间线, 让模型得以描述、总结、定位视频中的任意瞬间。 触发场景:提供视频文件 / URL(.mp4/.mov/.avi/gif 等) Give LLMs eyes for video: extract key frames + a timestamped motion timeline so the model can describe, summarize, or locate moments in a video.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

SKILL.md
readonly