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.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
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.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
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.