baoyu-gemini-web
Image generation skill using Gemini Web. Generates images from text prompts via Google Gemini. Also supports text generation. Use as the image generation backend for other skills like cover-image, xhs-images, article-illustrator.
Security Assessment
About baoyu-gemini-web
The baoyu-gemini-web skill is a powerful tool designed for image generation and text generation utilizing the capabilities of Google Gemini. This skill effectively addresses the need for creating visual content from text prompts, making it easier for users to generate high-quality images and text responses that meet their specific requirements. Whether you need to illustrate an article, create cover images, or generate engaging content for social media, this skill streamlines the process, allowing users to focus on their creative ideas without the technical overhead typically associated with image generation.
FAQ
How do I generate an image using a prompt?
You can generate an image by using the command 'npx -y bun scripts/main.ts --prompt "Your prompt here" --image your_image.png'.
What models are available for text generation?
The available models include gemini-3-pro (default), gemini-2.5-pro, and gemini-2.5-flash.
Do I need to authenticate to use this skill?
Yes, the first run requires authentication with Google through Chrome, and cookies are cached for subsequent uses.
Can I generate images from multiple prompt files?
Yes, you can concatenate multiple prompt files using the '--promptfiles' option.
Is JSON output supported?
Yes, you can get JSON output by using the '--json' flag in your command.
Install baoyu-gemini-web
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
JimLiu/baoyu-skills