skills.rest
marcoapereirav-arch
marcoapereirav-archCOMMUNITY
Explore all skills by this author →
GitHub

image-generation

Generate and edit images via OpenRouter and Gemini with configurable prompts and aspect ratios.

Updated Aug 23, 2026
Search Tags:#gemini#openrouter#edit#image-generation#thumbnail#logo
One-click install
npx skills add https://github.com/marcoapereirav-arch/nvision-saas-factory --skill image-generation-marcoapereirav-arch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-generation
Source: https://github.com/marcoapereirav-arch/nvision-saas-factory/tree/main/saas-factory/.claude/skills/image-generation
Command: npx skills add https://github.com/marcoapereirav-arch/nvision-saas-factory --skill image-generation-marcoapereirav-arch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Generating and editing images can be time-consuming and error-prone when trying to create logos, thumbnails, banners, illustrations, or other visual assets. This skill streamlines that process by leveraging OpenRouter + Gemini to produce ready-to-use visuals from simple prompts and optional source images.

Core Features & Use Cases

  • Generate new visuals from natural language prompts for logos, banners, thumbnails, and illustrations.
  • Edit existing images by applying transformations or enhancements using a provided input image.
  • Provide asset-ready outputs for marketing, product pages, and social media with configurable aspect ratios and model choices.

Quick Start

Provide a prompt and an optional input image to generate or refine a visual asset using the image-generation skill.

Frequently Asked Questions about image-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate logos and thumbnails using Gemini AI?▼

You can generate logos and thumbnails by providing a natural language prompt to the image-generation skill. It leverages OpenRouter and Gemini AI to produce a ready-to-use image file and an optional textual description based on your prompt.

Can I edit existing images with Gemini through OpenRouter?▼

Yes, you can edit existing images by providing an optional input image alongside your prompt. The skill uses Gemini via OpenRouter to apply transformations or enhancements to the source image and outputs a refined visual asset.

Do I need an OpenRouter API key to generate visual assets?▼

Yes, an OPENROUTER_API_KEY configured via the AI setup-base is required. This key allows the skill to access OpenRouter and Gemini models to produce logos, banners, and illustrations from your prompts.

What image dimensions or aspect ratios can I specify for banners and illustrations?▼

You can specify configurable aspect ratios when generating banners and illustrations. The skill supports aspect ratio selection and model choices to ensure the output visual asset meets your specific formatting requirements.

What is the best way to create marketing visuals from text prompts?▼

Using the image-generation skill streamlines creating marketing visuals from text prompts by leveraging Gemini AI. It produces asset-ready outputs for marketing, product pages, and social media from simple natural language descriptions.

Related Skills

Explore More Design & Creative Skills→
antgroupantgroup
16

firecrawl

Access Firecrawl API for web search, scraping, and site crawling.

Official
Intermediate
akobryan1akobryan1
1

banner-design

Generates customizable social media and advertising banners for multiple platforms and styles.

Community
Intermediate
gerald-icagerald-ica

ad-creative

Generate platform-optimized ad copy variations for Google RSA, Meta, LinkedIn, and TikTok.

Community
Intermediate
devonjonesdevonjones
12

nano-banana

Generate, edit, and compose images with the Gemini 3 Pro Image model.

Community
Intermediate