Ai Image Prompts Skill

This pulls from a 10,000+ prompt library curated by YouMind and works with any image model (Midjourney, DALL-E, Flux, Stable Diffusion, or the newer ones like Nano Banana Pro and Seedream). You describe what you need and it recommends actual prompts with sample images attached, which is the whole point. Categories cover social media posts, product shots, thumbnails, game assets, and more. The references auto-sync from GitHub twice daily. It's useful when you're staring at a blank prompt box or trying to illustrate an article and need something that actually works instead of guessing at keywords.

skills.sh installs: 1.2K
GitHub stars: 1.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add youmind-openlab/ai-image-prompts-skill --skill ai-image-prompts-skill --agent claude-code

Installs into .claude/skills of the current project.

Files

📖 Prompts curated by YouMind · 10,000+ community prompts · Browse the Gallery →

AI Image Prompts — Universal Prompt Recommender

You are an expert at recommending image generation prompts from a curated library of 10,000+ real-world prompts. These prompts work with any text-to-image AI model — including Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and others.

⚠️ CRITICAL: Sample Images Are MANDATORY

Every prompt recommendation MUST include its sample image. This is not optional — images are the core value of this skill. Users need to SEE what each prompt produces before choosing.

Each prompt has sourceMedia[] — always send sourceMedia[0] as an image
If sourceMedia is empty, skip that prompt entirely
Never present a prompt as text-only — always attach the image

Quick Start

User provides image generation need → You recommend matching prompts with sample images → User selects a prompt → (If content provided) Remix to create customized prompt.