resonance-design-studio

Generates visual assets from structured, model-neutral image prompts with documented reproducible settings.

Updated Dec 1, 2025
One-click install
npx skills add https://github.com/manusco/wolfgang --skill resonance-design-studio-manusco
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: resonance-design-studio
Source: https://github.com/manusco/wolfgang/tree/main/.agents/skills/design/studio
Command: npx skills add https://github.com/manusco/wolfgang --skill resonance-design-studio-manusco

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI-generated images often look generic, plastic, or inconsistent because prompts are vague one-line guesses. This Skill turns image generation into a disciplined engineering process: structured prompts, concrete camera and lighting parameters, and documented settings so every asset reproduces. ## Core Features & Use Cases - Structured Prompt Craft: Separates Subject, Style, Light, Camera, and Exclusions into independent fields so each can be edited without disturbing the rest. - Artifact Recovery: Diagnoses and fixes the AI look (waxy skin, dead eyes, garbled text) with targeted camera, film stock, and inpainting adjustments instead of blind rerolls. - Set Consistency: Holds seeds, reference images, and shared style anchors so multi-image campaigns stay visually coherent. - Use Case: You need a hero image for a B2B fintech landing page. The Skill produces a structured prompt with a named lens, light direction, 16:9 aspect ratio, and a safe zone for overlay copy, then saves the recipe next to the asset. ## Quick Start Ask the Skill to generate a hero image for your product, providing the subject, placement, brand palette, and aspect ratio.

Frequently Asked Questions about resonance-design-studio

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

FAQPage Schema
How do I write image generation prompts that do not look generic?▼

Structure the prompt into separate Subject, Environment, Light, and Camera fields instead of one run-on sentence. Replace vague words like 'realistic' or '8k' with a concrete lens, aperture, light direction, and film stock so the model has an actual capture setup to follow.

How do I keep a set of AI-generated images visually consistent?▼

Hold the seed and pass a reference image, keep the structured style fields identical across every prompt, and vary only the subject field. Document the shared style parameters so the series can be extended later without drift.

Why do AI-generated images look plastic with smooth skin and dead eyes?▼

The model defaults to its averaged output when no capture medium is specified. Fix it by naming a concrete film stock or sensor, a prime lens, natural light direction, and adding grain or imperfection, then repair local flaws with inpainting rather than rerolling.

Can image models render text for thumbnails and social graphics?▼

Image models garble small text, so exclude text from the prompt and set copy in layout afterward. For thumbnails, keep text absent or large enough to survive compression, and route headline language to a copywriting skill.

When should visual asset generation not handle interface design?▼

Asset generation covers illustration, hero art, textures, and mascots, not screens or components. The moment the work is a real UI with type and controls, interface taste and style judgment belong to a dedicated design skill.