/generate-visuals

Generate production-ready prompts for AI image and video generation.

2|Updated Feb 22, 2026
One-click install
npx skills add https://github.com/nielskaspers/generate-visuals --skill generate-visuals
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: /generate-visuals
Source: https://github.com/nielskaspers/generate-visuals/tree/main
Command: npx skills add https://github.com/nielskaspers/generate-visuals --skill generate-visuals

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill transforms vague requests into production-ready prompts for generating authentic-looking AI images and videos, avoiding the common "plastic" or "AI-generated" look.

Core Features & Use Cases

  • Universal Prompting: Works with any AI generation tool (Gemini, Midjourney, DALL-E, Sora, etc.).
  • Anti-AI Techniques: Incorporates film stock references, lens imperfections, and material textures to ensure realism.
  • Contextual Composition: Optimizes prompts for specific use cases like website heroes, social media, or ad creatives.
  • Video Motion Direction: Explicitly defines camera, subject, and environmental movement for dynamic video clips.
  • Use Case: Instead of asking for "a car," you can ask for "a cinematic shot of a dusty 1974 Porsche 911 Carrera parked on a gravel shoulder overlooking the Pacific coast, late afternoon fog rolling in, paint faded to a warm patina of Tangerine Orange," and get a prompt ready for any AI tool.

Quick Start

Use the /generate-visuals skill to create a hero image for a blog post about sustainable fashion.

Frequently Asked Questions about /generate-visuals

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

FAQPage Schema
How do I write AI image generation prompts that look photorealistic instead of plastic?

To make AI image generation prompts look photorealistic, you need to incorporate anti-AI techniques like film stock references, lens imperfections, and material textures. This grounds the visual output in authentic, human-made aesthetics.

Can I use these AI generation prompts with any image or video model?

Yes, these AI generation prompts are universally compatible with any model. You can use the production-ready outputs with tools like Gemini, Midjourney, DALL-E, and Sora for both image and cinematic video generation.

What is the best way to direct motion when generating AI video clips?

The best way to direct motion in AI video clips is to explicitly define camera, subject, and environmental movement within the prompt. This contextual composition ensures dynamic and intentional video generation.

How do I optimize AI visuals for specific design contexts like website heroes or ads?

To optimize AI visuals for website heroes or ad creatives, the prompt engineering process applies contextual composition rules. This tailors the scene expansion and technical specifications to fit your specific use case perfectly.

Why does my AI art generation output look artificial and lack authentic textures?

AI art generation looks artificial when prompts lack grounding in physical media. Adding references to specific film stocks, lens flaws, and material textures overrides the default plastic AI look with authentic photography details.