YouTube 內容擷取技能

Extract metadata and transcripts from public YouTube videos for downstream analysis.

Updated Dec 9, 2025
One-click install
npx skills add https://github.com/bohachu/silicon-valley-flow --skill youtube
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: YouTube 內容擷取技能
Source: https://github.com/bohachu/silicon-valley-flow/tree/main/.claude/skills/YouTube內容擷取技能
Command: npx skills add https://github.com/bohachu/silicon-valley-flow --skill youtube

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @distube/ytdl-core, @danielxceron/youtube-transcript, and includes scripts (resource) components.

What problem does it solve?

YouTube 影片內容往往包含豐富的資訊與論點,但手動提取、整理與摘要耗時且易遺漏重點。本 Skill 自動擷取影片標題、描述、字幕,以及元資料,並可進一步整合成簡報或內容。

Core Features & Use Cases

  • 自動內容擷取:抓取影片標題、描述、頻道作者與時長等元資料。
  • 字幕與轉錄:取得完整字幕/轉錄文本,方便後續分析與摘要。
  • 元資料分析與整合:提供關鍵字與要點,支援快速產出摘要或簡報內容。

Quick Start

使用 YouTube URL 執行擷取,即可取得影片元資料與字幕,必要時再將結果交給其他技能生成簡報。

Frequently Asked Questions about YouTube 內容擷取技能

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract YouTube video transcripts and metadata automatically?

This Skill extracts complete transcripts and metadata (title, description, author, duration, view count, publish date) from public YouTube videos using @distube/ytdl-core for metadata and @danielxceron/youtube-transcript for subtitles, enabling downstream summarization and content analysis without manual copying.

Can I use YouTube transcripts to generate summaries and slides automatically?

Yes. This Skill retrieves full video transcripts and metadata, which you can pipe to downstream Skills for automatic summarization and slide generation, eliminating manual content extraction and enabling rapid content repurposing workflows.

What are the requirements to extract content from YouTube videos?

You need Node.js 18+, network access to reach YouTube, and the dependencies @distube/ytdl-core and @danielxceron/youtube-transcript installed. The Skill works on public YouTube videos and outputs metadata and transcripts in JSON format when the --json flag is used.

How does YouTube transcript extraction compare to manual transcription?

Automated transcript extraction via @danielxceron/youtube-transcript retrieves subtitles and captions instantly at scale, whereas manual transcription is time-intensive and error-prone; this Skill automates the retrieval to focus your effort on analysis and summarization instead.

What happens if a YouTube video doesn't have subtitles or transcripts available?

The Skill still extracts metadata (title, description, author, duration, view count, publish date) even when subtitles are unavailable. If no transcript exists, you receive the metadata alone; availability depends on whether the video owner provided captions or auto-generated subtitles.

Can I export YouTube metadata and transcripts in JSON format for further processing?

Yes. Use the --json flag to output extracted metadata and transcripts in JSON format, enabling seamless integration with downstream analysis tools, summarization Skills, or presentation-generation workflows.