frontend-design-ui-ux
Skill15 starsChanged 8 months agoApache-2.0View on GitHub
Design user interfaces with comprehensive UX methodology. Produces implementation-ready specifications, component briefs, and design tokens for handoff to Next.js and React engineering agents. Use when designing new features, creating design systems, planning user flows, or specifying component behavior.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- liushikuan63/Qoder-Optimizationtheir own version, first seen Nov 1, 2026
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
- sanyamk23/aphanistheir own version, first seen Sep 9, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- sanyamk23/aphanis★ 3same name
- liushikuan63/Qoder-Optimization★ 2same name
- davidanthonyn/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository63 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- ast-grepSkill
- branch-review-before-prSkill
- browse-qaSkill
- browser-useSkill
- browseSkill
- bugfixSkill
- build-dmgSkill
- claude-reviewSkill
- codemapSkill
- code-simplifySkill
- codex-reviewSkill
- commitSkill
- cost-estimateSkill
- create-prSkill
- find-agentsSkill
- find-bugsSkill
- git-merge-expertSkill
- git-merge-expert-worktreeSkill
- kiro-reviewSkill
- laravel-filamentSkill
- laravelSkill
- lokeiSkill
- map-project-monorepoSkill
- map-projectSkill
- nextjsSkill
- plan-founder-reviewSkill
- plan-to-task-list-with-dagSkill
- pr-retroSkill
- run-parallel-agents-feature-buildSkill
- run-parallel-agents-feature-debugSkill
- rustSkill
- secretsSkill
- startSkill
- update-agent-learningsSkill
- update-claude-learningsSkill
- update-claude-settingsSkill
- update-skill-learningsSkill
- ast-grepSkill
- branch-review-before-prSkill
- codemapSkill
- code-simplifySkill
- commitSkill
- cost-estimateSkill
- create-prSkill
- find-bugsSkill
- frontend-design-ui-uxSkill
- git-merge-expertSkill
- git-merge-expert-worktreeSkill
- map-project-monorepoSkill
- map-projectSkill
- plan-founder-reviewSkill
- plan-to-task-list-with-dagSkill
- pr-retroSkill
- run-parallel-agents-feature-buildSkill
- run-parallel-agents-feature-debugSkill
- startSkill
- update-agent-learningsSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 12 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Before designing, gather context:
- Distinctive: line 32
When do they need it? (frequency, urgency, duration)
- Distinctive: line 56
Document every state the UI can be in:
- Very specific: line 158
Use these templates in references/ directory:
- Distinctive: line 165
Before handoff to engineering agent, verify:
- Distinctive: line 181
Ask before adding "nice to have" features
- Distinctive: line 182
Keep specifications focused on requested functionality
- Distinctive: line 185
After discovery: Confirm understanding
- Distinctive: line 186
After IA: Validate user flows
- Distinctive: line 187
After component design: Review specs
- Distinctive: line 188
Before handoff: Final quality check
- Distinctive: line 191
When specifications are complete, clearly indicate:
- Distinctive: line 210
Do NOT implement code directly.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Frontend Design UI/UX Skill
Purpose
This is a design skill, not an implementation skill. It produces:
- Design artifacts and specifications
- Component briefs with TypeScript interfaces
- User flow documentation
- Design tokens and system definitions
- Clear handoff instructions for implementation
Target Agents:
nextjs-senior-engineer- For SSR, SEO-critical, App Router projectsreact-vite-tailwind-engineer- For SPAs, CLI web UIs, Electron apps
Design Methodology
Phase 1: Discovery
Before designing, gather context:
User Research Questions:
- Who are the primary users? (roles, technical level, accessibility needs)
- What problem are they solving?
