reversa-image-prompt-json

Generate structured JSON image prompts through a three-stage guided interview.

1|Updated Dec 20, 2025
One-click install
npx skills add https://github.com/Rdinda/FMA_Pontos --skill reversa-image-prompt-json-rdinda
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reversa-image-prompt-json
Source: https://github.com/Rdinda/FMA_Pontos/tree/main/.agents/skills/reversa-image-prompt-json
Command: npx skills add https://github.com/Rdinda/FMA_Pontos --skill reversa-image-prompt-json-rdinda

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill turns vague image ideas into structured, model-ready JSON prompts, so you can reliably generate high-quality product and scene imagery without rewriting prompts from scratch.

Core Features & Use Cases

  • Structured JSON prompt building: Creates a ready-to-use master_prompt schema tailored for image generation.
  • Guided, multi-round interview: Collects product details, composition, lighting, colors, and technical settings in three question rounds.
  • Prompt quality guardrails: Enforces premium descriptive language, movement-freeze requirements, hero centering, and consistent output constraints for Nano Banana 2.

Quick Start

Tell an AI assistant: "Generate an image prompt JSON for a {product type} with a {luxury cinematic} look, include dynamic frozen motion, and set resolution {2K} with aspect ratio {16:9}."

Frequently Asked Questions about reversa-image-prompt-json

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

FAQPage Schema
How do I generate a structured JSON image prompt for product photography?

A structured JSON image prompt is a model-ready schema containing your master prompt, resolution, aspect ratio, and scene details. It transforms vague product photography ideas into validated, structured data to reliably generate high-quality imagery without rewriting prompts from scratch.

Can I create a cinematic luxury image prompt with a 16:9 aspect ratio?

Yes, you can create a cinematic luxury image prompt with a 16:9 aspect ratio by specifying your technical preferences. The system validates the resolution and aspect ratio settings, enforcing premium descriptive language and hero centering constraints within the final JSON output.

What is the best way to build image prompts compatible with Midjourney and DALL-E?

The best way to build compatible image prompts for Midjourney and DALL-E is using a guided multi-round interview to capture composition and lighting details. This process outputs a structured JSON master prompt with quality guardrails, ensuring consistent results across image generation models.

Does the JSON image prompt schema include a synthid watermark?

Yes, the JSON image prompt schema includes a validated synthid watermark. Along with enforced resolution and aspect ratio settings, this watermark is integrated into the final output to ensure generated product photography meets Nano Banana 2 compatibility requirements.

Why does the image prompt generation require a three-stage interview process?

The image prompt generation requires a three-stage interview process to systematically collect product details, scene composition, and technical settings. This structured approach ensures all visual parameters are captured before summary confirmation, preventing vague inputs and enforcing premium descriptive language in the JSON output.