Is this an official Google Cloud API integration?

No, this skill utilizes a reverse-engineered client for the Gemini Web interface. It requires users to accept a disclaimer regarding the unofficial nature of the connection.

How does the authentication process work?

Upon the first execution, the skill will attempt to open a supported browser (Chrome, Edge, or Chromium) to log into Google. Once authenticated, cookies are cached locally for subsequent requests.

Can I use this skill to analyze existing images?

Yes, the skill supports vision input via the --reference flag, allowing you to attach local images for Gemini to analyze or use as a prompt reference.

Which Gemini models can I use with this skill?

The skill supports multiple models including gemini-3-pro (default), gemini-2.5-pro, and gemini-2.5-flash.

Does it support conversation history?

Yes, by providing a unique --sessionId, the skill tracks conversation metadata, allowing for multi-turn dialogues where Gemini remembers previous context.

Gemini Web Image & Text Generator

Name: Gemini Web Image & Text Generator
Author: xiaxingxiaowei1983

byxiaxingxiaowei1983

0•

Content Management

Generates high-quality AI images and text responses by interfacing directly with the Google Gemini web platform from Claude Code.

This skill provides a powerful bridge between Claude Code and the Google Gemini web interface, enabling seamless image generation, text synthesis, and advanced vision capabilities without requiring an official API key. It allows developers to generate visual assets from text prompts, analyze reference images, and maintain complex, multi-turn conversations via persisted session IDs. Designed to act as a versatile backend for visual content workflows, it includes built-in proxy support and automated browser authentication, making it an essential tool for creators and developers looking to integrate Gemini's latest models into their local development environment.

Key Features

010 GitHub stars

02High-fidelity image generation from text prompts with custom save paths

03Integrated proxy support (HTTP/HTTPS) for global accessibility

04Support for multi-turn conversations using persisted session IDs

05Automated browser-based authentication and secure cookie caching

06Vision input processing for analyzing or modifying local reference images

Use Cases

01Leveraging Gemini's vision models to describe or provide feedback on local UI mockups

02Generating blog post illustrations and social media cover images directly from the command line

03Building automated content pipelines that require simultaneous text and image generation

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add xiaxingxiaowei1983/openclaw awkn-danger-gemini-web

For use in Claude.ai and ChatGPT

Key Features

010 GitHub stars

02High-fidelity image generation from text prompts with custom save paths

03Integrated proxy support (HTTP/HTTPS) for global accessibility

04Support for multi-turn conversations using persisted session IDs

05Automated browser-based authentication and secure cookie caching

06Vision input processing for analyzing or modifying local reference images

Use Cases

01Leveraging Gemini's vision models to describe or provide feedback on local UI mockups

02Generating blog post illustrations and social media cover images directly from the command line

03Building automated content pipelines that require simultaneous text and image generation