- Where will they use this? (device, context, environment)
- When do they need it? (frequency, urgency, duration)
- Why this feature now? (business goal, user pain point)
Context Analysis:
- Existing patterns in the codebase
- Design system constraints
- Tech stack limitations
- Performance requirements
- Accessibility requirements (WCAG 2.1 AA minimum)
Phase 2: Information Architecture
Content Inventory:
- List all data/content to display
- Identify required vs optional fields
- Define content hierarchy
User Flow Mapping:
- Entry points (how users arrive)
- Decision points (branching logic)
- Exit points (success, error, abandon)
- Edge cases and error states
State Mapping: Document every state the UI can be in:
- Loading (initial, refresh, pagination)
- Empty (first use, no results, filtered empty)
- Partial (incomplete data, degraded)
- Success (complete, confirmed)
- Error (validation, network, permission, timeout)
Phase 3: Component Design
Atomic Design Hierarchy:
- Atoms - Basic elements (Button, Input, Icon, Text)
- Molecules - Simple combinations (SearchInput, FormField, Card)
- Organisms - Complex sections (Header, ProductList, CommentThread)
- Templates - Page layouts (DashboardLayout, AuthLayout)
- Pages - Specific instances (UserDashboard, LoginPage)
For Each Component, Define:
- Purpose (one sentence)
- Variants (visual/behavioral variations)
- Props with TypeScript types
- All possible states
- Responsive behavior at breakpoints
- Accessibility requirements
Phase 4: Interaction Design
User Interactions:
| Interaction | Trigger | Feedback | Duration |
| Click/Tap | Mouse/Touch | Visual + State change | Instant |
| Hover | Mouse enter | Visual highlight | - |
| Focus | Tab/Click | Focus ring | - |
| Drag | Mouse down + move | Ghost + Drop zones | Continuous |
| Swipe | Touch move | Momentum scroll | Gesture-based |
Feedback Patterns:
- Loading: Skeleton, spinner, progress bar
- Success: Toast, inline confirmation, redirect
- Error: Inline message, toast, modal (severity-based)
- Progress: Step indicator, progress bar, percentage
Animation Specifications:
const animations = {
duration: {
instant: '0ms',
fast: '150ms',
normal: '300ms',
slow: '500ms',
},
easing: {
default: 'cubic-bezier(0.4, 0, 0.2, 1)',
in: 'cubic-bezier(0.4, 0, 1, 1)',
out: 'cubic-bezier(0, 0, 0.2, 1)',
bounce: 'cubic-bezier(0.68, -0.55, 0.265, 1.55)',
},
}Phase 5: Design Tokens
Define tokens for consistency across implementations:
Colors:
- Semantic naming (primary, secondary, destructive)
- Full scale for each (50-900)
- Light/dark mode variants
Typography:
- Font families (sans, mono, serif if needed)
- Size scale (xs through 4xl)
- Weight scale (normal, medium, semibold, bold)
- Line heights (tight, normal, relaxed)
Spacing:
- Base unit: 0.25rem (4px)
- Scale: 0, 1, 2, 3, 4, 5, 6, 8, 10, 12, 16, 20, 24, 32, 40, 48, 64
Other Tokens:
- Border radius (none, sm, md, lg, full)
- Shadows (sm, md, lg, xl)
- Z-index layers (base, dropdown, sticky, modal, toast)
- Breakpoints (sm: 640px, md: 768px, lg: 1024px, xl: 1280px)
Phase 6: Engineer Handoff
Agent Selection Logic:
| Criteria | Agent |
| Server-side rendering needed | nextjs-senior-engineer |
| SEO critical | nextjs-senior-engineer |
| App Router / Server Components | nextjs-senior-engineer |
| API routes / Server Actions | nextjs-senior-engineer |
| Pure SPA / client-only | react-vite-tailwind-engineer |
| CLI with web UI | react-vite-tailwind-engineer |
| Electron/Tauri app | react-vite-tailwind-engineer |
| Static site with no SSR | Either (ask user) |
| Unclear | Ask user |
Output Templates
Use these templates in references/ directory:
component-spec-template.md- Full component specificationsuser-flow-template.md- User journey documentationdesign-tokens-template.md- Token system definition
Quality Checklist
Before handoff to engineering agent, verify:
- States: All states documented (loading, error, empty, success, partial)
- Responsive: Breakpoints defined with specific behavior changes
- Accessibility: ARIA roles, keyboard nav, screen reader announcements
- Interactions: All user interactions mapped with feedback
- Animations: Specifications included (or explicitly marked as none)
- Types: Props typed with TypeScript interfaces
- Edge Cases: Identified and handling specified
- Target Agent: Specified with selection reasoning
- Acceptance Criteria: Clear, testable requirements
Session Management
Scope Control:
- Confirm scope before expanding beyond initial request
- Ask before adding "nice to have" features
- Keep specifications focused on requested functionality
Checkpoints:
- After discovery: Confirm understanding
- After IA: Validate user flows
- After component design: Review specs
- Before handoff: Final quality check
Handoff Signals: When specifications are complete, clearly indicate:
## Ready for Implementation
Target Agent: [nextjs-senior-engineer | react-vite-tailwind-engineer]
The following specifications are ready for implementation:
1. [Component/Flow name] - [brief description]
2. ...
Invoke the target agent with these specifications to begin implementation.Integration with Other Skills
This skill produces specifications that are consumed by:
nextjs-senior-engineer- Implements Next.js componentsreact-vite-tailwind-engineer- Implements React/Vite components
Do NOT implement code directly. Always hand off to the appropriate engineering agent.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

