ui-ux-expert-skill
Technical workflow for implementing accessible React user interfaces with shadcn/ui, Tailwind CSS, and TanStack Query. Includes 6-phase process with mandatory Style Guide compliance, Context7 best practices consultation, Chrome DevTools validation, and WCAG 2.1 AA accessibility standards. Use after Test Agent, Implementer, and Supabase agents complete their work.
Install
mkdir -p .claude/skills/ui-ux-expert-skill && curl -L -o skill.zip "https://mcp.directory/api/skills/download/284" && unzip -o skill.zip -d .claude/skills/ui-ux-expert-skill && rm skill.zipInstalls to .claude/skills/ui-ux-expert-skill
About this skill
UI/UX Expert Technical Skill
Version: 1.0.0 Agent: ui-ux-expert Last Updated: 2025-01-26
Purpose
This skill provides the complete technical workflow for implementing accessible, performant React user interfaces that:
- Pass 100% of E2E tests without modification
- Comply with WCAG 2.1 AA accessibility standards
- Follow the project's Style Guide exactly
- Achieve Core Web Vitals green metrics
- Integrate with implemented use cases (not data services directly)
6-PHASE WORKFLOW (MANDATORY)
PHASE 0: Style Guide Study (MANDATORY FIRST STEP)
Objective: Internalize the project's visual design system before ANY implementation.
⚠️ CRITICAL: This is the FIRST step. All implementations must reference the Style Guide.
Steps:
-
Read Style Guide completely:
Read('.claude/STYLE_GUIDE.md') -
Memorize key constraints:
- Color Palette: 5 brand colors (Brand-1 through Brand-5) + semantic tokens
- NO arbitrary hex values (e.g.,
bg-[#4A5FFF]is PROHIBITED) - ONLY use semantic tokens:
bg-primary,text-foreground,border, etc.
- NO arbitrary hex values (e.g.,
- Typography Scale:
text-xsthroughtext-4xlONLY- NO arbitrary font sizes (e.g.,
text-[32px]is PROHIBITED)
- NO arbitrary font sizes (e.g.,
- Spacing Scale:
spacing-1(4px) throughspacing-24(96px) ONLY- NO arbitrary values (e.g.,
p-[17px]is PROHIBITED)
- NO arbitrary values (e.g.,
- Animation Durations: 200ms, 300ms, or 500ms ONLY
- NO other durations
- Border Radius:
--radiusvariable (default 0.5rem)
- Color Palette: 5 brand colors (Brand-1 through Brand-5) + semantic tokens
-
Note component conventions:
- Hover states:
hover:bg-accent,hover:shadow-lg - Focus states:
focus:ring-2 focus:ring-ring - Disabled states:
disabled:opacity-50 disabled:cursor-not-allowed - Dark mode: automatic via
.darkclass
- Hover states:
Deliverable: Mental model of Style Guide constraints to apply during implementation.
PHASE 1: Component Research (BEFORE Design)
Objective: Consult Context7 and shadcn MCP for latest best practices BEFORE designing components.
⚠️ CRITICAL: Research first, design second. Avoid implementing outdated patterns.
Steps:
-
Context7: React patterns (MANDATORY)
mcp__context7__get_library_docs({ context7CompatibleLibraryID: "/reactjs/react.dev", topic: "hooks useEffect useState useMemo useCallback custom hooks best practices", tokens: 2500 })Extract: Latest Hook patterns, composition strategies, performance tips
-
Context7: Next.js App Router (MANDATORY)
mcp__context7__get_library_docs({ context7CompatibleLibraryID: "/vercel/next.js", topic: "client components use client app router best practices", tokens: 2000 })Extract:
'use client'directive usage, routing hooks, data fetching -
Context7: Tailwind CSS (MANDATORY)
mcp__context7__get_library_docs({ context7CompatibleLibraryID: "/tailwindlabs/tailwindcss.com", topic: "responsive design mobile-first breakpoints animations utilities", tokens: 2000 })Extract: Responsive patterns, utility combinations, animation classes
-
Context7: TanStack Query (MANDATORY)
mcp__context7__get_library_docs({ context7CompatibleLibraryID: "/tanstack/query", topic: "useQuery useMutation optimistic updates error handling", tokens: 2500 })Extract: Data fetching patterns, cache invalidation, loading states
-
shadcn MCP: Component discovery (MANDATORY)
mcp__shadcn__search_items_in_registries({ registries: ['@shadcn'], query: "form input button card dialog", // Adjust based on feature limit: 20 }) mcp__shadcn__view_items_in_registries({ items: ['@shadcn/button', '@shadcn/form', '@shadcn/dialog'] })Extract: Available components, composition patterns, accessibility features
-
Additional Context7 queries (as needed):
- React Hook Form:
/react-hook-form/react-hook-form- "zodResolver validation errors" - Framer Motion (if animations needed):
/grx7/framer-motion- "variants spring animations"
- React Hook Form:
Deliverable: Notes on latest patterns to apply in design phase.
PHASE 2: Design Architecture (BEFORE Implementation)
Objective: Plan component hierarchy, state management, and user flows.
