Claude/Codex/Cursor skill from the Tailwind CSS team that upgrades AI-generated UI from generic to designer-quality, in any existing project.
Qué hace
ui.sh Design is a Claude/Codex/Cursor skill that gives AI coding agents the instincts of a senior designer, steering output away from generic AI-generated UI toward layouts with real hierarchy, color, and typography craft. Built by the creators of Tailwind CSS and Refactoring UI, it installs via a s
AI coding agents ship UI fast, but the output has a fingerprint: purple palettes, text gradients, every section boxed into a card. ui.sh Design is a skill that rewires the agent's design judgment before it writes a single line. The result looks like a senior designer reviewed it, not like a model interpolated between a thousand Dribbble screenshots.
ui.sh comes from Adam Wathan (Tailwind CSS) and Steve Schoger (Refactoring UI), two people who have spent years codifying design intuition into teachable rules. The skill format packages that intuition as curated prompts, markdown guidelines, and reference examples that travel with the agent's context. Per the project's own framing: "The designs will look better, the implementations will be more robust, the code will be more accessible, and no one is going to look at it and immediately think 'great, another obviously AI-designed landing page.'"
Install once with npx, then prefix any UI prompt with /design. The skill guides the agent on layout hierarchy, color, spacing, typography, and component details. It builds within the project's existing framework, components, assets, and conventions, then checks the result across responsive breakpoints and interaction states. Pairing it with the ideas skill lets you spin up multiple design concepts in parallel and pick the direction you like.
The before/after examples in the docs show the gaps are often subtle: a login page without the skill looks competent but dated; with it, the spacing tightens, the social login buttons feel intentional, and the typographic hierarchy reads cleanly. The team notes most testing was done with Claude Code running the Opus model, and that's where the best results appear.
ui.sh is currently invite-only, and Wathan himself describes the current state as "uncomfortably early." The skill primitive it relies on is itself new, so the surface area and conventions are still evolving. That's a real consideration for teams who need production stability over cutting-edge output quality.
If you're already using Claude Code or Codex to build UI and you're tired of outputs that feel obviously AI-designed, ui.sh Design is the most direct fix available, backed by some of the strongest design-systems pedigree in the ecosystem. Get on the waitlist early; the underlying skill platform is moving fast.
Características
Notas de campo
Revisado el Jun 26, 2026
Ideal para
Resultados para creadores
Ten cuidado
Probado con
Profundiza
Independent review of ui.sh by a third-party design tools site, naming its creators (Adam Wathan, Steve Schoger) and positioning it as an AI design toolkit for coding agents with concrete context.
Independent hands-on early-access review of ui.sh specifically, describing its /ui skill, Tailwind CSS integration, and real user impressions of landing page and dashboard generation.
Independent newsletter covering ui.sh's architectural shift to local-first skills, providing a practitioner's snapshot of the product's evolution and concrete feature changes.
Staff engineer's independent comparative review of 10 AI UI skills, providing substantive critical analysis of the genre ui.sh belongs to and how such tools instruct AI agents.
ui.sh Design is an AI agent skill that gives coding agents like Claude Code, Codex, and Cursor the design judgment of a senior designer when generating UI. It works by injecting curated prompts, guidelines, and reference examples into the agent's context, steering decisions about layout, hierarchy, color, spacing, and typography. It was created by Adam Wathan (Tailwind CSS) and Steve Schoger (Refactoring UI), and is part of a broader suite of ui.sh skills for interface builders.
Install it by running `npx @uidotsh/install design --token=<your_token>` inside your project. Once installed, prefix any UI prompt with `/design` to activate the skill, for example `/design Create a login page for a SaaS application`. The skill works within your existing framework, components, and conventions, and checks results across responsive breakpoints and interaction states automatically.
ui.sh requires a token to install, indicating it is access-gated rather than freely open. The platform is currently invite-only, and pricing details are not publicly disclosed in the available sources. Wathan has described the current state as 'uncomfortably early,' so the commercial model may still be taking shape.
The Design skill is best for developers and teams who are already building UI with an AI coding agent and want to move the output quality from 'obviously AI-generated' to 'looks like a designer reviewed it.' It actively steers agents away from common AI tells like purple-heavy palettes, text gradients, and unnecessary card boxing, and it works within whatever framework and component library the project already uses.
ui.sh Design sits inside your existing agent workflow rather than requiring a separate design tool or IDE. Unlike tools such as TypeUI (which also offers design skills for Claude, Codex, and Cursor but as a standalone catalog), ui.sh integrates directly via MCP and a shell installer, meaning the skill travels with your project and respects your existing codebase conventions. The tradeoff is that ui.sh is invite-only and early, while alternatives may offer more immediate access.
The biggest limitation is access: ui.sh is invite-only and the creators describe it as 'uncomfortably early,' meaning stability, coverage, and conventions are still evolving. The best results are with Claude Code running the Opus model; other agents and models may produce weaker improvements. The skill primitive itself is new, so the surface area of what it covers will change as the platform matures.
Adam Wathan@adamwathan
Creator, Tailwind CSS
“So much of what makes a design looks visually great is matching your content to a design concept that fits your copy. With installed in your project, we'll point out to you when there's a mismatch and help you tweak the copy or find a bette…”
Sabatino Masala@sabatinomasala
“The skill refactored this boring table to an interactive receipt overview with refined UI elements, pretty neat. We already had the preview component available obviously, but the /ui skill glued everything together in a cohesive design.”
Una habilidad de IA que proporciona a los agentes de codificación inteligencia de diseño, reglas de razonamiento y estilos de interfaz para generar UI/UX profesional en distintas plataformas y frameworks.
Best for Arrancar un sistema de diseño a partir de la descripción de un proyecto.Una habilidad de diseño para Claude Code, Cursor y Codex que se niega a parecer generada por IA: elige una macroestructura para el encargo, aplica uno de veinte temas y ejecuta decenas de filtros anti-repetición antes de emitir el resultado.
Best for Diseñar UI que no parezca generada por IAHabilidades de agente para ingeniería real de Matt Pocock, en lugar de vibe coding: habilidades pequeñas, componibles e independientes del modelo (instalables mediante skills.sh), con una configuración guiada e integración con el gestor de incidencias.
Best for Alinear un agente antes de que escriba códigoOpen-source collection of 45+ AI agent skills for marketing, CRO, SEO, copywriting, analytics, and growth, built for Claude Code, Cursor, and any Agent Skills-compatible agent.
Best for Technical marketers and founders using Claude Code, Cursor, Windsurf, or OpenAI Codex who want marketing domain knowledge baked inOpen-source PM skills marketplace: 68 AI skills and 42 workflows across 9 Claude plugins for product managers doing discovery, strategy, execution, and launch.
Best for PMs using Claude Code or Claude Cowork who want framework-driven decisions baked into daily AI workflowsA catalog of repeatable AI agent workflows with built-in feedback loops, plus an installable skill for finding, adapting, and designing your own loops.
Best for Teams using Codex, Cursor, or Claude Code who want agents to iterate reliably instead of making one-shot guesses