create-component

A guided process for adding or changing SEED Design components across React, Lynx, and shared packages. It covers architecture, implementation, documentation, examples, and verification.

In plain words
What is it for?
Use it to build or refactor components, update registry snippets and examples, or write and verify Storybook stories. Storybook is a tool for developing and viewing UI components in isolation.
Why use it?
It keeps component work aligned across platforms and requires decisions and checks at each stage, reducing the risk of incomplete or inconsistent changes.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/daangn/seed-design/create-component
Any agent
npx skills add daangn/seed-design --skill create-component
Clone the repo
git clone --depth 1 https://github.com/daangn/seed-design

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00088 $0.02608
Opus 5 $0.00044 $0.01304
Sonnet 5 $0.00018 $0.00522
Haiku 4.5 $0.00009 $0.00261

Measured 2d ago against content hash 1d974b68a9bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-component 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.

skills/create-component/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Component

이 문서는 라우터다. 컴포넌트 작업의 흐름과 게이트만 정의하고, 실제 내용은 각 Phase의 reference 파일에 있다. 각 Phase에 진입할 때 해당 reference를 그때 읽는다. 모두 미리 읽지 않는다.

핵심 흐름

Platform Gate  →  Delivery Surface Gate  →  Phase 0 Pre (Brainstorm)  →  Phase 0 (Architecture)  →  Phase 1 (Implementation)  →  Phase 2 (Verification)
 React/Lynx 결정      package/snippet 판단           사용자 합의              아키텍처 결정              레이어별 구현                자동·수동 검증

각 Phase 사이에 게이트가 있다. 게이트 통과 전까지 다음 Phase로 가지 않는다. 흐름이 깨지면 빠진 요구사항·어긋난 아키텍처·우회된 검증이 누적되어 다른 컴포넌트까지 흔든다.


Storybook-only fast path

요청이 docs/stories/*.stories.tsx, docs/.storybook/*의 작성·리팩터링·검증에만 한정되고 컴포넌트 API나 동작을 바꾸지 않으면 Platform/Delivery Surface/Phase 0 게이트를 적용하지 않는다.

  1. references/storybook.md를 읽는다.
  2. docs/.storybook/preview.ts, docs/stories/utils/parameters.ts, 가까운 기존 story를 확인한다.
  3. CSF Next factory 패턴으로 작성하고 story별 동작 범위를 보존한다.
  4. references/storybook.md의 검증 명령과 references/visual-testing.md의 Storybook 항목을 실행한다.

컴포넌트 API·상태·recipe까지 바뀌면 fast path를 중단하고 일반 핵심 흐름으로 돌아간다.


막힘 처리 (모든 Phase 공통)

작업 중 막히면 임의 우회·mock·as any·테스트 생략·"나중에 고치자" 금지. 통증 메모 작성 → 사용자 보고 → 결정 후 재시도.

상세 룰과 차단점 분류표: references/sticking-policy.md


Platform Gate: 대상 플랫폼 결정

진입 시 즉시 읽기 → references/platform-gate.md

Phase 0 Pre 전에 target platform을 react / lynx / cross-platform 중 하나로 확정한다. 플랫폼이 정해져야 Headless, Recipe, Styled UI, Snippet, Docs, Example, Verification 경로가 결정된다.

🔒 게이트 Platform → 0Pre

  • target platform 확정
  • cross-platform이면 shared Rootage/API와 플랫폼별 구현 분리 원칙 확인
  • packages/lynx-react-headless/<component> 패키지가 필요하면 사용자 확인 전 구현 금지

Delivery Surface Gate: 공개 표면 결정

진입 시 즉시 읽기 → references/api-design.md의 "Delivery Surface Gate"와 "Analog Parity Check"

Platform Gate 직후, 구현 전에 이 컴포넌트를 package export, registry snippet, 둘 다, docs-only 중 어디로 제공할지 확정한다. React 동등 컴포넌트가 있다면 variant/interface뿐 아니라 docs Usage import, registry 존재 여부, package export, example surface를 함께 비교한다.

Read the full file on GitHub · 189 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 First seen · 189 lines · 88 tokens per session scan A 1d974b68a9bf

Subscribe to this mod's changes

create-component is a skill published in the GitHub repository daangn/seed-design (1,074 stars, last pushed 2d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,608 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

design-to-code

Lanhu to Code workflow for Claude Code. Convert Lanhu design URLs into Vue/React frontend code with component reuse, design token mapping, TODO-safe business logic, and optional code review.

ursazoo/lanhu-to-code · 42 tokens

component-doc-gen

Scan frontend src directories and generate docs/components.md so Claude Code can reuse existing Vue/React components during design-to-code generation.

ursazoo/lanhu-to-code · 29 tokens

material-ui-nextjs

Integrates Material UI with Next.js App and Pages routers using @mui/material-nextjs, Emotion cache providers, next/font, CSS layers with Tailwind/CSS Modules, Link component prop patterns, CSS theme variables SSR notes, and App Router useSearchParams + Suspense. Use when setting up or debugging MUI in a Next.js app.

mui/material-ui · 76 tokens

material-ui-styling

Chooses the right Material UI styling approach (sx, styled, theme overrides, global CSS) from official MUI guidance. Use when styling @mui/material components, customizing themes, overriding slots, or comparing sx vs styled.

mui/material-ui · 52 tokens

material-ui-tailwind

Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.

mui/material-ui · 67 tokens

material-ui-theming

Guides Material UI theming and design tokens (createTheme, ThemeProvider, palette, colorSchemes, cssVariables, theme.vars, dark mode, TypeScript augmentation). Use when building or extending a theme, toggling light/dark, or aligning tokens across an app.

mui/material-ui · 63 tokens