Youtube Agent Skill
Extract transcripts from YouTube videos via the YouTube caption system
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/axoviq-ai/synthadoc --skill youtubeThe instruction itself
5 sections, as written by the authorYouTube 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] ...
The provider must implement:
async def complete(messages, system=None, temperature=0.0, max_tokens=4096)
-> object with .text (str), .input_tokens (int), .output_tokens (int)
Message (used to build the messages list) is importable from
synthadoc.skills.base:
from synthadoc.skills.base import Message
When this skill is used
- Source starts with
https://www.youtube.com/,https://youtu.be/, or
https://www.youtubekids.com/
To search YouTube by topic instead of ingesting a specific URL, use the web
search skill — it filters Tavily results to YouTube domains automatically:
synthadoc ingest "youtube Moore's Law"
synthadoc ingest "youtube kids: Sesame Street"
synthadoc ingest "search for youtube: history of computing"
Limitations
- Only works for videos that have captions (auto-generated or manually added).
If no captions are available the source is skipped with a warning.
- Private or deleted videos are skipped gracefully.
Other skills for the same job
different authors, same section of the catalogue
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
How to use it
Take axoviq-ai/youtube from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.