ui-ux-design
Skill2 starsChanged 6 months agoMITView on GitHub
UI/UX design systems, Figma workflows, accessibility checklists, browser-based visual audit with automated screenshots, component specification patterns, and design-to-code handoff procedures. Use when designing interfaces, creating design systems, auditing accessibility, reviewing existing UI via browser screenshots, specifying components, or preparing design handoff for developers.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- mblauberg/provenanttheir own version, first seen Nov 15, 2026
- jDxve/avengers-kittheir own version, first seen Nov 8, 2026
- SWEStash/swe-workflow-skillstheir own version, first seen Nov 8, 2026
- delorenj/skillstheir own version, first seen Nov 7, 2026
- velonx/agent-skillstheir own version, first seen Nov 1, 2026
- rogue-dev-studio/ai-agents-roguetheir own version, first seen Nov 1, 2026
Used with
Projects with it also use prd-generator and security-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dhzrxSkillprd-generator
Generate comprehensive Product Requirements Documents with AI PM best practices for new features and products
Also in 3 projects that use this
SentrySkillsecurity-review
Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.
Also in 3 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- EmeaAppGbb/spec2cloud★ 100same name
- felvieira/claude-skills-fv★ 28same name
- arvindand/agent-skills★ 17same name
- delorenj/skills★ 17same name
- crgarcia12/Liliput★ 4same name
- hahuyhungdev/ai-coding-config★ 3same name
- AntJanus/skillbox★ 2same name
- rogue-dev-studio/ai-agents-rogue★ 2same name
- augments-labs/sdlc-skills★ 1same name
- hicay/claude-code-skills★ 1same name
10 more not listed
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 repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-skillsSkill
- analyze-localSkill
- analyze-prodSkill
- analyzeSkill
- architectureSkill
- asset-validationSkill
- blog-postSkill
- bugfixSkill
- cloud-platformsSkill
- code-reviewSkill
- content-creationSkill
- context-engineeringSkill
- create-prSkill
- deployment-proceduresSkill
- deploy-productionSkill
- deploy-stagingSkill
- docsSkill
- feature-devSkill
- geo-writerSkill
- humanizerSkill
- infra-changeSkill
- marketing-operationsSkill
- marketingSkill
- ml-pipelineSkill
- planSkill
- pre-commitSkill
- productSkill
- project-initSkill
- prompt-engineeringSkill
- qaSkill
- releaseSkill
- run-testsSkill
- security-scanSkill
- seo-reviewSkill
- social-media-managerSkill
- test-localSkill
- test-strategySkill
- worktree-isolationSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Before creating a design system:
- Distinctive: line 39
Inconsistency map: Document where the same concept is implemented differently
- Distinctive: line 58
Follow Atomic Design progression:
- Distinctive: line 67
States: Default, hover, focus, active, disabled, loading, error
- Distinctive: line 109
When handing off designs to developers, provide:
“Common” is measured: kept by at least 6 in 10 of the 18 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
UI/UX Design
Systematic UI/UX design skill with design system creation guides, Figma workflow patterns, accessibility audit checklists, browser-based visual audit procedures, and design-to-code handoff templates. Produces consistent, accessible, conversion-optimized interfaces.
