youtube-transcript

Extract YouTube video metadata and transcripts into Markdown files.

Updated Jun 16, 2026

Search Tags:#Playwright #youtube #text analysis #transcript extraction #Chromium browser

Ready to run

npx skills add https://github.com/grebbel/ghs-wiki --skill youtube-transcript-grebbel

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: youtube-transcript
Source: https://github.com/grebbel/ghs-wiki/tree/main/.claude/skills/youtube-transcript-skill
Command: npx skills add https://github.com/grebbel/ghs-wiki --skill youtube-transcript-grebbel

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, pyyaml, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the process of extracting transcripts from YouTube videos, enabling easier access to spoken content for analysis, research, and documentation.

Core Features & Use Cases

Automated Transcript Extraction: Extracts metadata and transcript from YouTube videos.
Custom Output: Saves the transcript as a Markdown file with YAML front-matter for easy integration into existing documents.
Use Case: Ideal for academic researchers, content creators, or anyone who needs to access and process spoken content quickly and efficiently.

Quick Start

Use the "youtube-transcript" skill to extract the transcript from a YouTube video by providing its URL.

Frequently Asked Questions about youtube-transcript

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

FAQPage Schema

How do I extract auto-generated transcripts from YouTube videos for text analysis?▼

You can extract auto-generated transcripts by using Playwright to drive a Chromium browser and retrieve the video's spoken content. This process captures both metadata and transcript text, saving the output as structured Markdown files for automated analysis.

Does YouTube transcript extraction require Playwright and a Chromium browser to run?▼

Yes, YouTube transcript extraction requires Playwright and PyYAML to function properly. Playwright drives the Chromium browser to access the video page and capture the auto-generated transcript, while PyYAML formats the extracted metadata into structured Markdown.

What is the best way to save YouTube video transcripts as Markdown files with YAML front-matter?▼

The best way to save YouTube transcripts as Markdown files with YAML front-matter is to automate the extraction process using a browser automation tool. This captures video metadata and spoken content, structuring them directly into a formatted Markdown document for research.

Can I automate YouTube transcript extraction for academic research and documentation?▼

Yes, you can automate YouTube transcript extraction to streamline academic research and documentation. By driving a Chromium browser with Playwright, the system automatically retrieves spoken video content and metadata, generating structured Markdown files for immediate analysis.

Are there limitations when extracting YouTube transcripts using browser automation?▼

Limitations of browser-based transcript extraction include reliance on auto-generated captions and the need for a running Chromium environment. If a video lacks auto-generated transcripts, the Playwright automation will not be able to extract the spoken content.

How do YouTube transcript extraction tools format metadata into structured Markdown files?▼

YouTube transcript extraction tools format metadata into structured Markdown by capturing video details and spoken content via Playwright, then using PyYAML to generate YAML front-matter. This creates a standardized Markdown document ready for integration into existing research workflows.