frontend-design-fix
について
このスキルは、タイポグラフィ、カラー、モーション、空間構成、背景の5つの核心的な次元にわたって審美的なアップグレードを適用することで、一般的なフロントエンドデザインを変革します。一般的なデザインの欠陥を診断し、技術に依存しない原則を提供するとともに、フレームワーク固有の実装を参照します。フロントエンドコードの視覚的魅力を体系的に高め、予測可能なデザインパターンを打破するためにご活用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/matteocervelli/llmsgit clone https://github.com/matteocervelli/llms.git ~/.claude/skills/frontend-design-fixこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
Frontend Design Fix Skill
Overview
This orchestrator skill diagnoses generic design patterns and applies targeted aesthetic upgrades across five design dimensions. Fixes are tech-agnostic (principles) but reference framework-specific implementation skills.
The 5 Dimensions:
- Typography – Replace generic fonts, fix weight hierarchies, aggressive size jumps
- Color & Theme – Remove predictable palettes, introduce CSS variables, add dominant + accent strategy
- Motion – Add orchestrated page loads, staggered reveals, hover surprises
- Spatial Composition – Break centered layouts, introduce asymmetry, adjust spacing strategy
- Backgrounds & Details – Layer gradients, add geometric patterns, create atmospheric depth
Quick Diagnosis
"What's wrong with my design?"
It looks like a template → See ./sub-skills/audit.md
Font choices feel default → See ./sub-skills/typography-fixes.md
Color palette is predictable → See ./sub-skills/color-fixes.md
Everything's static and boring → See ./sub-skills/motion-fixes.md
Layout is centered and uniform → See ./sub-skills/spatial-fixes.md
Backgrounds are flat/plain → See ./sub-skills/background-fixes.md
5-Phase Fix Process
Phase 1: Audit
Identify generic elements, score anti-patterns, assess brand context
→ See ./sub-skills/audit.md
Phase 2: Assess Brand & Context
Understand emotional intent, target audience, competitive differentiation
Phase 3: Apply Dimension-Based Fixes
- Typography fixes (typeface, weights, size jumps)
- Color fixes (palette strategy, CSS variables, accents)
- Motion fixes (orchestration, scroll triggers, hover)
- Spatial fixes (asymmetry, overlap, diagonal flow)
- Background fixes (gradients, patterns, depth)
→ See specific sub-skills below
Phase 4: Validate Improvements
- Visual hierarchy strengthened?
- Brand personality evident?
- Accessibility maintained (WCAG AA+)?
- Performance acceptable?
Phase 5: Generate Before/After Report
Document improvements, measure impact, establish design guidelines
Anti-Pattern Detection Checklist
Typography
- Using Inter, Roboto, Open Sans, Lato, or system fonts
- Font weights in safe middle range (400, 500, 600 only)
- Size progression is linear/minimal (1.25–1.5x scale)
Color
- Material Design trinity (Blue, Red, Green)
- Oversaturated neon accents
- No color strategy document or CSS variable structure
Layout
- Everything is centered (hero, cards, sections)
- Uniform padding/margins everywhere
- Symmetric, grid-based composition only
Motion
- No animations at all
- Linear timing on all transitions
- Slow, sluggish animations (2s+)
Background
- Flat solid colors throughout
- No visual depth or layering
- No contextual details or micro-patterns
Sub-Skills Reference
| Sub-Skill | Purpose | Lines |
|---|---|---|
audit.md | Design audit checklist and scoring | ~100 |
typography-fixes.md | Font replacement, weight hierarchy, size jumps | ~100 |
color-fixes.md | Palette overhaul, CSS variables, accent strategy | ~100 |
motion-fixes.md | Orchestrated animations, scroll triggers, hover | ~100 |
spatial-fixes.md | Break centered layout, asymmetry, spacing | ~100 |
background-fixes.md | Gradients, patterns, textures, depth | ~100 |
When to Use This Skill
✅ Design audit reveals generic patterns or lack of differentiation ✅ Existing design feels "AI-generated" or template-like ✅ Need to upgrade without complete redesign ✅ Applying brand personality to standardized UI ✅ Want to improve motion, hierarchy, or visual depth ✅ Building stronger design system foundations
Getting Started
- Run the audit →
./sub-skills/audit.md - Identify weakest dimensions → Anti-pattern checklist above
- Apply targeted fixes → Follow relevant sub-skill(s)
- Validate improvements → Phase 4 checklist
- Document changes → Generate before/after report
Related Skills
- frontend-design – Create new designs (principles-first approach)
- frontend-design-react – React + Vite implementation
- frontend-design-vue – Vue 3 implementation
- frontend-design-svelte – Svelte implementation
- frontend-design-html – Static HTML/CSS implementation
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
creating-opencode-plugins
メタThis skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.
polymarket
メタThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