Steps:
-
Review E2E test specifications:
// Read E2E tests to understand required user flows Read('app/e2e/{feature}.spec.ts')Extract:
- Required
data-testidselectors - User interaction sequences
- Expected UI elements (buttons, forms, lists)
- Success/error state behaviors
- Required
-
Design component hierarchy:
## Component Architecture ### Page Level (app/(main)/{feature}/page.tsx) - Route container - TanStack Query for data fetching - Layout composition ### Feature Components (features/{feature}/components/) - {Feature}List - Display collection - {Feature}Form - Create/Edit form - {Feature}Dialog - Modal interactions ### Presentation Components - {Feature}Item - Single item card - {Feature}Filters - Filter controls - {Feature}Stats - Statistics display ### Base Components (shadcn/ui) - Button, Input, Card, Dialog (composition, not modification) -
Plan state management:
## State Strategy **Server State** (TanStack Query): - useQuery for reads (list, single item) - useMutation for writes (create, update, delete) - Query key structure: ['feature', ...params] **Form State** (React Hook Form): - Zod schema for validation - zodResolver integration - Accessible error messages **UI State** (Zustand - if needed): - Dialog open/close - Sidebar collapsed state - Theme preference (handled by next-themes) -
Design user flows:
## Flow 1: Create {Entity} 1. User clicks "Create" button → Opens dialog with form 2. User fills fields (real-time validation) 3. User submits → Loading state, disable form 4. Success: → Close dialog, toast notification, refetch list 5. Error: → Show error in form, keep dialog open, focus first error ## Flow 2: Edit {Entity} [Similar pattern...] ## Flow 3: Delete {Entity} [Similar pattern...] -
Plan accessibility patterns:
## Accessibility Design **Keyboard Navigation**: - Tab order: logical flow - Enter: submit forms, activate buttons - Escape: close dialogs - Arrow keys: navigate lists **ARIA Labels**: - Icon buttons: aria-label with context - Form fields: htmlFor + id association - Loading states: aria-busy - Error messages: aria-invalid + aria-describedby **Focus Management**: - Auto-focus first field on dialog open - Return focus to trigger on close - Focus trap in modals -
Plan responsive strategy:
## Responsive Design **Mobile (< 640px)**: - Single column layout - Stack cards vertically - Full-width buttons - Hide non-essential content **Tablet (640px - 1024px)**: - 2-column grid - Sidebar collapsible - Optimized spacing **Desktop (> 1024px)**: - 3-column grid - Fixed sidebar - Full feature set
Deliverable: Written design document covering hierarchy, state, flows, accessibility, and responsive strategy.
PHASE 3: Implementation (Following Design)
Objective: Build React components following the design from Phase 2.
🔐 CASL Integration (IF Authorization Required):
If E2E tests verify <Can> component visibility or the feature requires permission-based UI, implement CASL React integration FIRST before other components. See Pattern 0: CASL React Integration below.
Implementation Order (Bottom-Up):
-
CASL Integration (IF authorization required - implement FIRST)
- AbilityContext provider
- useAppAbility hook
- Load ability in layout/page
-
Form Components (Highest Priority)
- Complex, reusable
- React Hook Form + Zod validation
- Example:
CreateTaskForm.tsx
-
List/Display Components
- TanStack Query integration
- Loading and error states
- Example:
TaskList.tsx
-
Action Components
- Buttons, dialogs
- Wire up mutations
- Example:
CreateTaskDialog.tsx
-
Page Integration
- Compose all components
- Test user flows
- Example:
app/(main)/tasks/page.tsx
Code Patterns:
Pattern 0: CASL React Integration (IF Authorization Required)
When to implement: If E2E tests verify <Can> component visibility or PRD specifies permission-based UI.
Step 0.1: Create Ability Context
File: features/{feature}/context/AbilityContext.tsx
'use client';
import { createContext, useContext, type ReactNode } from 'react';
import type { AppAbility } from '../entities';
const AbilityContext = createContext<AppAbility | null>(null);
export function AbilityProvider({
ability,
children,
}: {
ability: AppAbility;
children: ReactNode;
}) {
return (
<AbilityContext.Provider value={ability}>
{children}
</AbilityContext.Provider>
);
}
export function useAppAbility() {
const ability = useContext(AbilityContext);
if (!ability) {
throw new Error('useAppAbility must be used within AbilityProvider');
}
return ability;
}
Step 0.2: Load Ability in Layout/Page
File: app/(main)/{feature}/layout.tsx or app/(main)/{feature}/page.tsx
import { loadUserAbility } from '@/features/{feature}/use-cases/loadUserAbility';
import { AbilityProvider } from '@/features/{feature}/context/AbilityContext';
import { createClient } from '@/lib/supabase-server';
import { redirect } from 'next/navigation';
export default async function FeatureLayout({
children,
}: {
children: React.ReactNode;
}) {
---
*Content truncated.*
You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversUnlock seamless Figma to code: streamline Figma to HTML with Framelink MCP Server for fast, accurate design-to-code work
Create modern React UI components instantly with Magic AI Agent. Integrates with top IDEs for fast, stunning design and
Boost AI coding agents with Ref Tools—efficient documentation access for faster, smarter code generation than GitHub Cop
Explore Magic UI, a React UI library offering structured component access, code suggestions, and installation guides for
Effortlessly manage Netlify projects with AI using the Netlify MCP Server—automate deployment, sites, and more via natur
FlyonUI is a React UI library for accessing component code, block metadata, and building workflows with conversational c
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.