Skip to main content
skill CX Codex

design-system · rampstackco — Claude Code skill: build a design system

Builds or audits a design system: tokens, component library, naming conventions, contribution model and docs. Useful when products drift apart visually.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add rampstackco/claude-skills --skill design-system -a claude-code
Open on GitHub

What design-system does

The skill works in five stacked layers: foundations (tokens), elements (atoms), components (molecules and organisms), patterns (page templates), and documentation with governance. Each layer feeds the one above, so tokens come first and components sit on top of them. For tokens it suggests a two-tier setup: base values like color-blue-600 plus semantic names like color-text-link, with components referencing the semantic tier.

A new system follows a set order: inventory the existing UI, spot duplicates, define foundations, audit elements, build the library, pick priority components, document patterns, set governance, then migrate surfaces gradually. An audit takes a different route — what is documented, what lives in Figma, what is in code, what production actually uses, then gaps, divergent implementations, component drift and fix priorities.

The skill stays stack-agnostic in principle: structure and governance carry over, while implementation depends on your tools — Figma, Storybook, a code library. It expects inputs: brand identity, product surfaces, team tooling, existing components, and constraints such as accessibility and browser support. If brand identity is undefined, run brand-identity first, because tokens depend on it. A single page or component is a job for design-standards instead.

What it helps with

  • build a design system from scratch without losing track of layers
  • find duplicate components across the product
  • define tokens at the system level, not per page
  • separate base tokens from semantic ones
  • set a contribution model and a system owner

Example prompts for the agent

  • Build a design system for our product, starting with foundations and tokens
  • Audit our existing design system: where are the gaps and where do Figma and code diverge
  • Structure our component library into elements, components and patterns

How to install design-system

1Skills CLI (Vercel)

npx skills add rampstackco/claude-skills --skill design-system -a claude-code

2Manually: put the files in place

~/.claude/skills/design-system/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/design-system/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about design-system

How do I install design-system in Claude?

Run npx skills add rampstackco/claude-skills --skill design-system -a claude-code. The skill file then sits at ~/.claude/skills/design-system/SKILL.md.

What does the design-system skill do?

It helps you build or audit a design system: tokens, component library, naming conventions, contribution model and documentation. It works through five layers, from foundations to governance.

How is design-system different from design-standards?

This skill builds the system itself. Applying it to specific pages or components is design-standards, and brand visual identity is brand-identity.

Source text

SKILL.md · MIT
---
name: design-system
description: "Build or audit a design system including component library, design tokens, naming conventions, contribution model, and documentation. Use this skill whenever the user wants to build a design system, audit an existing system, define design tokens at the system level, structure a component library, or set up design system governance. Triggers on design system, component library, design tokens, atomic design, atoms, molecules, organisms, design system documentation, Storybook, Figma library, system governance, design contribution model. Also triggers when teams are inconsistent across products and a system is the answer."
category: design
catalog_summary: "Component library, design tokens, design system documentation"
display_order: 1
---

# Design System

Build, evolve, or audit a design system. Stack-agnostic in principle. Implementation is stack-specific (Figma, Storybook, code library, etc.) but the structure and governance principles transfer.

This skill is for building the system. For applying a system to specific pages or components, use `design-standards`. For brand visual identity, use `brand-identity`.

---

## When to use

- Building a design system from scratch
- Auditing an existing system for gaps or fragmentation
- Defining design tokens at the system level
- Structuring a component library
- Establishing contribution and governance models
- Migrating from ad-hoc components to a documented system

## When NOT to use

- Designing a single page or component (use `design-standards`)
- Brand identity work (use `brand-identity`)
- Component-level frontend implementation (use `frontend-component-build`)
- Pure design documentation for marketing (use `brand-style-guide`)

---

## Required inputs

- The brand identity (tokens, voice, imagery direction)
- The product surfaces the system needs to support (web, mobile, marketing, app, internal tools)
- The team and its working tools (Figma, code framework, doc platform)
- Existing components, even if undocumented
- Constraints (accessibility requirements, performance targets, browser support)

If brand identity is undefined, run `brand-identity` first.

---

## The framework: 5 layers

A complete design system has five layers, stacked. Each layer feeds the layer above.

### 1. Foundations (tokens)

The atomic decisions. Color, type, spacing, radius, shadow, motion, breakpoints.

