Agent Skills › sdyckjq-lab/llm-wiki-skill › youtube-transcript

youtube-transcript

GitHub

从YouTube视频提取字幕或转录文本。支持指定URL、视频ID及时间戳格式，自动处理段落整理与文件保存，适用于需要获取视频文字内容的场景。

deps/youtube-transcript/SKILL.md sdyckjq-lab/llm-wiki-skill

Trigger Scenarios

用户请求YouTube视频的转录本、字幕或 captions 用户提供 YouTube URL 并要求提取内容

Install

npx skills add sdyckjq-lab/llm-wiki-skill --skill youtube-transcript -g -y

More Options

Non-standard path

npx skills add https://github.com/sdyckjq-lab/llm-wiki-skill/tree/main/deps/youtube-transcript -g -y

Use without installing

npx skills use sdyckjq-lab/llm-wiki-skill@youtube-transcript

指定 Agent (Claude Code)

npx skills add sdyckjq-lab/llm-wiki-skill --skill youtube-transcript -a claude-code -g -y

安装 repo 全部 skill

npx skills add sdyckjq-lab/llm-wiki-skill --all -g -y

预览 repo 内 skill

npx skills add sdyckjq-lab/llm-wiki-skill --list

SKILL.md

Frontmatter

{
    "name": "youtube-transcript",
    "description": "Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com\/watch?v=, youtu.be\/, or similar). Supports output with or without timestamps."
}

YouTube Transcript

Extract transcripts from YouTube videos using the youtube-transcript-api.

Usage

Run the script with a YouTube URL or video ID:

uv run scripts/get_transcript.py "VIDEO_URL_OR_ID"

With timestamps:

uv run scripts/get_transcript.py "VIDEO_URL_OR_ID" --timestamps

Defaults

Without timestamps (default): Plain text, one line per caption segment
With timestamps: [MM:SS] text format (or [HH:MM:SS] for longer videos)

Supported URL Formats

https://www.youtube.com/watch?v=VIDEO_ID
https://youtu.be/VIDEO_ID
https://youtube.com/embed/VIDEO_ID
Raw video ID (11 characters)

Output

CRITICAL: YOU MUST NEVER MODIFY THE RETURNED TRANSCRIPT
If the transcript is without timestamps, you SHOULD clean it up so that it is arranged by complete paragraphs and the lines don't cut in the middle of sentences.
If you were asked to save the transcript to a specific file, save it to the requested file.
If no output file was specified, use the YouTube video ID with a -transcript.txt suffix.