skills.rest
lamtuanvu
lamtuanvuCOMMUNITY
Explore all skills by this author →
GitHub

analyze-video

Analyze local videos and YouTube URLs to extract UI elements, text, actions, and timestamps.

Updated Feb 4, 2026
Search Tags:#multimodal#video#gemini#analyze#timestamps#ui-elements
One-click install
npx skills add https://github.com/lamtuanvu/agentskills --skill analyze-video-lamtuanvu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: analyze-video
Source: https://github.com/lamtuanvu/agentskills/tree/main/plugins/mobile-development/skills/analyze-video
Command: npx skills add https://github.com/lamtuanvu/agentskills --skill analyze-video-lamtuanvu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @google/genai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Analyzes video content to generate detailed, structured descriptions of what happens, including UI elements, visible text, actions, and temporal context.

Core Features & Use Cases

  • Gemini-powered multimodal video understanding for local files and YouTube URLs
  • Flexible input with optional start/end clipping and frame-rate control
  • Inline data support for small files or File API uploads for large videos
  • Real-world use: extract UI components and timestamps from a product demo to inform QA and documentation

Quick Start

Analyze a local video file named recording.mp4 to produce a detailed breakdown with UI elements, on-screen text, actions, and timestamps.

Frequently Asked Questions about analyze-video

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

FAQPage Schema
How do I analyze a video to extract UI elements and timestamps?▼

To analyze video content and extract UI elements and timestamps, you can use Gemini-powered multimodal video understanding. This processes local files or YouTube URLs to generate structured descriptions of on-screen actions and temporal context.

Can I analyze a YouTube URL to detect on-screen text and actions?▼

Yes, you can analyze a YouTube URL to detect visible text and actions. The Skill applies Gemini multimodal understanding directly to YouTube links, extracting detailed descriptions and temporal context without needing local downloads.

How do I process large local video files with Gemini for detailed summaries?▼

To process large local video files with Gemini for detailed summaries, the Skill automatically utilizes the File API for uploads. Smaller files are handled via inline data, ensuring flexible input across different file sizes.

Does Gemini video analysis support frame rate control and video clipping?▼

Yes, Gemini video analysis supports frame rate control through fps sampling and video clipping via start and end times. This allows targeted extraction of UI components and actions from specific segments.

What is the best way to generate QA documentation from a product demo video?▼

The best way to generate QA documentation from a product demo video is to extract UI components and timestamps using multimodal video analysis. This captures on-screen actions and text to inform testing and documentation workflows.

Related Skills

Explore More Data & Analytics Skills→
vibery-studiovibery-studio
3

ai-multimodal

Unify audio, image, video, and document processing via Google Gemini multimodal API.

Official
Advanced
htlin222htlin222
77

retro

Extract human-readable content from Claude Code session JSONL files into structured retrospective reports.

Community
Intermediate
wuyuxiangXwuyuxiangX

yux-blog-writer

Converts video summaries into blog articles with selectable writing styles.

Community
Intermediate
zeroix07zeroix07

video-understand

Analyze video content to extract scenes, actions, and temporal events.

Community
Advanced