When to Use
- Creating or extending a design system (tokens, components, patterns)
- Designing new pages, features, or user flows
- Auditing existing UI for accessibility compliance
- Preparing design specifications for developer handoff
- Setting up Figma project structure and workflows
- Reviewing existing UI via automated browser screenshots and heuristic analysis
- Reviewing UI components against heuristics and platform guidelines
When NOT to Use
- Writing page content or copy (use
content-creationskill) - Implementing frontend code (use
frontend-engineerrole) - Conducting SEO audits (use
seo-reviewskill workflow) - Writing technical documentation (use
docsskill workflow)
Design System Creation
Step 1: Audit Existing UI
Before creating a design system:
- Screenshot inventory: Capture all existing screens and components
- Pattern extraction: Identify recurring colors, typography, spacing, components
- Inconsistency map: Document where the same concept is implemented differently
- Priority matrix: Rank components by frequency of use × inconsistency severity
Step 2: Define Foundations
Build from the ground up:
| Foundation | What to Define | Token Naming |
| Color | Brand, semantic, neutral, overlay palettes | color-{category}-{shade} |
| Typography | Font families, size scale, weights, line heights | font-{property}-{size} |
| Spacing | Base unit (4px or 8px), scale | spacing-{size} |
| Border radius | Scale from none to full | radius-{size} |
| Elevation | Shadow levels | shadow-{level} |
| Motion | Duration, easing curves | motion-{property}-{variant} |
| Breakpoints | Viewport thresholds | breakpoint-{name} |
Step 3: Build Components
Follow Atomic Design progression:
- Atoms: Button, Input, Label, Icon, Badge, Avatar, Checkbox, Radio, Toggle
- Molecules: Input Group, Search Bar, Card, Dropdown, Tooltip, Alert, Breadcrumb
- Organisms: Header, Footer, Sidebar, Form, Data Table, Modal, Navigation
For each component, document:
- Variants: Primary, secondary, outline, ghost, destructive
- Sizes: xs, sm, md, lg, xl
- States: Default, hover, focus, active, disabled, loading, error
- Accessibility: ARIA role, keyboard behavior, screen reader announcement
- Responsive: Behavior at each breakpoint
- Do / Don't: Usage examples and anti-patterns
Step 4: Document and Maintain
- Publish component library with live examples
- Version with semantic versioning
- Changelog for every update
- Deprecation notices with migration guides
See design-system-checklist.md for the full creation checklist.
Figma Workflow
See figma-workflow.md for detailed Figma project setup, component organization, Auto Layout patterns, and developer handoff procedures.
Quick Reference
| Figma Concept | Code Equivalent |
| Auto Layout | Flexbox / CSS Grid |
| Component variants | React props / variant configs |
| Design tokens (Variables) | CSS custom properties |
| Constraints | CSS positioning / responsive rules |
| Component instances | React component usage |
Accessibility Audit
See accessibility-checklist.md for the comprehensive WCAG 2.2 AA audit checklist.
Quick Audit (5-Minute Check)
- Tab through the page — can you reach and operate every interactive element?
- Zoom to 200% — does content reflow without horizontal scrolling?
- Check contrast — do all text elements meet 4.5:1 (normal) / 3:1 (large)?
- Screen reader test — do headings, landmarks, and alt text make sense?
- Keyboard-only — can you complete the primary task without a mouse?
Design-to-Code Handoff Template
When handing off designs to developers, provide:
## Component: [Name]
### Visual Spec
- Dimensions: [width × height or fluid]
- Spacing: [padding, margin in token values]
- Colors: [background, text, border in token values]
- Typography: [font, size, weight, line-height in token values]
- Border: [width, style, color, radius in token values]
- Shadow: [elevation token]
### Variants
- [variant-name]: [visual differences]
### States
- Default: [spec]
- Hover: [changes from default]
- Focus: [focus indicator spec]
- Active: [changes]
- Disabled: [opacity, cursor, interaction]
### Responsive Behavior
- Mobile (< 640px): [layout changes]
- Tablet (640–1024px): [layout changes]
- Desktop (> 1024px): [default layout]
### Interactions
- [trigger] → [animation: property, duration, easing]
### Accessibility
- Role: [ARIA role if not implicit]
- Keyboard: [key bindings]
- Screen reader: [announcement text]
### Code Reference
- Component: `<ComponentName variant="..." size="..." />`
- Tokens: `--token-name: value`Integration
- Follows rules:
ui-ux-designerrole (design principles, accessibility, design systems) - Used by workflows:
ui-ux-designskill (primary),feature-devskill (UI features) - Companion resources:
design-system-checklist.md,figma-workflow.md,accessibility-checklist.md,visual-audit-checklist.md
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.

