baoyu-danger-gemini-web

Generate text and images via the Gemini Web API with session support.

Updated Feb 6, 2026

Search Tags:#cli #gemini #session-management #image-generation #text-generation #cookie-auth #vision-input

Ready to run

npx skills add https://github.com/glfruit/gorin-skills --skill baoyu-danger-gemini-web-glfruit

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: baoyu-danger-gemini-web
Source: https://github.com/glfruit/gorin-skills/tree/main/openclaw/baoyu-danger-gemini-web
Command: npx skills add https://github.com/glfruit/gorin-skills --skill baoyu-danger-gemini-web-glfruit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires baoyu-chrome-cdp, and includes scripts (resource) components.

What problem does it solve?

This skill provides an integrated Gemini Web API client to generate text and images from prompts, enabling back-end generation for AI-enabled tools and workflows.

Core Features & Use Cases

Text generation via Gemini Web API
Image generation from prompts with optional vision inputs
Vision input through reference images and multi-turn conversations with session support
Cookie-based authentication support and session management for persistent interactions

Quick Start

Run the main CLI with a prompt to generate text or images, optionally saving the output image.

Frequently Asked Questions about baoyu-danger-gemini-web

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

FAQPage Schema

How do I generate text and images using the Gemini Web API?▼

You can generate text and images via the Gemini Web API by running the main CLI with a prompt. It supports reference images for vision inputs and optionally saves the generated output image.

Can I maintain multi-turn conversations with session support in Gemini?▼

Yes, multi-turn conversations are supported with session management. This allows persistent interactions using cookie-based authentication to maintain context across multiple text and image generation prompts.

Do I need Chrome cookie access for Gemini API text generation?▼

Yes, cookie-based authentication is required for Gemini API text generation. The skill uses the baoyu-chrome-cdp dependency to access Chrome cookies and authenticate your Gemini Web API backend requests.

What runtime is required to execute Gemini image generation scripts?▼

You need bun or npx as the runtime execution environment for the Gemini image generation scripts. Additionally, a Gemini Web API backend must be configured to process the prompts and return generated images.

Does this skill support vision input through reference images?▼

Yes, vision input is supported through reference images. You can provide images alongside your text prompts to generate contextual outputs, leveraging the Gemini Web API's vision capabilities for multi-turn conversations.

What are the limitations of using cookie auth for Gemini Web API generation?▼

Cookie-based authentication depends on active Chrome sessions via the baoyu-chrome-cdp dependency. If the Chrome browser session expires or cookies become invalid, the Gemini Web API text and image generation will fail until re-authentication.