baoyu-danger-gemini-web

Generate images and text via the reverse-engineered Gemini Web API.

Updated May 1, 2026
One-click install
npx skills add https://github.com/flashfoxer/openclaw-my-skills --skill baoyu-danger-gemini-web-flashfoxer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-danger-gemini-web
Source: https://github.com/flashfoxer/openclaw-my-skills/tree/main/baoyu-imagine/baoyu-danger-gemini-web
Command: npx skills add https://github.com/flashfoxer/openclaw-my-skills --skill baoyu-danger-gemini-web-flashfoxer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bun, npx, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of generating images and text using the reverse-engineered Gemini Web API, providing a versatile tool for image generation, text generation, and multi-turn conversations.

Core Features & Use Cases

  • Image Generation: Generate images from prompts using the Gemini Web API.
  • Text Generation: Generate text based on prompts, including multi-turn conversations.
  • Reference Images: Use reference images for vision input in image generation.
  • Use Case: When you need to generate images or text for a project, or when a user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.

Quick Start

Use the baoyu-danger-gemini-web skill to generate an image with the prompt "A cute cat".

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 images using the Gemini Web API?

You can perform text generation and multi-turn conversations by sending sequential prompts to the skill, which maintains context via the reverse-engineered Gemini Web API to provide continuous responses.

Do I need bun and npx to run Gemini Web API text generation?

Yes, you need both bun and npx installed in your environment, as these dependencies are required to execute the scripts that interact with the reverse-engineered Gemini Web API.

Can I use reference images for vision input with Gemini Web API generation?

Yes, you can use reference images for vision input, allowing the Gemini Web API to process visual data alongside text prompts for more contextual image and text generation.

What are the limitations of using a reverse-engineered Gemini Web API?

Using a reverse-engineered Gemini Web API means functionality depends on the unofficial web interface, which may break or change without warning, limiting long-term stability compared to official endpoints.

Does the Gemini Web API skill support multi-turn conversations?

Yes, the Gemini Web API skill supports multi-turn conversations, enabling back-and-forth text generation where the AI maintains context across multiple prompted interactions.