Youtube Transcribe Skill

Pulls transcripts from YouTube videos and saves them as plain text files. It tries yt-dlp first for speed, handling cookies and multiple subtitle languages (Chinese and English), then falls back to browser automation with Chrome DevTools MCP if the CLI fails. The browser path is thorough but slow, it clicks through the description dropdown to find the transcript button, then extracts content via DOM scripting to avoid accessibility tree overhead. Nice touch that it converts VTT and SRT files into clean timestamp-plus-text format. If you're doing research, content analysis, or just need searchable video content, this handles the annoying parts. Works best if you already have yt-dlp installed.

skills.sh installs: 358
GitHub stars: 1.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add feiskyer/claude-code-settings --skill youtube-transcribe-skill --agent claude-code

Installs into .claude/skills of the current project.

Files

YouTube Transcript Extraction

Extract subtitles/transcripts from a YouTube video URL and save them as a local file.

Input YouTube URL: $ARGUMENTS

Step 1: Verify URL

Confirm the input is a valid YouTube URL (supports youtube.com/watch?v=, youtu.be/, and youtube.com/shorts/ formats). If no URL is provided via arguments, check the conversation context for a YouTube link.

Step 2: CLI Quick Extraction (Priority Attempt)

Use command-line tools to quickly extract subtitles.

2.1 Check Tool Availability

Execute which yt-dlp.

If yt-dlp is found, proceed to 2.2.
If yt-dlp is not found, skip to Step 3.

2.2 Get Video Title

yt-dlp --cookies-from-browser=chrome --get-title "[VIDEO_URL]"

Tip: Always add --cookies-from-browser to avoid sign-in restrictions. Default to chrome.
If it fails with a browser error (e.g., "Could not open Chrome"), ask the user to specify their available browser (e.g., firefox, safari, edge) and retry.