Communitygithub.com

leonxlnx/stitch-design-taste

Habilidade de Sistema de Design Semântico para Google Stitch. Gera arquivos DESIGN.md que impõem padrões de UI premium e antigênéricos — tipografia rigorosa, cor calibrada, layouts assimétricos, micromovimento perpétuo e desempenho acelerado por hardware.

O que é stitch-design-taste?

Esta habilidade, projetada para o Google Stitch, define um gosto de design semântico rigoroso e premium. Ela gera automaticamente arquivos `DESIGN.md` que codificam padrões de UI exigentes para combater a estética genérica. As diretrizes incluem tipografia estrita com hierarquia clara, paletas de cores calibradas para consistência e contraste, layouts assimétricos que quebram a simetria previsível, micromovimentos perpétuos para engajamento sutil e desempenho acelerado por hardware para transições suaves. Útil para agentes de IA e desenvolvedores humanos que desejam criar interfaces sofisticadas e distintas, a habilidade garante que o design resultante pareça intencional e polido, alinhado com os princípios da Google Stitch. O arquivo `DESIGN.md` gerado serve como um contrato de design executável, guiando a implementação com especificações concretas em vez de descrições vagas, tornando-o ideal para pipelines de desenvolvimento automatizados com agentes como Claude Code ou Cursor.

Funciona com~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/leonxlnx/taste-skill/tree/main/skills/stitch-design-taste

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

O que stitch-design-taste faz?

Habilidade de Sistema de Design Semântico para Google Stitch. Gera arquivos DESIGN.md que impõem padrões de UI premium e antigênéricos — tipografia rigorosa, cor calibrada, layouts assimétricos, micromovimento perpétuo e desempenho acelerado por hardware.

Visão Geral

Esta habilidade define um gosto de design semântico e rigoroso para ser aplicado automaticamente por agentes de IA (como Claude Code, Cursor ou Codex) ao gerar código de interface de usuário para o ecossistema Google Stitch. O resultado é um arquivo DESIGN.md que serve como guia de estilo executável, garantindo que cada componente, página ou fluxo siga um padrão visual premium e coeso.

Por que usar?

  • Antigênérico: Combate a homogeneização visual comum em frameworks de UI.
  • Semântico: As decisões de design são baseadas em intenção e contexto, não em aparência.
  • Executável por Agente: O arquivo DESIGN.md gerado é estruturado para que agentes de IA possam interpretá-lo e aplicá-lo consistentemente.
  • Focado em Performance: Exige hardware-accelerated rendering e animações otimizadas (60fps+).

Público-Alvo

  • Desenvolvedores que usam Google Stitch para criar produtos internos ou externos.
  • Equipes de design e engenharia que desejam manter um padrão visual alto sem fricção manual.
  • Agentes de IA que precisam de diretrizes de design explícitas e não ambíguas.

Como Funciona

  1. Invocação: O agente (ex.: Claude) chama esta habilidade no contexto de um projeto Stitch.
  2. Geração: A habilidade analisa o contexto do projeto e gera um arquivo DESIGN.md na raiz ou em uma pasta de design.
  3. Aplicação: O agente usa o DESIGN.md como referência para estilizar componentes, layouts e animações.

Princípios de Design (do DESIGN.md gerado)

  • Tipografia: Apenas fontes system-ui, com escala modular e hierarquia estrita (ex.: h1: 2rem/1.2, h2: 1.5rem/1.3).
  • Cor: Paleta reduzida (2-3 cores primárias + neutros), com contraste WCAG AA mínimo. Cores calibradas para consistência perceptual.
  • Layout: Assimetria intencional, quebra de grid previsível, uso de espaços em branco generosos.
  • Micro-movimento: Transições sutis (Like 0.2s ease-out), hover states com escala ou opacidade, loading states animados. Nunca animações gratuitas.
  • Performance: Uso de will-change, transform: translateZ(0), e contain: layout style paint para hardware acceleration.

Exemplo de Uso

# Supondo que o agente tenha esta habilidade carregada
stitch generate component Button --design-taste premium

Ou, em um prompt para Claude:

Use a habilidade leonxlnx/stitch-design-taste para gerar um DESIGN.md para este projeto.

Dependências

  • Google Stitch (versão 2023.1 ou superior)
  • Node.js 18+ (para execução local de scripts de design)
  • Agente de IA compatível (Claude, Cursor, Codex, etc.)

Licença

MIT

Contribuição

Pull requests são bem-vindos. Por favor, abra uma issue primeiro para discutir mudanças significativas.


Criado para elevar o padrão visual da Stitch.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

leonxlnx/design-taste-frontend

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

leonxlnx/design-taste-frontend-v1

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

leonxlnx/full-output-enforcement

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

leonxlnx/gpt-taste

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

leonxlnx/high-end-visual-design

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

leonxlnx/image-taste-frontend

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

leonxlnx/image-to-code

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

leonxlnx/industrial-brutalist-ui

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

leonxlnx/minimalist-ui

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

leonxlnx/redesign-existing-projects

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

leonxlnx/taste-skill

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

leonxlnx/taste-skill

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

leonxlnx/taste-skill

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

leonxlnx/taste-skill

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

leonxlnx/taste-skill

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

leonxlnx/taste-skill

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

leonxlnx/taste-skill

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.

leonxlnx/taste-skill

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

leonxlnx/taste-skill

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

leonxlnx/taste-skill

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Habilidades Relacionadas