gemini-browser-image

Automate Gemini image generation and editing in a real browser.

30|1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/qianleigood/crawclaw --skill gemini-browser-image
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-browser-image
Source: https://github.com/qianleigood/crawclaw/tree/main/skills-optional/gemini-browser-image
Command: npx skills add https://github.com/qianleigood/crawclaw --skill gemini-browser-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright-core, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Seamless image workflows in Gemini require a real browser session to preserve login state, UI-driven uploads, and authentic page behavior that API-only tools cannot replicate.

Core Features & Use Cases

  • Browser-based image generation and editing within the Gemini UI, preserving login state and local artifacts.
  • Handles file uploads, persistent sessions, and UI-driven interactions that rely on the Gemini web app.
  • Use Case: When you must test image prompts against the live Gemini interface with real browser cues and saved outputs.

Quick Start

Authenticate in Gemini and run the Gemini Browser Image workflow to perform a logged-in image task.

Frequently Asked Questions about gemini-browser-image

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

FAQPage Schema
How do I automate Gemini image generation in a browser without an API key?

Automating Gemini image generation without an API key requires driving the live web UI via browser automation. This Skill uses playwright-core to handle file uploads, manage login state, and interact with the interface to generate and save images locally.

Can I use Playwright to upload images and preserve login state for Gemini workflows?

Yes, Playwright supports preserving login state for Gemini workflows. This Skill leverages a logged-in browser profile to handle UI-driven file uploads and authentic page behavior, ensuring persistent sessions for image generation.

What's the best way to test image prompts against the live Gemini interface?

Testing image prompts against the live Gemini interface is best done through real browser automation. This Skill executes logged-in image tasks, processes UI-driven uploads, and verifies saved local outputs to validate prompt behavior.

How does browser automation handle file uploads for Gemini image editing?

Browser automation handles Gemini file uploads by interacting directly with the web UI. This Skill manages the upload process, maintains a stable image-generation state, and verifies the saved local output without needing API integration.

Do I need a logged-in browser profile to automate Gemini web image workflows?

Yes, a logged-in browser profile is required to automate Gemini web image workflows. This Skill depends on reusing an authenticated session to perform UI-driven interactions and file uploads that API-only tools cannot replicate.

Why does Gemini image generation require real browser sessions instead of API calls?

Gemini image generation requires real browser sessions because authentic page behavior and UI-driven uploads are necessary. This Skill preserves login state and handles local artifacts that API-only tools cannot replicate during image workflows.