**Why this layer matters:**
- Tokens are the source of truth for everything above
- Token changes propagate everywhere automatically
- Without tokens, the system has no foundation

**Output:**
- A documented token set (see `design-standards/references/design-tokens-template.md`)
- Token implementation in code (CSS variables, JS objects, Style Dictionary, etc.)
- Token implementation in Figma (variables and styles)
- A primer doc explaining what tokens to use when

**Common patterns:**
- Two-tier tokens: base tokens (raw values) + semantic tokens (named uses). Example: `color-blue-600` (base) + `color-text-link` (semantic). Components reference semantic tokens. Theme changes update semantic tokens, not base.

### 2. Elements (atoms)

The smallest functional building blocks. Buttons, inputs, labels, badges, icons, links, dividers.

**Per element, document:**
- Visual variants (primary, secondary, ghost, etc.)
- Size variants (small, medium, large)
- States (default, hover, focus, active, disabled, error, loading)
- Anatomy (the parts that make up the element)
- Spacing and proportions
- Accessibility (keyboard support, screen reader behavior, ARIA)
- Code usage (props, examples)

**Output:**
- Element library in Figma
- Element components in code
- Per-element documentation

### 3. Components (molecules + organisms)

Combinations of elements that form recognizable UI patterns. Cards, alerts, modals, navigation, forms, data tables, headers, footers.

**Per component:**
- Composition (which elements it uses)
- Variants and configurations
- Use cases (when to reach for this vs. an alternative)
- Layout behavior (responsive, contained, full-bleed)
- Anti-patterns (when NOT to use it)

**Output:**
- Component library
- Per-component documentation with usage guidance

### 4. Patterns (templates)

Larger structures that combine components. Sign-in flow, settings page, dashboard layout, marketing page sections.

**Per pattern:**
- The structure and components used
- The user journey it supports
- Layout grid and spacing
- Responsive behavior
- Variants (e.g., "with sidebar," "fullscreen," "modal")

**Output:**
- Pattern library or page templates
- Documentation showing complete examples

### 5. Documentation and governance

How the system gets used, contributed to, and maintained.

**Documentation includes:**
- Getting started guide for new team members
- How to use vs. how to extend
- Contribution model
- Versioning policy
- Migration paths when breaking changes happen
- Decision log for major system choices

**Governance includes:**
- Who owns the system (a team or rotation)
- How new components get proposed and approved
- How conflicts get resolved
- How the system evolves vs. stays stable
- Cadence of review and updates

---

## Workflow

### For a new design system

1. **Inventory the existing UI.** Screenshot every component, button, form, modal across the product. The list of distinct UI patterns is your starting scope.
2. **Identify the duplicates.** Same component built 5 different ways across the product. These are your high-value consolidation targets.
3. **Define foundations.** Token set, with both base and semantic layers. Document each.
4. **Audit elements.** From the inventory, identify the actual elements (buttons, inputs, etc.) and reduce variants to a managed set.
5. **Build the element library.** Figma + code. Document each element.
6. **Identify priority components.** The 10 to 15 components that appear most often. Build those first.
7. **Document patterns.** Page-level templates that show the system in use.
8. **Establish governance.** Owner, contribution model, review cadence.
9. **Roll out.** Migrate existing surfaces to the system progressively.

### For an existing design system audit

1. **Inventory what exists.** What's documented, what's in Figma, what's in code, what's actually used in production.
2. **Map gaps.** Where the system is incomplete. Where teams build outside the system because the system can't serve their need.
3. **Map fragmentation.** Where the system has divergent implementations (Figma vs. code, web vs. mobile, multiple teams).
4. **Identify decay.** Components that have drifted from the documented standard.
5. **Prioritize fixes.** Foundation gaps first. High-use component drift second. Rarely-used component cleanup last.
6. **Plan rollout.** Major changes need migration paths.

---

## Failure patterns

- **Building the system before the brand is set.** Tokens depend on brand. Set brand first.
- **Atoms-up extreme.** Spending 6 months on tokens and elements before producing components anyone uses. Ship components people need; refine tokens iteratively.
- **One-person system.** A system without governance fails as soon as the original designer leaves. Establish ownership early.
- **Stale documentation.** A system with code that's diverged from the docs is worse than no system. Synchronize or kill the docs.
- **Versioning everything.** Treating every component as needing a major version. Most components evolve in place. Reserve versioning for breaking changes.
- **Adopting "atomic design" dogmatically.** Atoms / molecules / organisms is a useful mental model, not a rigid taxonomy. Don't argue about whether something is a molecule or an organism.
- **Building in a vacuum.** A system designed without input from the teams using it gets ignored. Co-design with consumers.
- **No deprecation path.** Old components linger in code forever because no one knows it's safe to remove them. Document deprecation explicitly.
- **Token explosion.** Defining 200 color tokens for a brand with 10 colors. Discipline. Most products need fewer tokens than they have.

