avibebuilder/claude-prime / .claude/skills/frontend-design
frontend-design
VerifiedBuilds distinctive, production-grade UIs that avoid generic AI aesthetics. Use whenever the user wants to build, restyle, or give visual direction to any interface — pages, dashboards, landing pages, components, onboarding flows, mobile screens, or design systems — even without an explicit 'design' request. Also triggers for: picking an aesthetic direction, improving the look of a dull/generic existing page, adding visual personality, or choosing colors/typography. Includes a bundled design intelligence database for concrete guidance across web (React, Next.js, Vue, Tailwind) and mobile (React Native, Flutter, SwiftUI).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.2 KB |
| references/design-system-generation.md | markdown | 3.7 KB |
| references/quality-checklist.md | markdown | 2.7 KB |
| scripts/.gitignore | other | 24 B |
| scripts/core.pyexecutable | script | 4.6 KB |
| scripts/search.pyexecutable | script | 13.2 KB |
| scripts/tests/test_search.py | script | 8.8 KB |
references/design-system-generation.md
View on GitHub# Design System Generation Workflow
When generating a complete design system recommendation for a project, follow this multi-domain search orchestration.
## Workflow
### Step 1: Identify Product Category
```bash
python3 .claude/skills/frontend-design/scripts/search.py "user query" --domain products --top 1 --json
```
Extract `Product Type` from the result — this is the category (e.g., "SaaS", "E-Commerce", "FinTech").
### Step 2: Get Reasoning Rules
```bash
python3 .claude/skills/frontend-design/scripts/search.py "category from step 1" --domain ui-reasoning --top 1 --json
```
Extract from the result:
- `Style_Priority` — which styles to prioritize (e.g., "Glassmorphism + Flat Design")
- `Color_Mood` — color direction (e.g., "Trust blue + Accent contrast")
- `Typography_Mood` — font mood (e.g., "Professional + Hierarchy")
- `Key_Effects` — animation/effect guidelines
- `Anti_Patterns` — what to avoid
- `Decision_Rules` — conditional logic (JSON)
### Step 3: Multi-Domain Search
Run these searches independently, or in parallel when your environment supports it.
Use the style priority from Step 2 to weight the style search.
```bash
# Style — weighted by reasoning's Style_Priority
python3 .claude/skills/frontend-design/scripts/search.py "user query + style priority keywords" --domain styles --top 3 --json
# Colors — match product type
python3 .claude/skills/frontend-design/scripts/search.py "user query" --domain colors --top 2 --json
# Landing patterns
python3 .claude/skills/frontend-design/scripts/search.py "user query" --domain landing --top 2 --json
# Typography
python3 .claude/skills/frontend-design/scripts/search.py "user query" --domain typography --top 2 --json
```
### Step 4: Aggregate Best Matches
From the parallel search results, select:
| Domain | Selection Strategy |
|--------|--------------------|
| **Style** | Pick the result whose `Style Category` best matches the reasoning's `Style_Priority`. If multiple priorities (e.g., "Glassmorphism + Flat Design"), prefer the first. |
| **Colors** | Pick the top result matching the product type. |
| **Landing** | Pick the top result. Use `Section Order`, `Primary CTA Placement`, `Color Strategy`. |
| **Typography** | Pick the top result. Use `Heading Font`, `Body Font`, `Google Fonts URL`, `CSS Import`. |
### Step 5: Present Design System
Combine everything into a cohesive recommendation:
**Pattern**
- Name, section order, CTA placement from landing results
- Conversion strategy from landing's `Conversion Optimization`
**Style**
- Style name, keywords, effects from style results
- Performance and accessibility notes
**Colors**
- Primary, On Primary, Secondary, On Secondary, Accent, On Accent, Background, Foreground, and Border values from color results
- Use the paired "on" colors to preserve readable text and UI contrast on each surface
**Typography**
- Heading + Body font pairing
- Google Fonts URL and CSS Import for easy integration
- Mood keywords for context
**Effects & Animation**
- Combine style's `Effects & Animation` with reasoning's `Key_Effects`
**Anti-Patterns (what to avoid)**
- From reasoning's `Anti_Patterns`
- Always include: no emoji icons, cursor-pointer required, 4.5:1 contrast minimum
**Decision Rules (conditional guidance)**
- From reasoning's `Decision_Rules` JSON — present as "if X, then Y" guidance
## Example
Query: "SaaS analytics dashboard"
1. Products search → Category: "SaaS (General)"
2. Reasoning search → Style Priority: "Glassmorphism + Flat Design", Anti-patterns: "Excessive animation + Dark mode by default"
3. Parallel searches → Style: Glassmorphism, Colors: SaaS palette, Landing: SaaS Starter pattern, Typography: Professional pairing
4. Present unified recommendation with all sections above
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |