Frontend Design logo

Frontend Design

Community
opensesh
frontend-design

Use when building UI components, making design decisions for frontend work, reviewing UI implementation quality, or planning interaction patterns.

Overview

Publisheropensesh
RepositoryDESIGN-OPS
Skill namefrontend-design
Stars
23
Forks
5
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by opensesh on GitHub. Read the source before you install it.

Installation

Install the Frontend Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/opensesh/DESIGN-OPS/tree/main/skills/frontend-design
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/opensesh/DESIGN-OPS.git /tmp/DESIGN-OPS
mkdir -p .claude/skills
cp -r /tmp/DESIGN-OPS/skills/frontend-design .claude/skills/frontend-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Frontend Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Frontend Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Frontend Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Frontend Design

Create distinctive, production-grade frontend interfaces with intentional aesthetics.

Purpose

This skill guides creation of frontend interfaces that feel genuinely designed—not auto-generated. It covers design thinking, interaction patterns, motion, forms, layout, accessibility, and performance.

When to Activate

Use this skill when:

  • Building UI components or pages
  • Making design decisions for frontend work
  • Reviewing UI implementation quality
  • Planning interaction patterns

1. Design Thinking

Before writing any code, establish your design intent:

Purpose & Context

What problem are we solving? Who uses this? Think about the user's emotional state, their goals, and what success looks like.

Aesthetic Direction

Choose a clear visual direction:

DirectionFeelWhen to Use
Warm MinimalClean, inviting, focusedDashboard UIs, tools, productivity
EditorialMagazine-like, typographicContent-heavy pages, portfolios
Soft/OrganicRounded, gentle, approachableConsumer apps, onboarding
Industrial/RawUtilitarian, honest, functionalDeveloper tools, technical docs
Luxury/RefinedSpacious, elegant, deliberateBrand sites, premium products

Key insight: Bold maximalism and refined minimalism both work—the magic is in commitment, not intensity.

The Memorable Detail

Ask yourself: What's the one thing someone will remember about this interface? Maybe it's a delightful hover state, an unexpected color choice, or how perfectly the typography flows.


2. Design System Integration

Color Philosophy

css
/* Use semantic tokens, not arbitrary colors */
--bg-primary      /* Main background */
--bg-secondary    /* Elevated surfaces */
--fg-primary      /* Primary text */
--fg-secondary    /* Secondary text */
--border-primary  /* Interactive borders */
--border-secondary /* Container borders */
--brand-primary   /* Accent/CTA color */

Typography Hierarchy

CategoryUsage
DisplayHeadlines, titles, hero text
BodyParagraphs, inputs, tabs
SmallLabels, captions, hints, metadata
AccentSpecial callouts, tech feel (use sparingly)

Border Philosophy

Borders should support, not dominate:

jsx
// Default: nearly invisible
className="border border-border-secondary"

// Hover: slightly more visible
className="hover:border-border-primary"

// Focus: full visibility
className="focus:border-border-primary"

3. Interaction Patterns

Hit Targets & Touch

ContextMinimum SizeNotes
Desktop24×24pxVisual can be smaller if hit area is expanded
Mobile44×44pxApple HIG standard
Input font≥16pxPrevents iOS Safari auto-zoom
jsx
// Expand hit target beyond visual bounds
<button className="p-2 -m-2">
  <Icon className="w-6 h-6" /> {/* Visual is 24px, hit area is 40px */}
</button>

Focus Management

  • Use :focus-visible over :focus to avoid focus rings on click
  • Use :focus-within for grouped controls (e.g., input with icon)
  • Every focusable element requires a visible focus state
  • Implement focus traps in modals/drawers per WAI-ARIA patterns

Loading States

TimingValuePurpose
Show delay150–300msPrevent flash on fast responses
Minimum visible300–500msAvoid jarring disappearance
jsx
// Don't: Show spinner immediately
{isLoading && <Spinner />}

// Do: Delay spinner appearance
const showSpinner = isLoading && loadingDuration > 200;

Optimistic Updates

Update the UI immediately when success is likely:

  1. Show change instantly
  2. Send request to server
  3. On success: confirm (subtle)
  4. On failure: rollback + show error + offer retry

Destructive Actions

PatternWhen to Use
Confirmation dialogPermanent deletion, irreversible changes
Undo with timeoutSoft deletes, sends, publishes
Type-to-confirmAccount deletion, production deployments

4. Motion & Animation

When to Animate

Animate only when it serves a purpose:

  • Clarify cause/effect: Show where something came from or went
  • Maintain context: Help users track changes during transitions
  • Deliberate delight: Reward interactions meaningfully

Don't animate for decoration or to fill silence.

