baoyu-danger-gemini-web

Generate text and images via the Gemini Web API with a local CLI client.

1|2|Updated Feb 28, 2026

Search Tags:#image-generation #multi-turn #text-generation #cookies #reference-images #consent #gemini-web

Ready to run

npx skills add https://github.com/zhangdszq/vk-skills --skill baoyu-danger-gemini-web-zhangdszq

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill provides a CLI-based client to generate text and images using the Gemini Web API, including support for vision input with reference images and multi-turn conversations, enabling seamless content creation without relying on the Gemini UI.

Core Features & Use Cases

Text generation from prompts using the Gemini Web API.
Image generation from prompts with optional vision input via reference images.
Multi-turn chat sessions with session state, and handling of reference and generated images.
Use cases include creating marketing copy, visual assets, or conversational content that leverages Gemini's capabilities.

Quick Start

Provide a prompt to start text or image generation using the Gemini Web Client.

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 outside of the standard UI?▼

You can generate text and images via the Gemini Web API using a local CLI client. This approach applies to workflows needing Gemini-powered content, including prompts with reference images and multi-turn conversations.

Can I use reference images for image generation with the Gemini Web API?▼

Yes, the Gemini Web API client supports image generation from prompts with optional vision input via reference images. This allows you to create visual assets directly from your CLI workflows.

Does the Gemini Web API client support multi-turn conversations?▼

Yes, the Gemini Web API client supports multi-turn chat sessions. It handles session state persistence, reference images, and generated images throughout the conversation.

How do I authenticate with the Gemini Web API using this client?▼

Authentication for the Gemini Web API is handled through browser cookies. The client supports consent handling and cookie-based authentication to establish and maintain your session.

What are the limitations of using a CLI client for Gemini Web API content generation?▼

Using the Gemini Web API via a CLI client requires cookie-based authentication and local session persistence. You must manage consent handling and optional image saving through scripted workflows rather than a visual interface.