skills.rest
lisposter
lisposterCOMMUNITY
Explore all skills by this author →
GitHub

baoyu-danger-gemini-web

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

1|Updated Feb 2, 2026
Search Tags:#image generation#gemini#multi-turn chat#consent management#vision input#text generation
One-click install
npx skills add https://github.com/lisposter/creator --skill baoyu-danger-gemini-web
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-danger-gemini-web
Source: https://github.com/lisposter/creator/tree/main/.agents/skills/baoyu-danger-gemini-web
Command: npx skills add https://github.com/lisposter/creator --skill baoyu-danger-gemini-web

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill enables generating Gemini-based text and images through a reverse-engineered Gemini Web API. It provides a backend for text generation, image creation from prompts, vision-input via reference images, and multi-turn conversations, useful when other skills need Gemini-backed generation capabilities.

Core Features & Use Cases

  • Gemini-powered text generation with optional image generation from prompts.
  • Vision-enabled generation using reference images for contextual input.
  • Multi-turn chat support to maintain conversational context across prompts.

Quick Start

Use the Gemini Web skill to generate text or images. Examples:

  • npx -y bun ${SKILL_DIR}/scripts/main.ts "Describe a sunset over the ocean"
  • npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "Create an illustration of a robot" --image robot.png
  • npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "Describe this image" --reference input.png

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 using a Gemini Web API backend?▼

This skill provides a reverse-engineered Gemini Web API backend for text generation, allowing you to execute the main script with a prompt string to receive generated text responses.

Can I generate images from prompts with Gemini?▼

Yes, you can generate images from prompts with Gemini by running the script with the --image flag and providing your descriptive prompt to produce the requested visual output.

How does vision input work for Gemini image generation?▼

Vision input works by passing a reference image alongside your prompt using the --reference flag, allowing the Gemini model to process the visual context to inform its generation output.

Does this Gemini Web skill support multi-turn chat conversations?▼

Yes, this Gemini Web skill supports multi-turn chat conversations, enabling you to maintain conversational context across multiple sequential prompts for continuous interactions.

When should I use a reverse-engineered Gemini Web API instead of an official backend?▼

You should use a reverse-engineered Gemini Web API when no official Gemini backend is available or when your workflow explicitly requires Gemini-based generation capabilities without official API access.

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

Because it relies on a reverse-engineered Gemini Web API rather than an official backend, limitations include potential instability, lack of guaranteed uptime, and possible breaking changes if the web interface updates.

Related Skills

Explore More Software Engineering Skills→
flashfoxerflashfoxer

baoyu-danger-gemini-web

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

Community
Intermediate
haidonglethqbhaidonglethqb

ck:media-processing

Automate media encoding, conversion, filtering, and thumbnail generation with FFmpeg and ImageMagick.

Community
Intermediate
LennyDevXLennyDevX

ai-chat-gemini

Integrate Gemini-based chat into Nuxbee with streaming responses and system prompts.

Community
Advanced
shalevaminshalevamin

image-gen

Generate images from text prompts using OpenAI and Google APIs.

Community
Intermediate