Frontend Design System
Use when the user asks to build a component library, define primitive, semantic and component design tokens as CSS variables, design component APIs with CVA variants, or wire dark mode through semantic tokens. Produces coded token layers and component library structure. Not for Figma variables and token pipeline governance (use design-systems).
Install
npx skills add j4flmao/agent-skills --skill frontend-design-systemgit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/frontend/universal/design-system ~/.claude/skills/frontend-design-systemPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Frontend Design System
## Purpose
Build a three-tier design token system with CVA-based component variants and theme-aware architecture. Every visual value is a token. No hardcoded colors, spacing, or typography. Components support dark mode, responsive variants, and accessibility out of the box.
## Agent Protocol
### Trigger
Exact user phrases: "design system", "design tokens", "component library", "token architecture", "typography system", "spacing system", "component API design", "variant system", "create a design system", "dark mode theme".
### Input Context
Before activating, verify:
- The framework is known (React, Vue, Angular) or ask.
- The styling approach is known (CSS modules, Tailwind, styled-components, etc.).
### Output Artifact
Token definitions, component APIs, and (when asked) starter files for tokens, CVA variants, and theme configuration.
### Response Format
Token definitions:
```
Primitive: --color-{scale}-{step}
Semantic: --color-{role}
Component: --{component}-{property}
```
Component API:
```
Component: {Name}
Props: {list with types}
Variants: {variant name -> options}
```
No preamble or filler. Lead with tokens and component APIs. Keep prose tight but include the definitions the user needs.
### Completion Criteria
- [ ] Three-tier token hierarchy defined (primitive, semantic, component).
- [ ] Token naming convention established with examples.
- [ ] CVA or equivalent variant pattern specified.Details
- Skill name
frontend-design-system- Repository
- j4flmao/agent-skills
- Path
skills/frontend/universal/design-system/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Frontend Design System skill do?
Use when the user asks to build a component library, define primitive, semantic and component design tokens as CSS variables, design component APIs with CVA variants, or wire dark mode through semantic tokens. Produces coded token layers and component library structure. Not for Figma variables and token pipeline governance (use design-systems).
How do I install the Frontend Design System skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill frontend-design-system. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Frontend Design System popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Frontend Error Handling
45j4flmao/agent-skills
Use when the user asks about React error boundaries, Vue errorHandler, Angular ErrorHandler, svelte:boundary, fallback UI, retry and recovery, unhandled promise rejections or reporting frontend errors to Sentry. Produces layered error boundaries and user-facing recovery. Not for form validation messages (use frontend-form-handling).
Frontend Data Fetching
45j4flmao/agent-skills
Use when the user asks how to cache server data on the client with TanStack Query, SWR or RTK Query, query keys, staleTime/gcTime, cache invalidation, optimistic updates, pagination or infinite scroll. Produces a typed data-fetching layer with caching and mutation patterns. Not for backend API design (use backend-api-design).
Frontend Feature Flags
45j4flmao/agent-skills
Use when the user asks about frontend feature flags, LaunchDarkly, OpenFeature, Unleash, Flagsmith, gradual rollout, kill switches or A/B test assignment in the UI. Produces a typed, provider-agnostic flag layer without flicker. Not for server-side flag evaluation (use backend-feature-flags) or experiment statistics (use product-ab-testing).
Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.