Communitygithub.com

majiayu000/claude-skill-registry

Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.

What is claude-skill-registry?

claude-skill-registry is a Claude Code agent skill that design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/majiayu000/claude-skill-registry/tree/HEAD/skills/design/frontend-design-congdon1207-agents-md

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Frontend Design System

Philosophy: Every pixel has purpose. Restraint is luxury. User psychology drives decisions. Core Principle: THINK, don't memorize. ASK, don't assume.


🎯 Selective Reading Rule (MANDATORY)

Read REQUIRED files always, OPTIONAL only when needed:

FileStatusWhen to Read
ux-psychology.md🔴 REQUIREDAlways read first!
color-system.md⚪ OptionalColor/palette decisions
typography-system.md⚪ OptionalFont selection/pairing
visual-effects.md⚪ OptionalGlassmorphism, shadows, gradients
animation-guide.md⚪ OptionalAnimation needed
motion-graphics.md⚪ OptionalLottie, GSAP, 3D
decision-trees.md⚪ OptionalContext templates

🔴 ux-psychology.md = ALWAYS READ. Others = only if relevant.


🔧 Runtime Scripts

Execute these for audits (don't read, just run):

ScriptPurposeUsage
scripts/ux_audit.pyUX Psychology & Accessibility Auditpython scripts/ux_audit.py <project_path>

⚠️ CRITICAL: ASK BEFORE ASSUMING (MANDATORY)

STOP! If the user's request is open-ended, DO NOT default to your favorites.

When User Prompt is Vague, ASK:

Color not specified? Ask:

"What color palette do you prefer? (blue/green/orange/neutral/other?)"

Style not specified? Ask:

"What style are you going for? (minimal/bold/retro/futuristic/organic?)"

Layout not specified? Ask:

"Do you have a layout preference? (single column/grid/asymmetric/full-width?)"

⛔ DEFAULT TENDENCIES TO AVOID (ANTI-SAFE HARBOR):

AI Default TendencyWhy It's BadThink Instead
Bento Grids (Modern Cliché)Used in every AI designWhy does this content NEED a grid?
Hero Split (Left/Right)Predictable & BoringHow about Massive Typography or Vertical Narrative?
Mesh/Aurora GradientsThe "new" lazy backgroundWhat's a radical color pairing?
GlassmorphismAI's idea of "premium"How about solid, high-contrast flat?
Deep Cyan / Fintech BlueSafe harbor from purple banWhy not Red, Black, or Neon Green?
"Orchestrate / Empower"AI-generated copywritingHow would a human say this?
Dark background + neon glowOverused, "AI look"What does the BRAND actually need?
Rounded everythingGeneric/SafeWhere can I use sharp, brutalist edges?

🔴 "Every 'safe' structure you choose brings you one step closer to a generic template. TAKE RISKS."


1. Constraint Analysis (ALWAYS FIRST)

Before any design work, ANSWER THESE or ASK USER:

ConstraintQuestionWhy It Matters
TimelineHow much time?Determines complexity
ContentReady or placeholder?Affects layout flexibility
BrandExisting guidelines?May dictate colors/fonts
TechWhat stack?Affects capabilities
AudienceWho exactly?Drives all visual decisions

Audience → Design Approach

AudienceThink About
Gen ZBold, fast, mobile-first, authentic
MillennialsClean, minimal, value-driven
Gen XFamiliar, trustworthy, clear
BoomersReadable, high contrast, simple
B2BProfessional, data-focused, trust
LuxuryRestrained elegance, whitespace

2. UX Psychology Principles

Core Laws (Internalize These)

LawPrincipleApplication
Hick's LawMore choices = slower decisionsLimit options, use progressive disclosure
Fitts' LawBigger + closer = easier to clickSize CTAs appropriately
Miller's Law~7 items in working memoryChunk content into groups
Von RestorffDifferent = memorableMake CTAs visually distinct
Serial PositionFirst/last remembered mostKey info at start/end

Emotional Design Levels

VISCERAL (instant)  → First impression: colors, imagery, overall feel
BEHAVIORAL (use)    → Using it: speed, feedback, efficiency
REFLECTIVE (memory) → After: "I like what this says about me"

Trust Building

  • Security indicators on sensitive actions
  • Social proof where relevant
  • Clear contact/support access
  • Consistent, professional design
  • Transparent policies

3. Layout Principles

Golden Ratio (φ = 1.618)

