skills.rest
oguzhandilber
oguzhandilberCOMMUNITY
Explore all skills by this author →
GitHub

gemini-search-image-video-creator

Automates Gemini PRO 3.1 UI interactions for prompts, research, images and videos via Chrome dev-browser extension and relay server.

2|Updated Mar 2, 2026
Search Tags:#automation#image generation#gemini#chrome extension#video generation#deep research
One-click install
npx skills add https://github.com/oguzhandilber/gemini-search-image-video-creator --skill gemini-search-image-video-creator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-search-image-video-creator
Source: https://github.com/oguzhandilber/gemini-search-image-video-creator/tree/main
Command: npx skills add https://github.com/oguzhandilber/gemini-search-image-video-creator --skill gemini-search-image-video-creator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates interactions with Gemini PRO, enabling the generation of images, videos, and in-depth research directly through an AI agent, eliminating manual UI navigation.

Core Features & Use Cases

  • Image Generation: Create images based on user prompts.
  • Video Generation: Generate videos from descriptive prompts.
  • Deep Research: Conduct comprehensive AI-powered research on complex topics.
  • Prompt Chat: Send prompts and receive AI responses for various queries.
  • Use Case: Ask the AI to "Generate an image of a futuristic city skyline at sunset" or "Research the latest advancements in quantum computing."

Quick Start

Use the gemini-search-image-video-creator skill to generate an image of a cat playing a guitar.

Frequently Asked Questions about gemini-search-image-video-creator

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

FAQPage Schema
How do I automate Gemini PRO for image and video generation?▼

Automate Gemini PRO for image and video generation by using this Skill to control the UI via a Chrome dev-browser extension, sending prompts directly from your AI agent without manual navigation.

Can I use a Chrome extension to conduct deep research with Gemini?▼

Yes, you can conduct deep research with Gemini through a Chrome extension by managing browser automation and relay server connections to execute comprehensive AI-powered research tasks.

What is needed to set up Gemini PRO browser automation for an AI agent?▼

Setting up Gemini PRO browser automation requires configuring a Chrome dev-browser extension and establishing a relay server connection to facilitate command-line execution of prompt tasks.

Does this approach work for sending prompts to Gemini without manual UI interaction?▼

Yes, this approach works for sending prompts to Gemini by eliminating manual UI navigation, enabling your AI agent to directly send prompts, generate images, and generate videos.

Are there limitations to automating Gemini PRO through a dev-browser extension?▼

Automating Gemini PRO through a dev-browser extension is subject to the browser's environment constraints, requiring active relay server connections and command-line execution to maintain UI interaction stability.

Related Skills

Explore More Software Engineering Skills→
CraftOS-devCraftOS-dev
375

linkedin

Automate LinkedIn messaging, profile viewing, and connection requests via browser automation.

Community
Intermediate
MohammedSaudAlsahliMohammedSaudAlsahli

graphify

Convert code, documents, papers, images, and videos into knowledge graphs.

Community
Advanced
BuilderIOBuilderIO
11

playwright-cli

Automate browser interactions and Playwright test workflows via command-driven tooling.

Official
Advanced
lihanghanglihanghang

RedBookSkills

Automate Xiaohongshu content publishing via Chrome/CDP workflows.

Community
Advanced