Skills
.Work. You
Rest

watch-visual

Community

Extract visual insights from YouTube videos

Education & Research#multimodal#youtube#transcription#ffmpeg#video-analysis#frame-extraction#visual-understanding
Authorthiansit
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps users learn from YouTube videos when important information is conveyed visually—code on screen, diagrams, UI flows, or demonstrations—that transcripts alone cannot capture, enabling a complete multimodal understanding.

Core Features & Use Cases

  • Frame extraction & sampling: Download videos and extract representative frames at configurable intervals (quick, standard, detailed).
  • Multimodal alignment: Combine frame-level visual analysis with audio transcripts to build a timestamped timeline of visual + spoken content.
  • Visual intelligence: Read on-screen text, identify code, diagrams, UI elements, and notable visual changes to highlight demonstrations and actionable steps.
  • Use Case: Analyze a programming tutorial to extract code snippets shown on screen, identify the demonstration steps, and produce a combined timeline with screenshots and key insights.

Quick Start

Ask the skill to analyze this YouTube URL and specify the analysis detail level (quick, standard, or detailed).

Dependency Matrix

Required Modules

None required

Components

Standard package

đź’» Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: watch-visual
Download link: https://github.com/thiansit/LuPang/archive/main.zip#watch-visual

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.