Use for proportional harmony:
├── Content : Sidebar = roughly 62% : 38%
├── Each heading size = previous × 1.618 (for dramatic scale)
├── Spacing can follow: sm → md → lg (each × 1.618)

8-Point Grid Concept

All spacing and sizing in multiples of 8:
├── Tight: 4px (half-step for micro)
├── Small: 8px
├── Medium: 16px
├── Large: 24px, 32px
├── XL: 48px, 64px, 80px
└── Adjust based on content density

Key Sizing Principles

ElementConsideration
Touch targetsMinimum comfortable tap size
ButtonsHeight based on importance hierarchy
InputsMatch button height for alignment
CardsConsistent padding, breathable
Reading width45-75 characters optimal

4. Color Principles

60-30-10 Rule

60% → Primary/Background (calm, neutral base)
30% → Secondary (supporting areas)
10% → Accent (CTAs, highlights, attention)

Color Psychology (For Decision Making)

If You Need...Consider HuesAvoid
Trust, calmBlue familyAggressive reds
Growth, natureGreen familyIndustrial grays
Energy, urgencyOrange, redPassive blues
Luxury, creativityDeep Teal, Gold, EmeraldCheap-feeling brights
Clean, minimalNeutralsOverwhelming color

Selection Process

  1. What's the industry? (narrows options)
  2. What's the emotion? (picks primary)
  3. Light or dark mode? (sets foundation)
  4. ASK USER if not specified

For detailed color theory: color-system.md


5. Typography Principles

Scale Selection

Content TypeScale RatioFeel
Dense UI1.125-1.2Compact, efficient
General web1.25Balanced (most common)
Editorial1.333Readable, spacious
Hero/display1.5-1.618Dramatic impact

Pairing Concept

Contrast + Harmony:
├── DIFFERENT enough for hierarchy
├── SIMILAR enough for cohesion
└── Usually: display + neutral, or serif + sans

Readability Rules

  • Line length: 45-75 characters optimal
  • Line height: 1.4-1.6 for body text
  • Contrast: Check WCAG requirements
  • Size: 16px+ for body on web

For detailed typography: typography-system.md


6. Visual Effects Principles

Glassmorphism (When Appropriate)

Key properties:
├── Semi-transparent background
├── Backdrop blur
├── Subtle border for definition
└── ⚠️ **WARNING:** Standard blue/white glassmorphism is a modern cliché. Use it radically or not at all.

Shadow Hierarchy

Elevation concept:
├── Higher elements = larger shadows
├── Y-offset > X-offset (light from above)
├── Multiple layers = more realistic
└── Dark mode: may need glow instead

Gradient Usage

Harmonious gradients:
├── Adjacent colors on wheel (analogous)
├── OR same hue, different lightness
├── Avoid harsh complementary pairs
├── 🚫 **NO Mesh/Aurora Gradients** (floating blobs)
└── VARY from project to project radically

For complete effects guide: visual-effects.md


7. Animation Principles

Timing Concept

Duration based on:
├── Distance (further = longer)
├── Size (larger = slower)
├── Importance (critical = clear)
└── Context (urgent = fast, luxury = slow)

Easing Selection

ActionEasingWhy
EnteringEase-outDecelerate, settle in
LeavingEase-inAccelerate, exit
EmphasisEase-in-outSmooth, deliberate
PlayfulBounceFun, energetic

Performance

  • Animate only transform and opacity
  • Respect reduced-motion preference
  • Test on low-end devices

For animation patterns: animation-guide.md, for advanced: motion-graphics.md


8. "Wow Factor" Checklist

Premium Indicators

  • Generous whitespace (luxury = breathing room)
  • Subtle depth and dimension
  • Smooth, purposeful animations
  • Attention to detail (alignment, consistency)
  • Cohesive visual rhythm
  • Custom elements (not all defaults)

Trust Builders

  • Security cues where appropriate
  • Social proof / testimonials
  • Clear value proposition
  • Professional imagery
  • Consistent design language

Emotional Triggers

  • Hero that evokes intended emotion
  • Human elements (faces, stories)
  • Progress/achievement indicators
  • Moments of delight

9. Anti-Patterns (What NOT to Do)

❌ Lazy Design Indicators

  • Default system fonts without consideration
  • Stock imagery that doesn't match
  • Inconsistent spacing
  • Too many competing colors
  • Walls of text without hierarchy
  • Inaccessible contrast

❌ AI Tendency Patterns (AVOID!)