Easing Selection

Property ChangingRecommended Easing
Opacity onlylinear or gentle ease
Size/ScaleeaseOut (fast start, slow end)
PositioneaseOut or spring
EntereaseOut
ExiteaseIn (slow start, fast end)

Performance Rules

GPU-accelerated (prefer these):

css
transform: translate(), scale(), rotate();
opacity;
filter;

Layout-triggering (avoid animating):

css
width, height, padding, margin;
top, left, right, bottom;
font-size, line-height;

Anti-patterns:

css
/* Never: Animates everything including layout */
transition: all 0.3s;

/* Do: Explicit properties only */
transition: transform 0.3s, opacity 0.3s;

Accessibility (prefers-reduced-motion)

Always honor the user's motion preference:

jsx
const prefersReducedMotion = window.matchMedia(
  '(prefers-reduced-motion: reduce)'
).matches;

5. Form Design

Submission Behavior

Input TypeEnter Key Behavior
Single text inputSubmits form
Multiple inputsSubmits on last field
<textarea>Creates new line
<textarea> + Cmd/Ctrl+EnterSubmits form

Validation Patterns

TimingWhat to Validate
On blurFormat, required fields
On submitAll validation, server errors
Real-timeOnly for character limits or live search

Rules:

  • Show errors adjacent to the field, not in a summary
  • On submit error, focus the first invalid field
  • Don't pre-disable submit—let users discover issues

Mobile Considerations

  • Input font ≥16px prevents iOS auto-zoom
  • Use correct type and inputmode for better keyboards:
Datatypeinputmode
Emailemail—
Phonetel—
Numbertextnumeric
Credit cardtextnumeric

6. Layout Principles

Optical Alignment

Geometry lies. Adjust ±1–2px when perception beats math:

  • Circles and triangles appear smaller than squares at same dimensions
  • Text with descenders needs more bottom padding
  • Icons may need nudging to appear centered

Nested Border Radius

Child radius must be ≤ parent radius, and curves should be concentric:

Outer radius: 16px
Gap (padding): 8px
Inner radius: 16px - 8px = 8px

Layered Shadows

Use ≥2 shadow layers to mimic real light (ambient + direct):

css
box-shadow:
  0 1px 2px rgba(0,0,0,0.06),    /* Tight, direct light */
  0 4px 12px rgba(0,0,0,0.08);   /* Soft, ambient light */

7. Accessibility

Contrast Standards

  • Prefer APCA over WCAG 2 for more accurate perceptual contrast
  • Interactive states must have more contrast than rest state

Color Independence

Never rely on color alone for meaning:

  • Error states: color + icon + text
  • Status indicators: color + label
  • Charts: color + pattern or label

Screen Reader Support

  • Icon-only buttons require aria-label
  • Decorative elements get aria-hidden="true"
  • Use native elements (button, a, label) before ARIA
  • Maintain logical heading hierarchy (h1 → h2 → h3)

8. Performance

Response Time Targets

OperationTarget
UI response to input<100ms
API mutations<500ms
Page load (LCP)<2.5s

Rendering Optimization

  • Virtualize lists >100 items
  • Use content-visibility: auto for off-screen content
  • Minimize React re-renders

Asset Loading

AssetStrategy
Above-fold imagesPreload
Below-fold imagesLazy load
FontsPreload critical, subset via unicode-range
Third-party scriptsdefer or async

9. What to Avoid

Generic AI aesthetics:

  • Overused fonts (Inter, Roboto, Arial as primary)
  • Purple gradients on white backgrounds
  • Predictable layouts without character
  • Cookie-cutter component patterns

Interaction anti-patterns:

  • transition: all (performance killer)
  • Autoplay animations
  • Disabled submit buttons before user tries
  • Blocking paste on any input
  • Color-only status indicators

Instead:

  • Make unexpected choices that feel genuinely designed
  • Match implementation complexity to aesthetic vision
  • Commit fully to your visual direction

Related Skills

  • design-system-quality
  • brand-guidelines
  • brand-voice

Version: 1.0.0 | Interaction patterns adapted from Vercel Web Interface Guidelines

Frequently asked questions

What does the Frontend Design AI skill do?

Use when building UI components, making design decisions for frontend work, reviewing UI implementation quality, or planning interaction patterns.

Why use Frontend Design on TypingMind?

Because you install it once and use it with any model. Frontend Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Frontend Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/opensesh/DESIGN-OPS/tree/main/skills/frontend-design. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Frontend Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Frontend Design?

As many as you like. As long as a model supports skills, you can use Frontend Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Frontend Design AI skill free?

Yes. It is published on GitHub by opensesh under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