watch-video

Analyze public video URLs and generate reports on visual and auditory content.

1|2|Updated Jan 23, 2026
One-click install
npx skills add https://github.com/blink-new/claude --skill watch-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: watch-video
Source: https://github.com/blink-new/claude/tree/main/skills/watch-video
Command: npx skills add https://github.com/blink-new/claude --skill watch-video

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill allows you to get a detailed analysis of any public video URL without needing to watch it yourself, saving you time and effort.

Core Features & Use Cases

  • Multi-platform Support: Analyzes videos from Loom, YouTube, and other sites.
  • Comprehensive Reporting: Provides insights into both visual content and spoken narration.
  • Use Case: You receive a Loom link for a new feature demo. Instead of watching it, use this Skill to get a detailed report on what's on screen, what was said, and key action items.

Quick Start

Use the watch-video skill to analyze the YouTube video at https://www.youtube.com/watch?v=dQw4w9WgXcQ.

Frequently Asked Questions about watch-video

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

FAQPage Schema
How do I get a video summary from a YouTube link without watching it?

Video analysis tools can summarize YouTube links by transcribing audio with Whisper and using Gemini to analyze visual content. This provides a detailed report of spoken narration and on-screen elements without manual viewing.

Can I analyze Loom videos for bug reports and feature demos automatically?

Yes, you can analyze Loom videos for bug reports and feature demos automatically. The skill processes public Loom URLs to extract visual content, transcribe spoken narration, and generate detailed reports on demonstrated features.

Does video transcription and analysis require yt-dlp and Whisper?

Yes, this video analysis approach requires yt-dlp to extract video files and metadata, and Whisper to transcribe audio. Gemini is then used to analyze visual elements and summarize the comprehensive report.

What is the best way to extract action items from a video demonstration?

The best way to extract action items from a video demonstration is using AI video analysis to transcribe audio and evaluate visual content. This generates a detailed report highlighting key features and next steps without watching.

Are there limitations when analyzing public video URLs with Whisper and Gemini?

Limitations when analyzing public video URLs with Whisper and Gemini include requiring public access and depending on yt-dlp extraction compatibility. Private videos or unsupported platforms cannot be processed for transcription or visual analysis.