  • Same colors every project
  • Dark + neon as default
  • Purple/violet everything (PURPLE BAN ✅)
  • Bento grids for simple landing pages
  • Mesh Gradients & Glow Effects
  • Same layout structure / Vercel clone
  • Not asking user preferences

❌ Dark Patterns (Unethical)

  • Hidden costs
  • Fake urgency
  • Forced actions
  • Deceptive UI
  • Confirmshaming

10. Decision Process Summary

For EVERY design task:

1. CONSTRAINTS
   └── What's the timeline, brand, tech, audience?
   └── If unclear → ASK

2. CONTENT
   └── What content exists?
   └── What's the hierarchy?

3. STYLE DIRECTION
   └── What's appropriate for context?
   └── If unclear → ASK (don't default!)

4. EXECUTION
   └── Apply principles above
   └── Check against anti-patterns

5. REVIEW
   └── "Does this serve the user?"
   └── "Is this different from my defaults?"
   └── "Would I be proud of this?"

Reference Files

For deeper guidance on specific areas:


Related Skills

SkillWhen to Use
frontend-design (this)Before coding - Learn design principles (color, typography, UX psychology)
web-design-guidelinesAfter coding - Audit for accessibility, performance, and best practices

Post-Design Workflow

After implementing your design, run the audit:

1. DESIGN   → Read frontend-design principles ← YOU ARE HERE
2. CODE     → Implement the design
3. AUDIT    → Run web-design-guidelines review
4. FIX      → Address findings from audit

Next Step: After coding, use web-design-guidelines skill to audit your implementation for accessibility, focus states, animations, and performance issues.


Remember: Design is THINKING, not copying. Every project deserves fresh consideration based on its unique context and users. Avoid the Modern SaaS Safe Harbor!

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

majiayu000/claude-skill-registry

Builds, edit or validate Agent Skill through conversational discovery. Use when the user requests to "Create an Agent", "Optimize an Agent" or "Edit an Agent".

majiayu000/claude-skill-registry

Edit existing BMAD agents while maintaining compliance

majiayu000/claude-skill-registry

Edit existing BMAD agents while maintaining compliance

majiayu000/claude-skill-registry

Edit existing BMAD modules while maintaining coherence

majiayu000/claude-skill-registry

Edit existing BMAD modules while maintaining coherence

majiayu000/claude-skill-registry

Analyzes current state and user query to answer BMad questions or recommend the next workflow or agent. Use when user says what should I do next, what do I do now, or asks a question about BMad

majiayu000/claude-skill-registry

Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.

majiayu000/claude-skill-registry

Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.

majiayu000/claude-skill-registry

Portfolio allocation and rebalancing optimizer. Manages asset allocation across stocks/cash/bonds, performs periodic rebalancing, and ensures diversification according to market regime and risk tolerance.

majiayu000/claude-skill-registry

Create a hilarious and ultra-realistic video of an anthropomorphic animal acting like a human vlogger in a real-world setting.

majiayu000/claude-skill-registry

Speech-to-text transcription and translation via OpenAI Audio API -- models, response formats, timestamps, prompting, streaming, chunking, and diarization

majiayu000/claude-skill-registry

BlockRun works with Claude Code and Google Antigravity.

majiayu000/claude-skill-registry

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

majiayu000/claude-skill-registry

小省导购员数字人带货版即梦视频提示词生成系统,基于四大智能体协同(提示词生成师、质量管控师、知识库运维师、跨环节适配师),按照"主体+运动+场景+(镜头语言+光影+氛围)"公式输出中英文双版提示词,适配5s短视频。确保人物一致性、视觉连贯性、情绪连贯性,支持知识库智能复用和跨工具适配(Suno音乐、AI绘画),为数字人带货视频提供高质量提示词生成服务。

majiayu000/claude-skill-registry

Upload and manage files using Google Gemini File API via scripts/. Use for uploading images, audio, video, PDFs, and other files for use with Gemini models. Supports file upload, status checking, and file management. Triggers on "upload file", "file API", "upload image", "upload PDF", "upload video", "file management".

majiayu000/claude-skill-registry

CRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLM

majiayu000/claude-skill-registry

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

majiayu000/claude-skill-registry

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

majiayu000/claude-skill-registry

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

majiayu000/claude-skill-registry

Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.

Related Skills