Can I generate images using this Gemini skill?

Yes, the skill supports full image generation using the Gemini backend. You can specify output paths and prompts directly via the command line.

Is it possible to maintain context across multiple messages?

Yes, by using the --sessionId flag, you can maintain persistent, multi-turn conversations, allowing the model to remember previous interactions.

Does this skill require an official Google Cloud API key?

No, it uses a reverse-engineered approach that leverages browser-based authentication and cookies rather than a standard Google Cloud API key.

How does the authentication process work?

On the first run, the skill opens your local browser (such as Chrome or Edge) for Google authentication and automatically caches the cookies for subsequent uses.

What software environment is required to run this skill?

The skill is designed for the Nanobot TS framework and requires Bun to execute the TypeScript-based scripts.

Gemini Web Integration

Name: Gemini Web Integration
Author: chengyihua

bychengyihua

0•

Ciencia de Datos y ML

Enables high-quality text and image generation using a reverse-engineered Gemini Web API interface.

This skill provides a robust bridge to the Gemini Web API, allowing users to leverage Google's latest models for text generation, high-fidelity image creation, and vision-based tasks directly within their AI workflow. It supports multi-turn conversations through sophisticated session management, handles reference images for visual analysis, and automates cookie-based authentication via local browsers, making it an ideal choice for developers seeking Gemini's capabilities without the friction of standard API management.

Características Principales

01Automated browser-based authentication and secure cookie caching

02Advanced text and image generation via Gemini 3 Pro and Flash models

030 GitHub stars

04Persistent multi-turn conversations with automated session management

05Vision input support using reference images for AI-driven visual analysis

06Flexible output options supporting both standard text and structured JSON

Casos de Uso

01Analyzing and describing local image files using Gemini's advanced vision capabilities

02Generating high-quality AI images from descriptive text prompts for design workflows

03Maintaining context-aware AI chat sessions for complex, multi-step engineering tasks

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add chengyihua/nanobot-ts baoyu-danger-gemini-web

For use in Claude.ai and ChatGPT

Download Skill