agentleFS
xenitV1xenitV1/Antigravity-Workflows/skills/frontend-design/SKILL.md

frontend-design

Skill130 starsChanged 10 months agoMITView on GitHub

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.

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 180 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Color not specified?: Ask:

    line 48
  2. Distinctive:

    Style not specified?: Ask:

    line 51
  3. Distinctive:

    Layout not specified?: Ask:

    line 54
  4. Distinctive:

    Before any design work, ANSWER THESE or ASK USER:

    line 76
  5. Distinctive:

    ASK USER: if not specified

    line 189
  6. Distinctive:

    Contrast: Check WCAG requirements

    line 219
  7. Distinctive:

    Test on low-end devices

    line 288
  8. Distinctive:

    Default system fonts without consideration

    line 326

“Common” is measured: kept by at least 6 in 10 of the 180 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

  • color-system.md - Color theory and selection process
  • typography-system.md - Font pairing and scale decisions
  • visual-effects.md - Effects principles and techniques
  • animation-guide.md - Motion design principles
  • motion-graphics.md - Advanced: Lottie, GSAP, SVG, 3D, Particles
  • decision-trees.md - Context-specific templates
  • ux-psychology.md - User psychology deep dive

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

Download now (ZIP)

  • Other versions186 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 186

    1. anthropics/skills★ 186ksame name
    2. bytedance/deer-flow★ 84ksame name
    3. anthropics/claude-plugins-official★ 46ksame name
    4. novuhq/novu★ 40ksame name
    5. Dokploy/dokploy★ 38ksame name
    6. markmead/hyperui★ 12ksame name
    7. mengxi-ream/read-frog★ 10ksame name
    8. 1weiho/open-slide★ 9.3ksame name
    9. mfts/papermark★ 9.2ksame name
    10. papermark/papermark★ 9.2ksame name

    176 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use file-reading, brief-to-tasks and 9 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • SeifBenayedSkill

      file-reading

      Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.

      Also in 6 projects that use this

    • julianoczkowskiSkill

      brief-to-tasks

      Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

      Also in 7 projects that use this

    • vikneshwaran16032005-altSkill

      instantly-campaign

      Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.

      Also in 7 projects that use this

    • vikneshwaran16032005-altSkill

      albert-dm

      Reply to DMs and messages the way Albert would. Use when the user asks "how would Albert reply to this", pastes a conversation and wants an Albert-style response, or asks you to draft/write a DM in Albert's voice. Albert sells AI voice agents / automations to local service businesses (Go High Level, lead follow-up, bookings).

      Also in 6 projects that use this

    • AnthropicSkill

      academy-guide

      Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

      Also in 5 projects that use this

    • HK-hubSkill

      teach-impeccable

      One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

      Also in 16 projects that use this

    • +3 more from vikneshwaran16032005-alt
  • In this repository45 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.