baoyu-danger-gemini-web

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

Updated Feb 6, 2026
One-click install
npx skills add https://github.com/glfruit/gorin-skills --skill baoyu-danger-gemini-web-glfruit
Or copy as Structured Prompt for Agent
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.