Install any skill in seconds. Free to start, no credit card required.
Get Started Free →UI design system toolkit covering design tokens, component documentation, responsive calculations, and developer handoff. Use for creating design systems, maintaining visual consistency, or facilitating design-dev handoff.
.claude/skills/borghei-ui-design-system/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 101% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 202% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 207% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 167% | 0% |
Generate design tokens, create color palettes, calculate typography scales, build component systems, and prepare developer handoff documentation.
Use this skill when you need to:
Before generating the tokens or system, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Situation: You have a brand color and need a complete design token system.
Steps:
modern | classic | playfulbash python scripts/design_token_generator.py "#0066CC" modern json
bash # CSS custom properties python scripts/design_token_generator.py "#0066CC" modern css > design-tokens.css
# SCSS variables python scripts/design_token_generator.py "#0066CC" modern scss > _design-tokens.scss
# JSON for Figma/tooling python scripts/design_token_generator.py "#0066CC" modern json > design-tokens.json
Situation: You need to structure a component library using design tokens.
Steps:
| Component | Tokens Used | |-----------|-------------| | Button | colors, sizing, borders, shadows, typography | | Input | colors, sizing, borders, spacing | | Card | colors, borders, shadows, spacing | | Modal | colors, shadows, spacing, z-index, animation |
Size variants: sm: height 32px, paddingX 12px, fontSize 14px md: height 40px, paddingX 16px, fontSize 16px lg: height 48px, paddingX 20px, fontSize 18px
Color variants: primary: background primary-500, text white secondary: background neutral-100, text neutral-900 ghost: background transparent, text neutral-700
references/component-architecture.mdSituation: You need breakpoints, fluid typography, or responsive spacing.
Steps:
| Name | Width | Target | |------|-------|--------| | xs | 0 | Small phones | | sm | 480px | Large phones | | md | 640px | Tablets | | lg | 768px | Small laptops | | xl | 1024px | Desktops | | 2xl | 1280px | Large screens |
Formula: clamp(min, preferred, max)
css /* 16px to 24px between 320px and 1200px viewport */ font-size: clamp(1rem, 0.5rem + 2vw, 1.5rem);
Pre-calculated scales: css --fluid-h1: clamp(2rem, 1rem + 3.6vw, 4rem); --fluid-h2: clamp(1.75rem, 1rem + 2.3vw, 3rem); --fluid-h3: clamp(1.5rem, 1rem + 1.4vw, 2.25rem); --fluid-body: clamp(1rem, 0.95rem + 0.2vw, 1.125rem);
| Token | Mobile | Tablet | Desktop | |-------|--------|--------|---------| | --space-md | 12px | 16px | 16px | | --space-lg | 16px | 24px | 32px | | --space-xl | 24px | 32px | 48px | | --space-section | 48px | 80px | 120px |
references/responsive-calculations.mdSituation: You need to hand off design tokens to development team.
Steps:
bash # For CSS projects python scripts/design_token_generator.py "#0066CC" modern css
# For SCSS projects python scripts/design_token_generator.py "#0066CC" modern scss
# For JavaScript/TypeScript python scripts/design_token_generator.py "#0066CC" modern json
React + CSS Variables: tsx import './design-tokens.css';
<button className="btn btn-primary">Click</button>
Tailwind Config: javascript const tokens = require('./design-tokens.json');
module.exports = { theme: { colors: tokens.colors, fontFamily: tokens.typography.fontFamily } };
styled-components: typescript import tokens from './design-tokens.json';
const Button = styled.button background: ${tokens.colors.primary['500']}; padding: ${tokens.spacing['2']} ${tokens.spacing['4']}; ;
references/developer-handoff.mdGenerates complete design token system from brand color.
