yt-summary

Fetch YouTube transcripts or extract local audio text and summarize key takeaways.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/jpratt9/dotfiles --skill yt-summary-jpratt9
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: yt-summary
Source: https://github.com/jpratt9/dotfiles/tree/main/.agents/skills/yt-summary
Command: npx skills add https://github.com/jpratt9/dotfiles --skill yt-summary-jpratt9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, python, groq-whisper, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

Extracts and summarizes video content from YouTube transcripts and local audio/video files to quickly get the main points.

Core Features & Use Cases

  • YouTube Video Summarization: Summarizes the content of a YouTube video transcript into a readable summary.
  • Local File Transcription & Summary: Extracts text from local video/audio files, summarizes it, and presents the summary with key takeaways.
  • Use Case: Need to understand the content of a long video but don't have the time to watch it. Use this skill to get a quick summary of the main points and key insights.

Quick Start

Fetch a summary for the YouTube video at 'https://www.youtube.com/watch?v=video-id'.

Frequently Asked Questions about yt-summary

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

FAQPage Schema
How do I summarize a YouTube video from its URL?

To summarize a YouTube video, fetch the video transcript using yt-dlp and process the text with Python to produce a concise summary with key takeaways. This extracts the main points without watching the entire video.

Can I transcribe and summarize local video and audio files?

Yes, you can transcribe local video and audio files using automatic speech recognition with Groq Whisper. The extracted text is then processed to generate a summary highlighting the main points and key insights.

Does this approach require subtitles to extract text from videos?

No, subtitle extraction is not strictly required. If subtitles are unavailable, the skill uses Groq Whisper for automatic speech recognition to extract text from the video or audio file for summarization.

What is the best way to get key takeaways from long educational videos?

The best way to get key takeaways from long videos is to extract the transcript or audio and process it with text summarization. This produces a concise summary of the main points, ideal for time-constrained use cases.

Do I need Python and yt-dlp to extract video metadata for summarization?

Yes, you need Python and yt-dlp installed. yt-dlp fetches the video metadata and transcripts, while Python handles the text processing and summarization logic to deliver the final output.

Are there limitations when summarizing videos without existing transcripts?

Summarizing videos without existing transcripts relies on automatic speech recognition via Groq Whisper, which may introduce transcription inaccuracies. The final summary quality depends heavily on the clarity of the extracted audio.