frontend-designer
Skill4 starsChanged 13 days agoMITView on GitHub
This skill should be used when the user asks to "design a UI", "plan component architecture", "improve accessibility", "optimize frontend performance", or discusses UI/UX patterns. Provides pragmatic frontend design guidance with ADHD-friendly patterns.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- kozz36/frontend-designer-skilltheir own version, first seen Nov 1, 2026
- Samueladewole/claude-skillstheir own version, first seen Oct 13, 2026
- matos-ed/skillstheir own version, first seen Oct 11, 2026
- app-dev-panel/app-dev-paneltheir own version, first seen Oct 8, 2026
- A70III/ateliertheir own version, first seen Sep 22, 2026
- jamesrochabrun/skillstheir own version, first seen Nov 18, 2025
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- jamesrochabrun/skills★ 209same name
- app-dev-panel/app-dev-panel★ 91same name
- kozz36/frontend-designer-skill★ 9same name
- matos-ed/skills★ 1same name
- A70III/atelier★ 0same name
- Samueladewole/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 repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- system-architectSkill
- project-detectorSkill
- audit-routerSkill
- command-skill-token-efficiencySkill
- plugin-auditSkill
- sync-featuresSkill
- backend-designerSkill
- devops-helperSkill
- git-workflowSkill
- dist-extrasSkill
- distribution-strategistSkill
- homebrew-formula-expertSkill
- homebrew-multi-formulaSkill
- homebrew-setup-wizardSkill
- homebrew-workflow-expertSkill
- architecture-decision-recordsSkill
- changelog-automationSkill
- claude-md-lifecycleSkill
- guard-auditSkill
- hooksSkill
- insights-applySkill
- mode-controllerSkill
- drive-engineSkill
- plan-orchestratorSkill
- repo-triageSkill
- session-stateSkill
- task-analyzerSkill
- workflow-engineSkill
- orchestrator-resilienceSkill
- project-plannerSkill
- preflight-checkSkill
- releaseSkill
- test-generatorSkill
- test-strategistSkill
- adhd-workflowSkill
- brainstorm-insightsSkill
- brainstormSkill
- grillSkill
- prompt-refinerSkill
- background-task-managerSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
6
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 66
Use wizards for multi-step processes
- Distinctive: line 74
Start with Tailwind/Bootstrap, customize later
- Distinctive: line 75
Use proven component libraries (shadcn/ui, Headless UI)
- Distinctive: line 88
When analysis is needed, I will:
- Distinctive: line 91
Delegate to agents: when feasible:
- Very specific: line 95
Run in background: - Use Task tool with run_in_background: true
- Distinctive: line 114
When activated, I provide:
“Common” is measured: kept by at least 6 in 10 of the 5 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 Designer Skill
Auto-activated when: User discusses UI/UX, component architecture, accessibility, or frontend design decisions.
Core Capabilities
1. Component Architecture
- Component composition patterns
- Props vs state decisions
- Component reusability strategies
- Folder structure (colocation vs separation)
- Design system integration
2. UI/UX Patterns
- Layout patterns (grid, flexbox, responsive)
- Navigation patterns (tabs, drawer, breadcrumbs)
- Form design (validation, error handling, multi-step)
- Loading states and skeletons
- Empty states and error boundaries
3. Accessibility (A11y)
- WCAG compliance checklist
- Semantic HTML
- ARIA labels and roles
- Keyboard navigation
- Screen reader compatibility
- Color contrast (ADHD-friendly palettes)
4. Performance
- Code splitting strategies
- Lazy loading images/components
- Virtual scrolling for long lists
- Debouncing/throttling user input
- Bundle size optimization
ADHD-Friendly Design Patterns
Visual Hierarchy:
- Clear focus states (bold borders, high contrast)
- Reduce visual clutter (progressive disclosure)
- Consistent spacing (8px grid system)
- Limited color palette (3-5 colors max)
Interaction Design:
- Immediate feedback (loading spinners, success states)
- Undo/redo capabilities
- Auto-save (reduce "did I save?" anxiety)
- Confirmation dialogs for destructive actions
- Keyboard shortcuts for common actions
Cognitive Load Reduction:
- One primary action per screen
- Hide advanced options behind "Advanced" toggle
- Use wizards for multi-step processes
- Provide templates/presets
- Clear error messages with next steps
Design Philosophy: Solid Indie
Ship Fast Principles:
- Start with Tailwind/Bootstrap, customize later
- Use proven component libraries (shadcn/ui, Headless UI)
- Mobile-first responsive design
- Accessibility from day one (easier than retrofitting)
Anti-Patterns to Avoid:
- ❌ Custom design system before 10K users
- ❌ Over-abstraction (generic
<Button>with 20 props) - ❌ Premature animation (ship functionality first)
- ❌ Pixel-perfect designs (80% is shipping)
Delegation Strategy
When analysis is needed, I will:
- Quick assessment - Identify design problem
- Delegate to agents when feasible:
ux-ui-designeragent for comprehensive UX reviewexperienced-engineeragent for component architectureaccessibilityspecialist for a11y audit
- Run in background - Use Task tool with
run_in_background: true - Synthesize results - Provide actionable design recommendations
Example Activation
User: "I need to design a form for creating tasks with due dates and tags"
Skill activates and provides:
1. Form layout recommendation (vertical, clear labels)
2. Accessibility checklist (ARIA labels, keyboard nav)
3. UX patterns (inline validation, auto-save, success feedback)
4. Component structure (controlled vs uncontrolled inputs)
5. Delegates UX review to ux-ui-designer agent (background)
6. Returns with comprehensive form implementation planOutput Format
When activated, I provide:
Immediate Response
- Pattern Recognition: Identify the UI/UX problem
- Quick Recommendation: Suggest proven pattern
- Accessibility Note: Key a11y considerations
- ADHD-Friendly Tip: Cognitive load reduction suggestion
Delegated Analysis (Background)
- Launch appropriate agent for UX/accessibility review
- Provide progress updates
- Synthesize findings
Final Output
- Recommended approach with rationale
- Component structure (props, state, composition)
- Accessibility checklist (WCAG items to address)
- Code example (React/Vue component structure)
- Next steps (what to build first)
Integration with Existing Workflow
- Auto-activates during
/brainstormfor UI/UX discussions - Works with
/next(suggests frontend implementation steps) - Integrates with
/done(captures design decisions, patterns used)
Pattern Library Integration
Common patterns I'll reference:
| Pattern | Use Case | Example |
| Progressive Disclosure | Complex forms | Show advanced fields behind toggle |
| Optimistic UI | Create/update actions | Show success immediately, rollback on error |
| Skeleton Screens | Loading states | Show layout while data loads |
| Virtual Scrolling | Long lists | Render only visible items |
| Toast Notifications | Non-blocking feedback | Success/error messages that auto-dismiss |
Remember: This skill auto-activates based on keywords. Keep responses focused, accessible, and ADHD-friendly (reduce cognitive load, immediate feedback, clear hierarchy).
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.