| Argument | Values | Default | Description | |----------|--------|---------|-------------| | brand_color | Hex color | #0066CC | Primary brand color | | style | modern, classic, playful | modern | Design style preset | | format | json, css, scss, summary | json | Output format |
Examples:
bash# Generate JSON tokens (default) python scripts/design_token_generator.py "#0066CC" # Classic style with CSS output python scripts/design_token_generator.py "#8B4513" classic css # Playful style summary view python scripts/design_token_generator.py "#FF6B6B" playful summary
Output Categories:
| Category | Description | Key Values | |----------|-------------|------------| | colors | Color palettes | primary, secondary, neutral, semantic, surface | | typography | Font system | fontFamily, fontSize, fontWeight, lineHeight | | spacing | 8pt grid | 0-64 scale, semantic (xs-3xl) | | sizing | Component sizes | container, button, input, icon | | borders | Border values | radius (per style), width | | shadows | Shadow styles | none through 2xl, inner | | animation | Motion tokens | duration, easing, keyframes | | breakpoints | Responsive | xs, sm, md, lg, xl, 2xl | | z-index | Layer system | base through notification |
| Step | Brightness | Saturation | Use Case | |------|------------|------------|----------| | 50 | 95% fixed | 30% | Subtle backgrounds | | 100 | 95% fixed | 38% | Light backgrounds | | 200 | 95% fixed | 46% | Hover states | | 300 | 95% fixed | 54% | Borders | | 400 | 95% fixed | 62% | Disabled states | | 500 | Original | 70% | Base/default color | | 600 | Original × 0.8 | 78% | Hover (dark) | | 700 | Original × 0.6 | 86% | Active states | | 800 | Original × 0.4 | 94% | Text | | 900 | Original × 0.2 | 100% | Headings |
| Size | Value | Calculation | |------|-------|-------------| | xs | 10px | 16 ÷ 1.25² | | sm | 13px | 16 ÷ 1.25¹ | | base | 16px | Base | | lg | 20px | 16 × 1.25¹ | | xl | 25px | 16 × 1.25² | | 2xl | 31px | 16 × 1.25³ | | 3xl | 39px | 16 × 1.25⁴ | | 4xl | 49px | 16 × 1.25⁵ | | 5xl | 61px | 16 × 1.25⁶ |
| Level | Normal Text | Large Text | |-------|-------------|------------| | AA | 4.5:1 | 3:1 | | AAA | 7:1 | 4.5:1 |
Large text: ≥18pt regular or ≥14pt bold
| Aspect | Modern | Classic | Playful | |--------|--------|---------|---------| | Font Sans | Inter | Helvetica | Poppins | | Font Mono | Fira Code | Courier | Source Code Pro | | Radius Default | 8px | 4px | 16px | | Shadows | Layered, subtle | Single layer | Soft, pronounced |
Detailed reference guides in references/:
| File | Content | |------|---------| | token-generation.md | Color algorithms, HSV space, WCAG contrast, type scales | | component-architecture.md | Atomic design, naming conventions, props patterns | | responsive-calculations.md | Breakpoints, fluid typography, grid systems | | developer-handoff.md | Export formats, framework setup, Figma sync |
| Problem | Cause | Solution | |---------|-------|----------| | Generated colors fail WCAG contrast | Brand color too light or too saturated | Use darker shades (600+) for text on light backgrounds; check with contrast tool | | Token export has incorrect values | Wrong format argument or color syntax | Ensure hex color is quoted (e.g. "#0066CC"); verify format is json, css, or scss | | Typography scale too large/small | Default 1.25x ratio doesn't fit design | Modify type_scale_ratio in DesignTokenGenerator class (1.125 for tighter, 1.333 for looser) | | SCSS variables conflict with existing | Token naming collision | Prefix all tokens with project namespace (edit export function) | | Design tools show different colors | Hex rounding in color scale generation | Use JSON export as source of truth; sync with Tokens Studio plugin | | Spacing values don't align with grid | Custom spacing mixed with 8pt grid | Use only values from the generated spacing system; avoid arbitrary pixel values | | Shadow tokens look wrong in dark mode | Shadows designed for light backgrounds | Create separate dark-mode shadow tokens with lighter opacity values |
