image

Generate and optimize marketing images using AI models and design tools.

Updated Jun 21, 2026
One-click install
npx skills add https://github.com/NicolaeRotaru/ad-mycity --skill image-nicolaerotaru
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image
Source: https://github.com/NicolaeRotaru/ad-mycity/tree/main/.cursor/skills/image
Command: npx skills add https://github.com/NicolaeRotaru/ad-mycity --skill image-nicolaerotaru

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating marketing visuals — blog heroes, social graphics, product mockups, banners, and OG images — requires choosing the right AI model, writing effective prompts, matching platform dimensions, and optimizing files for web performance. This Skill guides that entire workflow so you produce on-brand, correctly sized, optimized images without guesswork. ## Core Features & Use Cases - AI Model Selection: Compares Gemini/Nano Banana, Flux, Ideogram, GPT Image, Midjourney, Recraft, and Stable Diffusion with a decision tree for text rendering, editing, brand consistency, and cost. - Platform-Specific Workflows: Provides exact dimensions and workflows for blog heroes (1200x630), social posts (Instagram, LinkedIn, X, Facebook), profile banners, and directory listings. - Image Optimization: Covers WebP/AVIF conversion, compression targets, lazy loading, and OG meta tags with ready-to-use commands (cwebp, ImageMagick, jpegoptim). - Use Case: You need a hero image for a blog post plus an OG preview. The Skill helps you pick Flux or Gemini, write a structured prompt (subject + setting + style + lighting + composition), generate at 1200x630, and compress to under 200KB as WebP. ## Quick Start Ask the assistant to create a 1200x630 blog hero image about your topic and optimize it as a WebP file under 200KB.

Frequently Asked Questions about image

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

FAQPage Schema
How do I generate marketing images with AI models?▼

Write a structured prompt covering subject, setting, style, lighting, composition, and aspect ratio, then generate with a model like Flux, Gemini, or Ideogram. Always specify dimensions explicitly and add style direction such as photorealistic or flat illustration.

Which AI image model is best for text in images?▼

Ideogram 3.0 renders text most accurately, making it the best choice for headlines and branded graphics. Gemini and GPT Image handle short text decently, but for anything beyond brief headlines, add text as an overlay in post-processing instead.

Can AI generate product screenshots and UI mockups?▼

No, AI models hallucinate interface elements and should not be used for product UI. Capture real screenshots at 2x resolution with browser DevTools or tools like CleanShot X, then frame them in device mockups and annotate with code overlays.

What size should OG images and social graphics be?▼

OG images should be 1200x630, which also works for blog heroes. Platform sizes vary: Instagram feed is 1080x1080, Stories are 1080x1920, LinkedIn feed is 1200x627, and X cards are 1200x675.

How do I optimize images for web performance?▼

Serve WebP with JPEG fallback, resize images to their display dimensions, compress photos to 75-85% quality, lazy load below-the-fold images, and set explicit width and height attributes. Use cwebp or ImageMagick for batch conversion.

When should I use Canva or Figma instead of AI generation?▼

Use design tools when exact brand guidelines must be followed, when you need many size variants of one design, or for recurring templates. Use AI generation for unique hero images, abstract visuals, and one-off creative concepts.