mcpbeat Sign in

Frontend Design Agent Skill

Design thinking and decision-making for web UI.

34k tokens
context cost
the whole folder, loaded on every use
37
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
505
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI --skill frontend-design

What comes with it

131 728 bytes besides the instruction
animation-guide.md
color-system.md
decision-trees.md
motion-graphics.md
scripts/accessibility_checker.py
scripts/ux_audit.py
sub-skills/60-30-10-rule.md
sub-skills/8-point-grid-concept.md
sub-skills/ai-tendency-patterns-avoid.md
sub-skills/audience-design-approach.md
sub-skills/color-psychology-for-decision-making.md
sub-skills/core-laws-internalize-these.md
sub-skills/dark-patterns-unethical.md
sub-skills/default-tendencies-to-avoid-anti-safe-harbor.md
sub-skills/easing-selection.md
sub-skills/emotional-design-levels.md
sub-skills/emotional-triggers.md
sub-skills/glassmorphism-when-appropriate.md
sub-skills/golden-ratio-1618.md
sub-skills/gradient-usage.md
sub-skills/key-sizing-principles.md
sub-skills/lazy-design-indicators.md
sub-skills/pairing-concept.md
sub-skills/performance.md
sub-skills/premium-indicators.md
sub-skills/readability-rules.md
sub-skills/scale-selection.md
sub-skills/selection-process.md
sub-skills/shadow-hierarchy.md
sub-skills/timing-concept.md
sub-skills/trust-builders.md
sub-skills/trust-building.md
sub-skills/when-user-prompt-is-vague-ask.md
typography-system.md
ux-psychology.md
visual-effects.md

The instruction itself

32 sections, as written by the author

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:

| File | Status | When to Read |

|------|--------|--------------|

| ux-psychology.md | 🔴 REQUIRED | Always read first! |

| color-system.md | ⚪ Optional | Color/palette decisions |

| typography-system.md | ⚪ Optional | Font selection/pairing |

| visual-effects.md | ⚪ Optional | Glassmorphism, shadows, gradients |

| animation-guide.md | ⚪ Optional | Animation needed |

| motion-graphics.md | ⚪ Optional | Lottie, GSAP, 3D |

| decision-trees.md | ⚪ Optional | Context templates |

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


🔧 Runtime Scripts

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

| Script | Purpose | Usage |

|--------|---------|-------|

| scripts/ux_audit.py | UX Psychology & Accessibility Audit | python 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.

🧠 Knowledge Modules (Fractal Skills)

1. When User Prompt is Vague, ASK:

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

3. Audience → Design Approach

4. Core Laws (Internalize These)

5. Emotional Design Levels

6. Trust Building

7. Golden Ratio (φ = 1.618)

8. 8-Point Grid Concept

9. Key Sizing Principles

10. 60-30-10 Rule

11. Color Psychology (For Decision Making)

12. Selection Process

13. Scale Selection

14. Pairing Concept

15. Readability Rules

16. Glassmorphism (When Appropriate)

17. Shadow Hierarchy

18. Gradient Usage

19. Timing Concept

20. Easing Selection

21. Performance

22. Premium Indicators

23. Trust Builders

24. Emotional Triggers

25. ❌ Lazy Design Indicators

26. ❌ AI Tendency Patterns (AVOID!)

27. ❌ Dark Patterns (Unethical)

Other skills for the same job

different authors, same section of the catalogue
Theme Factory
by anthropics
vendor ×16

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

36k tokens
Brand Guidelines
by anthropics
vendor ×13

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

3k tokens
Artifacts Builder
by JayZeeDesign
×8

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

11k tokens scripts
Web Artifacts Builder
by anthropics
vendor ×7

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

11k tokens scripts
Frontend Design
by Karanjot786
×6

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

1k tokens
Frontend Design
by anthropics
vendor ×4

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

5k tokens
Expo Tailwind Setup
by openai
vendor ×4

Set up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling

3k tokens
Use Dom
by openai
vendor ×3

Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.

3k tokens

How to use it

Copy the folder

Take dokhacgiakhoa/frontend-design from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.