| Criterion | Target | How to Measure | |-----------|--------|----------------| | Token consistency | Zero hardcoded color/spacing values in codebase | Lint rule violations count | | WCAG AA compliance | All text colors meet 4.5:1 contrast ratio | Automated contrast checker or manual audit | | Export format coverage | CSS, SCSS, and JSON all generate correctly | Run generator with each format; validate output | | Design-dev sync | <24h between token update and code deployment | Time from Figma change to production | | Component token coverage | 100% of components use design tokens | Audit component styles for hardcoded values | | Typography consistency | All text uses design system type scale | Visual audit across all pages | | Responsive behavior | Fluid typography works across all breakpoints | Test at xs, sm, md, lg, xl, 2xl widths |
In scope:
Out of scope:
| Tool / Platform | Integration Method | Use Case | |-----------------|-------------------|----------| | Figma / Tokens Studio | Import JSON output as token source | Sync design tool with code tokens | | Tailwind CSS | JSON tokens as tailwind.config.js theme | Configure Tailwind from design system | | styled-components / Emotion | Import JSON tokens in theme provider | CSS-in-JS theming | | Style Dictionary | Use JSON output as source tokens | Multi-platform token build (iOS, Android, web) | | Storybook | Pair tokens with component stories | Document component visual variations | | CI/CD | Token generation in build pipeline | Automated token updates on brand change |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 29,970 | 20,585 | -31% | 1 | 1 | 0% | 6,215 | 8,878 | +43% | 0 | 0 | — |
case-02 | fail→pass | 28,977 | 22,094 | -24% | 1 | 1 | 0% | 5,509 | 8,652 | +57% | 0 | 0 | — |
case-03 | fail→fail | 22,563 | 22,792 | +1% | 1 | 1 | 0% | 4,210 | 8,817 | +109% | 0 | 0 | — |
case-08 | fail→pass | 13,330 | 4,263 | -68% | 1 | 1 | 0% | 2,481 | 4,985 | +101% | 0 | 0 | — |
case-04 | fail→fail | 22,667 | 31,011 | +37% | 1 | 1 | 0% | 4,086 | 10,331 | +153% | 0 | 0 | — |
case-05 | fail→fail | 15,063 | 19,942 | +32% | 1 | 1 | 0% | 2,997 | 8,042 | +168% | 0 | 0 | — |
case-06 | fail→fail | 14,348 | 17,339 | +21% | 1 | 1 | 0% | 2,659 | 7,402 | +178% | 0 | 0 | — |
case-07 | pass→pass | 9,239 | 10,121 | +10% | 1 | 1 | 0% | 1,951 | 6,214 | +219% | 0 | 0 | — |
case-09 | fail→pass | 15,263 | 16,273 | +7% | 1 | 1 | 0% | 2,472 | 7,463 | +202% | 0 | 0 | — |
case-10 | pass→pass | 15,632 | 10,273 | -34% | 1 | 1 | 0% | 2,385 | 6,151 | +158% | 0 | 0 | — |
case-11 | fail→pass | 8,550 | 3,833 | -55% | 1 | 1 | 0% | 1,579 | 4,849 | +207% | 0 | 0 | — |
case-12 | fail→fail | 14,686 | 13,357 | -9% | 1 | 1 | 0% | 3,186 | 6,984 | +119% | 0 | 0 | — |
case-13 | fail→fail | 15,111 | 14,341 | -5% | 1 | 1 | 0% | 2,789 | 6,932 | +149% | 0 | 0 | — |
case-22 | fail→pass | 12,191 | 7,543 | -38% | 1 | 1 | 0% | 2,126 | 5,668 | +167% | 0 | 0 | — |
case-14 | pass→pass | 8,369 | 6,075 | -27% | 1 | 1 | 0% | 1,450 | 5,180 | +257% | 0 | 0 | — |
case-15 | pass→pass | 9,193 | 3,810 | -59% | 1 | 1 | 0% | 1,401 | 4,715 | +237% | 0 | 0 | — |
case-16 | pass→pass | 14,064 | 11,223 | -20% | 1 | 1 | 0% | 2,583 | 6,178 | +139% | 0 | 0 | — |
case-17 | fail→pass | 11,188 | 11,921 | +7% | 1 | 1 | 0% | 2,150 | 6,335 | +195% | 0 | 0 | — |
case-18 | pass→pass | 10,792 | 6,021 | -44% | 1 | 1 | 0% | 1,744 | 5,103 | +193% | 0 | 0 | — |
case-19 | pass→pass | 14,540 | 11,137 | -23% | 1 | 1 | 0% | 2,181 | 6,008 | +175% | 0 | 0 | — |
case-20 | fail→pass | 15,610 | 6,074 | -61% | 1 | 1 | 0% | 2,501 | 5,278 | +111% | 0 | 0 | — |
case-21 | pass→pass | 6,857 | 3,492 | -49% | 1 | 1 | 0% | 1,159 | 4,665 | +303% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.