---

## Output format

A design system has multiple deliverables. Typically:

- **Documentation site** (Notion, dedicated site, GitHub Pages, Storybook addon, etc.)
- **Figma library** (or equivalent design tool)
- **Code library** (npm package, monorepo workspace, copy-paste components)
- **Decision log** (system-level decisions and the reasoning)
- **Roadmap and changelog**

For a design system audit, output is a markdown report at `design-system-audit.md`:

1. Inventory of what exists (foundations, elements, components, patterns)
2. Gap analysis
3. Fragmentation analysis
4. Drift analysis
5. Prioritized remediation plan
6. Governance recommendations

---

## If required data is unavailable

This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.

---

## Reference files

- [`references/system-architecture.md`](references/system-architecture.md) - The four-layer model (tokens, primitives, patterns, templates) and how to decide where new work belongs.
- [`references/system-audit-template.md`](references/system-audit-template.md) - Template for auditing an existing design system.
- [`references/governance-playbook.md`](references/governance-playbook.md) - Contribution model, ownership, and decision process for an active system.

© rampstackco · MIT · rampstackco/claude-skills

Similar skills

Everything for Design →

design-system by other authors comes first.

design-system claudekit This skill builds design tokens, component specs, and presentation slides. Use it when an interface and its slides need to follow one visual system. CX Codex +1 42,700installs design-system affaan-m Builds a design system out of the styles already in your repo, or audits them: tokens, a ten-point UI score, and a check for generic AI styling. CX Codex +1 5,000installs design-system official anthropics This skill audits a design system, documents components, and helps extend existing patterns. Use it when tokens, states, naming, or accessibility need a closer check. CX Codex +1 4,200installs design-system Donchitos Walks one game system through every required GDD section and cross-references its dependencies. Useful when a design doc grows faster than you can keep it straight. CX Codex +1 484installs design-system BuilderOS Extracts design tokens from UI screenshots or mockups into docs/design.md for agents and a mirrored docs/design.html style guide. CX Codex +1 1,800installs design-system-patterns Seth Hobson Guides the design of design tokens, theme switching, and component library architecture. Use it when establishing shared UI foundations for a project. CX Codex 15,953installs ui-design-system Alireza Rezvani This skill builds design tokens, component structures, and responsive calculations. Use it when a project needs a consistent UI system or a developer handoff. 1,076installs figma-create-design-system-rules official openai Generates project-specific design system guidelines for AI coding agents handling Figma-to-code tasks. It inspects existing components and writes rules directly into your repository. CX Codex +1 2,900installs design-system-rules-agent official Figma A subagent that turns your codebase conventions into Figma-to-code rules and writes them into AGENTS.md, so later implementations stay consistent. CX Codex GP ChatGPT ★ 7,596repo stars tailwind-design-system Seth Hobson Helps build design systems with Tailwind CSS v4, from theme tokens to component variants. Use it when a project needs shared UI patterns. CX Codex 70,180installs theming-system Owl-Listener Designs a three-layer token architecture to support brand variants, color modes, and interface density in a single component library. CX Codex +1 2,100installs

From the same set11

logo-design This skill generates 6 to 12 logo variants across different architectures, then refines the chosen one to production. Useful when you need a logo, not a full identity. CX Codex +1 446installs creative-direction Builds a structured aesthetic brief across four directional axes: tone, aesthetic philosophy, audience relationship, and sensory ambition. Ideal before designing multi-touchpoint projects. CX Codex +1 417installs brand-style-guide Builds or audits a brand style guide across eight sections: story, logo, color, typography, imagery, voice, applications, dos and don'ts. Useful once the identity is done and needs handing off. CX Codex +1 388installs landing-page-copy Generates conversion-focused landing page copy across hero sections, objection handling, proof elements, and action buttons. CX Codex +1 374installs chatbot-flow-design Designs conversational flows, intent architectures, and fallback logic for website bots. Useful when scoping an AI chat agent or fixing an LLM that hallucinates facts. CX Codex +1 338installs seo-aeo-geo A skill for tuning content and site structure for AI search: citations in model answers, llms.txt, extraction-friendly markup. CX Codex +1 317installs email-deliverability A skill for email deliverability: sets up SPF, DKIM and DMARC, tracks sender reputation, and helps you work out why messages land in spam. CX Codex +1 314installs brand-ideation A skill for the early brand phase: it generates positioning territories, name candidates, mood directions and narratives, then helps you converge on one. CX Codex +1 308installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor