visual-asset-prompt-generator

Transform brand documentation into structured prompts for image and 3D generation.

4|1|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/Sheshiyer/brandmint-oracle-aleph --skill visual-asset-prompt-generator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: visual-asset-prompt-generator
Source: https://github.com/Sheshiyer/brandmint-oracle-aleph/tree/main/skills/visual-pipeline/visual-asset-prompt-generator
Command: npx skills add https://github.com/Sheshiyer/brandmint-oracle-aleph --skill visual-asset-prompt-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reads brand documentation (visual identity, product description, positioning) and generates optimized prompts for image generation (Nano Banana/Flux via fal.ai) and 3D model generation (Hunyuan3D). Use when generating visual assets from brand docs.

Core Features & Use Cases

  • Extract brand context from Visual Identity, Product Description, and Product Positioning to feed AI prompt generators.
  • Generate tailored prompts for 2D visuals and 3D models across output contexts like landing pages, pitch decks, websites, and social media.
  • Produce a structured prompts JSON and a human-readable visual-generation-guide for downstream pipelines.

Quick Start

Provide brand documentation and run the visual-asset-prompt-generator to produce a prompts JSON and a human-readable guide.

Frequently Asked Questions about visual-asset-prompt-generator

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

FAQPage Schema
How do I generate AI image prompts from brand documentation?

Generating AI image prompts from brand docs involves feeding visual identity and positioning texts into the system. It extracts context to produce a structured prompts JSON and a human-readable visual-generation-guide for downstream pipelines.

What is the best way to turn brand docs into 3D model prompts?

Turning brand docs into 3D model prompts requires processing visual identity and positioning texts. The system transforms these inputs into structured prompt formats optimized for 3D model generation tools like Hunyuan3D.

Can I use brand positioning text to create prompts for landing pages and pitch decks?

You can use brand positioning text to create prompts for landing pages and pitch decks. The generator applies brand context to produce tailored visual prompts specifically for landing pages, pitch decks, websites, and social content.

Does this prompt generator work with Nano Banana and Flux via fal.ai?

The prompt generator works with Nano Banana and Flux via fal.ai. It processes brand documentation to produce optimized visual prompts structured specifically for these image generation platforms.

What file formats do I get when generating visual assets from brand docs?

Generating visual assets from brand docs yields a structured prompts JSON file and a human-readable visual-generation-guide. These formats provide structured outputs for downstream image generation and 3D modeling pipelines.