watch-video

Extract text and visual data from video content using Python scripts.

51|3|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/Newuxtreme/watch-video-skill --skill watch-video-newuxtreme
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: watch-video
Source: https://github.com/Newuxtreme/watch-video-skill/tree/main
Command: npx skills add https://github.com/Newuxtreme/watch-video-skill --skill watch-video-newuxtreme

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, ffmpeg, ffprobe, whisper, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill transforms video content into structured notes, enabling you to quickly capture and review key information from videos.

Core Features & Use Cases

  • Video Transcription: Extracts time-synced transcripts from video content.

  • Frame Extraction: Generates still frames from videos to provide visual context.

  • Summary Creation: Produces structured markdown notes including summaries, timelines, and key quotes.

  • Use Case: Suppose you need to review a complex tutorial video. Use this Skill to generate a summary and notes, making it easier to understand and recall the content.

Quick Start

Use the /watch-video command followed by a YouTube URL or a path to a local video file to generate structured notes from the video.

Frequently Asked Questions about watch-video

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

FAQPage Schema
How do I generate structured notes from a YouTube video?

To generate structured notes from a YouTube video, use a tool that extracts text and visual data. This Skill produces time-synced transcripts, extracted frames, and markdown summaries directly from YouTube URLs.

Can I transcribe local video files into markdown summaries?

Yes, you can transcribe local video files into markdown summaries. The Skill processes local video paths to create structured notes, including timelines and key quotes, using Python scripts.

What libraries do I need for video transcription and frame extraction?

You need yt-dlp, ffmpeg, ffprobe, and whisper libraries for video transcription and frame extraction. These dependencies handle video downloading, processing, and speech-to-text conversion.

How does frame extraction work for instructional videos?

Frame extraction for instructional videos works by generating still frames from the content to provide visual context. These frames are extracted using Python scripts and integrated into the final structured notes.

What is the best way to summarize educational video content?

The best way to summarize educational video content is using automated transcription and frame extraction. This approach produces structured markdown notes with summaries, timelines, and key quotes for easy review.

Does this video transcription approach work for technical documentation?

Yes, this video transcription approach works for technical documentation. It is specifically applicable to educational content, technical documentation, and instructional videos, capturing key information for quick recall.