media-generate-image

What problem does it solve?

It turns brief or incomplete image requests into complete, high-quality prompts and then drives Gemini image generation in Chrome so users can get a downloadable image without managing the browser workflow themselves.

Core Features & Use Cases

• Smart prompt enrichment: Expands vague ideas into detailed prompts covering style, scene elements, mood, perspective, and narrative context.
• Interactive clarification: Uses quick picks or step-by-step questions when the request needs more detail before generation.
• Browser-based image creation: Opens Gemini, submits the prompt, waits for the result, and downloads the generated image.
• Use case: A user asks for “an image of a cat,” and the skill transforms that into a complete creative brief, generates the image, and saves it locally.

Quick Start

Ask the skill to generate an image of your subject, and it will refine the prompt if needed, create the image in Gemini, and download the result for you.