youtube-fetcher

Convert YouTube video transcripts into structured Markdown files with metadata.

195|15|Updated Mar 4, 2026

Search Tags:#note-taking #markdown #knowledge management #youtube #transcription

Ready to run

npx skills add https://github.com/JimmySadek/youtube-fetcher-to-markdown --skill youtube-fetcher

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: youtube-fetcher
Source: https://github.com/JimmySadek/youtube-fetcher-to-markdown/tree/main
Command: npx skills add https://github.com/JimmySadek/youtube-fetcher-to-markdown --skill youtube-fetcher

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires youtube-transcript-api, requests, yt-dlp, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of manually transcribing YouTube video content, offering an automated solution to convert video transcripts into structured Markdown files for efficient note-taking and knowledge management.

Core Features & Use Cases

Automated Transcription: Converts YouTube video transcripts into Markdown files with YAML frontmatter, enriching them with metadata and timestamps.
Structured Markdown: Outputs transcripts in a structured format compatible with note-taking apps like Obsidian, Logseq, and Markdown editors.
Use Case: For users who want to create a knowledge base from YouTube content, this Skill provides a streamlined process to extract transcripts, video details, and chapters into a usable format.

Quick Start

Run the skill with the command: python3 ~/.config/skillshare/skills/youtube-fetcher/scripts/fetch_transcript.py "https://www.youtube.com/watch?v=VIDEO_ID"

Frequently Asked Questions about youtube-fetcher

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

FAQPage Schema

How do I convert a YouTube video transcript to Markdown?▼

You can convert a YouTube video transcript to Markdown by executing the fetch_transcript.py script with the video URL as an argument. This automatically generates a structured Markdown file featuring YAML frontmatter, chapters, and timestamps for knowledge management.

What's the best way to extract YouTube transcripts for Obsidian and Logseq?▼

Extracting YouTube transcripts for Obsidian and Logseq is best done by generating structured Markdown with YAML frontmatter and embedded metadata. This format is natively compatible with these note-taking apps, allowing you to directly import the video details and chapters.

Do I need yt-dlp and youtube-transcript-api to fetch video metadata and captions?▼

Yes, you need yt-dlp and youtube-transcript-api to fetch video metadata and captions. The Skill explicitly requires yt-dlp for extracting video details and chapters, and youtube-transcript-api for retrieving the actual captions.

Can I automate YouTube transcription for a personal knowledge base?▼

You can automate YouTube transcription for a personal knowledge base by using a script that fetches captions and video metadata. This converts video content into structured Markdown files enriched with timestamps, streamlining content organization and retrieval.

Why does my YouTube video transcript output lack chapter timestamps?▼

Your YouTube video transcript output may lack chapter timestamps if the video creator has not added native chapters to the video. The extraction process relies on yt-dlp to pull existing chapter metadata, so unchaptered videos will not contain this structured data.