Youtube

This pulls YouTube captions without needing an API key or downloading audio files, which makes it fast and dead simple for transcript extraction. It triggers automatically when you pass in a YouTube URL (regular, shortened, or YouTube Kids). The main catch is it only works when captions exist, either auto-generated or manual, so you'll hit skips on videos without them. You can also combine it with web search to ingest multiple videos at once by searching "youtube Moore's Law" and it'll process whatever comes back. Built on youtube-transcript-api and licensed AGPL-3.0.

GitHub stars: 452
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add axoviq-ai/synthadoc --skill youtube --agent claude-code

Installs into .claude/skills of the current project.

Files

YouTube Skill

Extracts the transcript (captions) from a YouTube video using the YouTube caption system — no API key or audio download required. Optionally uses a vision-capable LLM to produce a structured summary (Overview, Topics, Key takeaways) before the raw transcript.

Setup

pip install youtube-transcript-api

Standalone usage

Transcript only (no LLM required):

import asyncio
from synthadoc.skills.youtube.scripts.main import YoutubeSkill

skill = YoutubeSkill()          # no provider — returns raw timestamped transcript

async def main():
    result = await skill.extract("https://www.youtube.com/watch?v=dQw4w9WgXcQ")
    print(result.text)          # "[0:00] text [0:04] text ..."
    print(result.metadata)      # {"video_id": "...", "title": "...", "url": "..."}

asyncio.run(main())

With LLM summarization (pass any provider that implements complete()):

skill = YoutubeSkill(provider=my_provider)
result = await skill.extract(url)
# result.text contains:
#   ## Executive Summary
#   <Overview / Topics / Key takeaways>
#
#   ## Transcript
#   [0:00] ...

SKILL.md on GitHub