prompt-image

Convert rough image ideas into generator-ready prompts with style-guide constraints.

1|Updated Apr 5, 2026
One-click install
npx skills add https://github.com/Alexmacapple/alex-claude-skill --skill prompt-image
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-image
Source: https://github.com/Alexmacapple/alex-claude-skill/tree/main/prompt-image
Command: npx skills add https://github.com/Alexmacapple/alex-claude-skill --skill prompt-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

prompt-image provides a structured pipeline to convert rough visual ideas into generator-ready prompts that adhere to a chosen style guide and the constraints of image generators.

Core Features & Use Cases

  • End-to-end prompt refinement pipeline (semantic fidelity checks, visual translation, style-guide conformance, and generator feasibility).
  • Supports multiple generators (Nano Banana 2, Qwen Image 2.0) with a 5-step process and a fixed 10-key Prompt1 structure.
  • Iterative refinement: up to three rounds to converge on a high-quality prompt ready for generation.

Quick Start

Provide a rough image concept as input and get back a fully structured, style-guide-compliant prompt ready to feed into your generator.

Frequently Asked Questions about prompt-image

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

FAQPage Schema
How do I convert a rough image idea into a structured prompt that follows my style guide?

To convert a rough idea into a structured prompt, this skill uses a multi-pass pipeline that analyzes your concept, decomposes it, and enriches it while enforcing style-guide constraints and generator feasibility.

Can I use this prompt engineering pipeline with Nano Banana 2 or Qwen Image 2.0?

Yes, the prompt engineering pipeline supports multiple image generators specifically including Nano Banana 2 and Qwen Image 2.0, formatting the final output into a fixed 10-key structure ready for generation.

Do I need a style guide loaded in my project to generate compliant image prompts?

Yes, you need a style guide loaded from your project to generate compliant image prompts, as the pipeline validates 10 Prompt1 keys and blocks terms that would break either the style guide or the generator.

What does the iterative refinement process do when optimizing image generation prompts?

The iterative refinement process performs up to three rounds of analysis, enrichment, and optimization to converge on a high-quality, generator-ready prompt that maintains strict semantic fidelity and visual translation accuracy.

Why does my image generation prompt get blocked during the style-guide compliance check?

Your image generation prompt gets blocked during the compliance check if it contains specific terms that would violate the loaded style-guide constraints or break the technical limitations of the target image generator.