Open Skills Logo
Open Skills

baoyu-danger-gemini-web

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.

Author

@JimLiu

Category

Image Processing

Install

Hot:16

Download and extract to your skills directory

Copy command and send to OpenClaw for auto-install:

Download and install this skill https://openskills.cc/api/download?slug=jimliu-skills-baoyu-danger-gemini-web&locale=en&source=copy

baoyu-danger-gemini-web

Skill Overview


Use reverse engineering of the Gemini Web API to implement AI content generation, supporting text generation, image creation, reference-image visual understanding, and multi-turn conversational sessions.

Use Cases


  • Claude Skill Image Backend: When other skills require image generation capabilities, it can be integrated as a backend service

  • Free AI Content Creation: Scenarios where you need to generate text or images but want to avoid official API costs

  • Multimodal AI Interaction: Applications that need to handle both text and visual inputs while maintaining conversation context

    • Core Features


  • Image Generation: Generate images from text descriptions, and support image-to-image variants using reference images

  • Text Generation: Use Gemini models for high-quality text generation, with support for selecting multiple models (gemini-3-pro, gemini-2.5-pro, gemini-2.5-flash)

  • Session Management: Supports multi-turn conversations, automatically saves and restores session state to maintain continuity of conversational context

    • Frequently Asked Questions

    What is baoyu-danger-gemini-web?


    It is an AI generation tool that implements Gemini model capabilities through reverse engineering of the Gemini Web API. It provides features such as text generation, image creation, and visual input references, allowing you to call Gemini without using the official API.

    How do I generate images with Gemini?


    Run the command npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "your description" --image output.png. This will generate the image. On first use, it will automatically open a browser to complete Google login authentication.

    Does the Gemini Web API require payment?


    This skill uses reverse engineering to call the Gemini Web interface and does not directly use the official paid API. However, please note that this is an unofficial usage method; on first use, you must read and agree to the relevant disclaimers.