baoyu-danger-gemini-web

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

3|Updated Jun 27, 2026

Search Tags:#automation #api #image generation #ai #vision #gemini

Ready to run

npx skills add https://github.com/XinAloha/skills --skill baoyu-danger-gemini-web-xinaloha

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires baoyu-chrome-cdp, and includes scripts (resource) components.

What problem does it solve?

This skill provides a programmatic interface to the Gemini Web API, allowing users to leverage Gemini's advanced text and image generation capabilities directly within their agent workflows, bypassing the need for manual browser interaction.

Core Features & Use Cases

Multi-modal Generation: Supports both text generation and image creation from prompts.
Vision Capabilities: Allows for reference images to be used as vision input for analysis or variation tasks.
Session Management: Maintains multi-turn conversation state, enabling complex, context-aware interactions.
Use Case: Integrate this skill into an agent to automatically generate social media graphics or perform vision-based document analysis by passing images and prompts through the Gemini backend.

Quick Start

Use the baoyu-danger-gemini-web skill to generate an image of a futuristic city based on the prompt provided in the current context.

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 automate Gemini text and image generation in an agent workflow?▼

Automating Gemini Web API text and image generation involves interfacing agent workflows with a reverse-engineered endpoint that supports multi-turn conversations and vision inputs via programmatic calls.

Can I use reference images as vision input for Gemini image analysis?▼

Reference images can be used as vision input for Gemini image analysis by passing them through the Gemini Web API alongside text prompts to perform analysis or generate image variations.

Do I need a browser session to authenticate against Google services for Gemini API automation?▼

Gemini API automation requires a valid browser session or cached cookies to authenticate against Google services, enabling programmatic access without manual browser interaction during automated workflows.

Does the baoyu-danger-gemini-web skill support multi-turn conversations with session persistence?▼

The baoyu-danger-gemini-web skill supports multi-turn conversations with session persistence, maintaining conversation state to enable complex, context-aware interactions for advanced agent workflows.

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

Using a reverse-engineered Gemini Web API for automation depends on maintaining a valid browser session or cached cookies for Google services, meaning functionality may break if the underlying web interface or authentication mechanisms change.