refero-design

Creates research-first UI designs using Refero MCP's screen and user-flow libraries.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/lemone112/labpics-dashboard --skill refero-design-lemone112
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: refero-design
Source: https://github.com/lemone112/labpics-dashboard/tree/main/.agents/skills/refero-design
Command: npx skills add https://github.com/lemone112/labpics-dashboard --skill refero-design-lemone112

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill empowers AI agents to move beyond generic, "AI-slop" designs by grounding their creative process in real-world design research and established best practices.

Core Features & Use Cases

  • Research-First Methodology: Guides agents through a structured discovery, research, analysis, and design process.
  • Real-time Design Research: Leverages the Refero MCP to search over 150,000 screens and 6,000 user flows for inspiration and patterns.
  • Craft Guidance: Provides detailed rules on typography, color, spacing, motion, and icons to ensure polished execution.
  • Use Case: When asked to design a new user interface, onboarding flow, or marketing landing page, this Skill ensures the AI researches existing successful patterns before generating a design, preventing common AI pitfalls like generic layouts and uninspired color palettes.

Quick Start

Use the refero design skill to research and design a new pricing page.

Frequently Asked Questions about refero-design

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

FAQPage Schema
How do I stop my AI agent from generating generic UI designs?

To avoid generic AI designs, this Skill implements a research-first methodology that grounds the AI agent in real-world design patterns. It guides the process from discovery through implementation, applying professional craft standards to typography, color, and spacing.

How do I research existing user flows before designing a new landing page?

You can research existing user flows by leveraging the Refero MCP to search a library of over 150,000 screens and 6,000 user flows. This extracts actionable patterns to guide the landing page design process from discovery to final output.

Does this AI design methodology require any specific design frameworks or dependencies?

This AI design methodology requires no external dependencies. It operates independently using internal scripts, references, and assets to guide the AI agent through the research, analysis, and design implementation process.

Can I use this approach to design an onboarding flow for a new application?

Yes, you can use this approach to design onboarding flows. It ensures the AI agent researches existing successful user flows and applies professional craft guidance for typography, motion, and icons before generating the interface design.

What is the best way to apply craft standards to AI-generated UI components?

The best way to apply craft standards to AI-generated UI is by providing detailed rules on typography, color, spacing, motion, and icons. This Skill enforces these professional craft standards during implementation to ensure polished execution and prevent generic layouts.

Why does my AI design output lack professional polish and spacing?

AI design output lacks professional polish when it bypasses real-world research and established craft standards. This Skill solves the problem by extracting actionable patterns from a vast screen library and enforcing specific rules for typography, color, and spacing.