SKILL · MIT

video-subtitle

<用户自制> 视频字幕：提取 YouTube 与 Bilibili 的字幕并依据实际读到的讲话文本作答。 Retrieve exact subtitle tracks and read scoped spoken evidence when an answer materially depends on a YouTube or Bilibili video and usable authoritative text is absent. A video URL alone does not trigger this capability.

GitHub source

When to use it

Analyze speech in YouTube or Bilibili videos. Retrieval needs yt-dlp.

“Use this Skill for my task, first checking the companion methods and actual tools it needs.”

What is included

Includes the method and configuration guidance. The package README specifies resources, scripts, companion Skills, and external tools. Install relevant companions and bind your own environment.

Ask naturally; if the client supports explicit invocation, select video-subtitle。The client’s existing authority, authentication, and tool boundaries remain in force.