Component Reference Design

Community

Vanszs

Positive reference library of modern, non-monotonous UI — the constructive companion to Anti-AI-Slop. Curated, copy-pasteable, accessible patterns sourced from trusted design authorities (MUI, shadcn/ui, Radix, Headless UI, Ant Design, Chakra, Mantine, Tailwind UI, Material Design 3, Apple HIG, IBM Carbon, NNG, Refactoring UI). Covers layout skeletons (with/without animation), typography systems & font pairings, every card variant, buttons & forms, navigation, data-display, overlays & feedback, tasteful accessible motion, a design-system index, and varied marketing-section anatomies. Use when designing or building any UI and you want a reference for "what good looks like."

Overview

Publisher	Vanszs
Repository	`Anti-AI-UI`
Skill name	`Component Reference Design`
Stars	20
Forks	6
Bundled files	7
License	MIT
Links	Skill source Repository

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.
7 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Vanszs on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Vanszs/Anti-AI-UI/tree/main/component-reference-design
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.

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/Vanszs/Anti-AI-UI.git /tmp/Anti-AI-UI
mkdir -p .claude/skills
cp -r /tmp/Anti-AI-UI/component-reference-design .claude/skills/vanszs-component-reference-design

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Component Reference 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 Component Reference 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 Component Reference 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.

Component Reference Design — Positive Pattern Library

Purpose

A reference of what good looks like, sourced from trusted design systems. Where Anti-AI-Slop tells you what to AVOID, this skill shows you what to BUILD: modern layouts, varied section anatomies, proven type systems, every card and component variant, and tasteful accessible motion — all copy-pasteable and a11y-correct.

Use the two skills together: Anti-AI-Slop = the filter, Component Reference = the palette.

How To Use This Skill

Identify what you're building (a page layout? a card? a form? a nav?).
Open the matching reference file (see Category Map) and pick a pattern by its when-to-use note — not by "what looks coolest in isolation."
Copy the concrete markup; swap in real content, brand color, and a non-Inter display font.
Apply the Anti-Monotony Rules below so the page doesn't feel templated.
Run the Anti-AI-Slop Pre-Delivery Audit before shipping.

Category Map (where to look)

You're building…	Open	Contains
Page/app skeleton, grid, responsive structure	`references/layouts.md`	Holy-grail, sidebar shell, dashboard, split-screen, full-bleed, bento, masonry, magazine, asymmetric, sticky-aside, container-query, Z/F patterns, Every-Layout primitives
Type scale, font pairing, fluid type	`references/typography.md`	8+ display+body pairings, modular scales (1.2/1.25/1.333), clamp() recipes, per-role leading/measure/tracking, Tailwind config, MUI/MD3/Apple/Carbon scales compared
Card, button, form, nav, table, list, badge	`references/components.md`	Card variants (17), buttons (10), form controls (13), navigation (13), data-display (16)
Modal, drawer, toast, tooltip, popover, animation	`references/animation.md`	Overlay/feedback components + tasteful motion patterns (timing, easing, reduced-motion, 13 motion recipes)
Choosing a library / design tokens	`references/design-systems.md`	18 design-system index (ecosystem, styling, a11y, theming, license, URL) + W3C DTCG tokens + decision matrix
Charts, graphs, KPI cards, sparklines, data-viz	`references/charts.md`	Beautiful modern Recharts patterns: color systems (teal/Okabe-Ito/OKLCH), premium chrome (custom tooltip/legend/axes/grid), bar/line/area/donut/radial, KPI+sparkline cards, specialty (heatmap/treemap/funnel/radar/scatter/bullet/waffle), motion, dark-mode/responsive, a11y, 15-point anti-slop scan
Admin dashboard — app shell, sidebar, topbar, widgets, tables, filters	`references/dashboards.md`	Modern clean admin dashboard: 15 clean-dashboard principles, app shell (grid sidebar+header), sidebar nav (collapsible/rail/groups/footer), topbar (breadcrumb/⌘K search/notif/avatar/org-switcher), command palette, grid composition (KPI→hero+side→table, bento), KPI/stat cards (delta inversion), chart placement/chrome, filters & toolbar (date-range/segmented/chips/saved-views), data table (TanStack/density/sort/selection/pagination), all states (skeleton/empty/error/zero), 3-tier color tokens + dark, anti-pattern cheat sheet

