claude-user/skills/design/SKILL.md
Unified design system for data/ML dashboards. Quick reference for brand vs data color decisions, component patterns, typography, spacing. Auto-invokes on styling, CSS, design, colors, UI, visualization keywords. Tiered loading - core always, philosophy/implementation on-demand.
npx skillsauth add ilyasibrahim/claude-agents-coordination designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
UI element or data visualization?
Never mix brand and data colors in same context.
--tableau-blue: #0176D3; /* Primary CTA */
--tableau-navy: #032D60; /* Headings, nav */
--tableau-green: #00A651; /* Success */
--tableau-bg-light: #EAF5FE; /* Backgrounds */
--tableau-text: #333333; /* Body text */
--tableau-border: #EBEBEB; /* Borders */
--data-1: #33BBEE; /* Primary cyan */
--data-2: #0077BB; /* Primary blue */
--data-3: #66CCEE; /* Light cyan */
--data-4: #4477AA; /* Light blue */
--data-5: #44AA99; /* Teal */
--data-error: #EE6677; /* Red (errors) */
--data-neutral: #BBBBBB; /* Grey (baseline) */
Sequence: ['#33BBEE', '#0077BB', '#66CCEE', '#4477AA', '#44AA99']
--font-heading: 'Space Grotesk', sans-serif;
--font-body: 'Inter', sans-serif;
--font-code: 'Fira Code', monospace;
--text-hero: 2.25rem; /* 36px */
--text-h1: 1.875rem; /* 30px */
--text-h2: 1.5rem; /* 24px */
--text-body: 1rem; /* 16px */
--text-small: 0.875rem; /* 14px */
--space-2: 0.5rem; /* 8px */
--space-4: 1rem; /* 16px */
--space-6: 1.5rem; /* 24px */
--space-8: 2rem; /* 32px - card padding */
--space-12: 3rem; /* 48px - section gap */
--shadow-sm: 0 1px 3px rgba(0,0,0,0.1), 0 1px 2px rgba(0,0,0,0.1);
--shadow-md: 0 4px 6px rgba(0,0,0,0.1), 0 2px 4px rgba(0,0,0,0.1);
--shadow-lg: 0 10px 15px rgba(0,0,0,0.1), 0 4px 6px rgba(0,0,0,0.05);
.btn-primary {
background: var(--tableau-blue);
color: white;
padding: 14px 32px;
border-radius: 6px;
}
.btn-primary:hover { transform: translateY(-2px); }
.card {
background: white;
border: 1px solid var(--tableau-border);
border-radius: 16px;
padding: var(--space-8);
box-shadow: var(--shadow-sm);
}
.data-card {
border-top: 4px solid var(--data-1);
}
.data-card__value {
color: var(--data-2);
font-size: var(--text-h1);
font-family: var(--font-heading);
}
const chartColors = ['#33BBEE', '#0077BB', '#66CCEE', '#4477AA', '#44AA99'];
new Chart(ctx, {
data: {
datasets: [
{ backgroundColor: chartColors[0] },
{ backgroundColor: chartColors[1] }
]
},
options: {
plugins: {
legend: { labels: { color: '#333333' } } // Brand for UI
}
}
});
For philosophy and full implementation details:
skills/design/philosophy.mdskills/design/implementation.mdVersion: 3.0.0
documentation
Voice, tone, and content guidelines for data/ML dashboards. Covers microcopy, error messages, success states, and data presentation language. Auto-invokes on copy, messaging, content, labels, error messages keywords.
development
Coordination protocol for main Claude Code agent. Explicit user invocation required ("mobilize agents", "coordinate", "check registry"). Provides agent orchestration, registry management, and handoff protocols. Subagents never access this - main agent provides context in task prompts.
development
Model evaluation metrics, testing protocols, and performance assessment for Somali dialect classification. Covers accuracy, F1-score, confusion matrix analysis, per-dialect performance, and evaluation best practices for multi-class classification tasks.
testing
MLOps best practices for model versioning, experiment tracking, deployment, monitoring, and retraining workflows. Covers reproducibility, CI/CD for ML, model registry, and production ML system design.