design-system-architect

design-system-architect is a skill for Cursor from roedyrustam/vibes-plug. It costs 54 tokens per session (9,530 once invoked), scanned A, original, MIT.

A guide to creating a shared UI design system: a reusable set of components, visual rules, and accessibility standards for an application or product family. It covers design tokens, Tailwind, Material Design, Radix UI, Base UI, shadcn/ui, and WCAG accessibility checks.

In plain words
What is it for?
Use it to define colors and spacing, build component libraries, create reusable variants, distribute components, apply Material Design principles, and audit interfaces against WCAG 2.2.
Why use it?
It helps teams keep interfaces consistent and makes common components easier to reuse, change, and review for accessibility.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the vibes-plug plugin — 171 skills, 8 agents, 2 MCP servers shipped together

Good fit Use it to define colors and spacing, build component libraries, create reusable variants, distribute components, apply Material Design principles, and audit interfaces against WCAG 2.2.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/roedyrustam/vibes-plug/design-system-architect
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add roedyrustam/vibes-plug --skill design-system-architect
Clone the repo
git clone --depth 1 https://github.com/roedyrustam/vibes-plug

Made for: Cursor.

Or install vibes-plug, the plugin that ships this one along with the rest of its 171 skills, 8 agents, 2 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for design-system-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/design-system-architect/github.svg)](https://agentmods.dev/skills/roedyrustam/vibes-plug/design-system-architect)
Your own site
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/design-system-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/design-system-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-system-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/design-system-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/design-system-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 163
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 196
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 197
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 264
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.09530
Opus 5.5 $0.00022 $0.03812
Sonnet 5.5 $0.00011 $0.01906
Haiku 4.5 $0.00005 $0.00953

Measured 2d ago against content hash f6b4fec6e392, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-system-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/design-system-architect/SKILL.md · 545 lines

How it starts

The opening of the file, as written. The whole thing — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design System Architect (2026 Edition — shadcn/ui Registry)

English | Bahasa Indonesia


English

Orchestration & Integration

Connects and orchestrates with relevant domain skills:

  • modern-web-guidance: Search and enforce 2026 web platform best practices before building UI primitives.
  • modern-css-native-expert: Pure CSS anchor positioning, @starting-style, and top-layer transitions.
  • tailwind-expert: Translates design tokens into CSS-first @theme variables.
  • ui-ux-pro-max: Design intelligence, F/Z scan patterns, 60-30-10 color layering, and typography scales.
  • visual-ui-auditor: Automated multimodal vision auditing and 20-point rubric verification.
  • anti-slop: Eliminates AI visual clichés (Pillar 7), pill-button addiction, and fake states.
  • brainstorming, zero-to-prod-orchestrator, session-memory-manager: Continuous lifecycle orchestration.

Description

Expert guide for building and maintaining scalable UI design systems. Covers design tokens with OKLCH and Tailwind v4 @theme, Material Design 3 (M3) integration, headless component primitives (Radix UI, Base UI 1.x), shadcn/ui registry for distributable component libraries, CVA for type-safe variants, and WCAG 2.2 accessibility compliance.

Trigger Conditions

  • Building a shared UI component library from scratch.
  • Setting up design tokens (colors, typography, spacing) with Tailwind v4.
  • Applying Material Design 3 (M3) principles (https://m3.material.io/).
  • Using headless primitives (Radix UI, Base UI 1.x) with custom styling.
  • Distributing components via the shadcn/ui registry format.
  • Auditing a component library for WCAG 2.2 accessibility compliance.
  • Enforcing anti-slop quality standards on component primitives and tokens.

Anti-Slop Component Design Contract

  • Zero Div-Soup Primitives: Build exclusively on accessible headless primitives (Radix UI, Base UI 1.x) using semantic HTML (<button>, <dialog>, <nav>, <input>).
  • Visual Hierarchy & Surface Layering Contract: Enforce explicit surface container tiers (Canvas L0, Card L1, Raised L2, Overlay L3) with crisp 1px solid borders (border-border) and directional micro-shadows (shadow-xs). Ban muddy 30px black shadows and ungrounded neon glow orbs.
  • Single Focal Primary Action: Component presets must enforce a single primary CTA variant per view; secondary and tertiary actions must map to outline, tonal, or ghost variants.
  • Mandatory 5 States: Every component primitive must explicitly define: default, hover/active, visible keyboard focus-visible:ring-2, loading/skeleton state, and disabled/error styling.
  • Optical Typography & Tabular Figures: Headings must default to tight letter-spacing (tracking-tight), uppercase eyebrows to wide letter-spacing (tracking-wider), and all numeric/counter/price components must enforce tabular-nums.
  • Contracted Contrast Tokens: All semantic tokens must pass WCAG 2.2 AA contrast ratios (>= 4.5:1 text, >= 3:1 graphical elements) in both light and dark themes.
  • Strict Scale Compliance: Ban arbitrary pixel values (p-[13px]); enforce unified @theme tokens.

Read the full file on GitHub · 545 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago Changed · +15 lines · +4 tokens per session f6b4fec6e392
  2. 3d ago Changed · +1 lines cbe730794281
  3. 6d ago Changed 4f1e457ea3fd
  4. 15d ago Changed ed0a58f023b7
  5. 17d ago Changed · +18 lines 66d5c039179d
  6. 20d ago Changed 211bd2c5ebfc
  7. 21d ago Changed · +187 lines 051fefb2cadb
  8. 23d ago Changed · +8 lines · +39 tokens per session 05c76904218e
  9. 25d ago Changed · +6 lines · -39 tokens per session aa18812a1ec1
  10. 1mo ago First seen · 310 lines · 50 tokens per session scan A 4b203a67e665

Subscribe to this mod's changes

design-system-architect is a skill published in the GitHub repository roedyrustam/vibes-plug (113 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 9,530 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

frontend-ui-engineering

Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

addyosmani/agent-skills · 58 tokens

ui-design

Unify product UI design, frontend implementation, and verification. Use when asked to design, redesign, build, or fix a web, desktop, or mobile interface; a page, dashboard, form, component, design system, responsive layout, accessibility, interface animation, or editable hero/banner/infographic within a product…

AnastasiyaW/codex-claude-code-config · 97 tokens

frontend-design

A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.

AnastasiyaW/codex-claude-code-config · 264 tokens

muse

Defining and managing design tokens, applying token systems to existing codebases, building design system foundations. Use for spacing, color, typography, dark mode, cross-platform output.

simota/agent-skills · 38 tokens

pixel

Generating pixel-accurate HTML/CSS code from image mockups (PNG/JPG/screenshots) and performing visual verification for faithful reproduction. Use when mockup-to-code generation is needed.

simota/agent-skills · 40 tokens

web-design-expert

Web design and UX guidance for visual systems, accessibility, interaction patterns, and performance-aware interfaces. Use when designing a website's look and feel, improving UX/accessibility, or reviewing a UI for polish and performance.

frankxai/claude-skills-library · 48 tokens