The Anti-Monotony Rules (apply to every multi-section page)

Never repeat the same section anatomy consecutively. Vary: centered → split → bento → stats-bar → full-bleed → alternating.
Vary container widths by content — text max-w-3xl, grids max-w-6xl, ≥1 full-bleed break per page.
Vary section padding — hero py-32, features py-16, CTA py-12. Never one uniform py-20.
One dominant element per section — size/weight ≥1.5× its neighbours.
Break rhythm every 2–3 sections — a full-bleed image, colour block, or stats bar.
Mix grid structures — 2-col, 4-col, asymmetric spans; a bento needs a real 2×2 dominant cell (else it's just a card grid).
≥2 deliberate asymmetric moments per page — unequal columns, off-centre headings, left-aligned text.

Proven Storytelling Sequence (Evil Martians, 100 dev-tool landing pages)

Hero (what is it?) → Trust (who uses it?) → Features (what/why?) → Social proof (what do users say?) → Supporting (FAQ / comparison / pricing) → Final CTA (what now?) — with each section using a DIFFERENT anatomy.

Non-Negotiable Quality Bar (every pattern here already follows it)

Semantic HTML first — <table>, <ul>, <dl>, <dialog>, <nav>, <button>, <a> before div-soup.
Accessible by default — labels wired, aria-* present, focus-visible rings, keyboard reachable, focus trap on modals.
prefers-reduced-motion gates every spatial animation.
Radius is a scale — inputs/buttons rounded-md, cards rounded-lg, modals rounded-xl, pills rounded-full.
Type — distinctive display font (NOT Inter-everywhere), modular scale, max-w-prose body, 2–3 weights.
Motion budget — hovers 100–150ms, entrances 200–300ms, exits faster; transform+opacity only.
WCAG AA contrast — 4.5:1 body, 3:1 large/UI; test light + dark.

Trusted Sources (full index in `references/design-systems.md`)

MUI · shadcn/ui · Radix Primitives & Themes · Headless UI · Ant Design · Chakra UI · Mantine · Tailwind UI · Material Design 3 · Apple HIG · IBM Carbon · Atlassian · Polaris (Shopify) · Fluent (Microsoft) · Base Web (Uber) · Park UI / Ark UI · daisyUI · Tremor · TanStack Table · Recharts · NNG · Refactoring UI · Every-Layout · Josh Comeau · Framer Motion / Motion · Emil Kowalski (Sonner, Vaul) · cmdk · W3C WAI-ARIA APG · W3C DTCG.

Output Expectations

Use these patterns as a starting point, then make ≥1 deliberate, content-specific choice per section (color, type, layout variation). The result should read as intentional, branded, varied, accessible, production-ready — never templated.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Component Reference Design AI skill do?

Why use Component Reference Design on TypingMind?

Because you install it once and use it with any model. Component Reference 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 Component Reference Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Vanszs/Anti-AI-UI/tree/main/component-reference-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Component Reference 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 Component Reference Design?

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

Is the Component Reference Design AI skill free?

Yes. It is published on GitHub by Vanszs under the MIT 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

Accessibility

affaan-m

CommunityPopular

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

Archify

Validated interactive HTML diagrams, upstream-maintained.

Auteur

Design and build cinematic, award-level web pages.

Concept Diagrams

Generate flat, minimal educational SVG visuals as HTML.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Component Reference Design — Positive Pattern Library

Purpose

How To Use This Skill

Category Map (where to look)

The Anti-Monotony Rules (apply to every multi-section page)

Proven Storytelling Sequence (Evil Martians, 100 dev-tool landing pages)

Non-Negotiable Quality Bar (every pattern here already follows it)

Trusted Sources (full index in references/design-systems.md)

Output Expectations

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

Trusted Sources (full index in `references/design-systems.md`)