Skip to content
Agentmart
Submit a tool
This entry duplicates Implement Figma → Next.js 16 + shadcn/ui, which is the one we list in search.

Implement Figma → Next.js 16 + shadcn/ui

This skill should be used when the user shares a Figma URL or node and asks to "구현해줘", "코드로 만들어줘", "Figma 컴포넌트 구현", "implement this Figma component", "Figma…

Skill by ureca-corp

IndexedMIT
Write a review

Chalk Labs

Need help deploying Implement Figma → Next.js 16 + shadcn/ui?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ureca-corp-implement-figma-next-js-16-shadcn-ui-e75d7e

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

This skill should be used when the user shares a Figma URL or node and asks to "구현해줘", "코드로 만들어줘", "Figma 컴포넌트 구현", "implement this Figma component", "Figma to code", "Figma shadcn 변환", "디자인 구현", "Figma 코드 변환", "implement figma design", "shadcn으로 구현", "이 피그마 shadcn으로 만들어줘", "피그마 디자인 코드 변환", or when the user provides a figma.com URL (with or without an explicit instruction). This skill enforces deterministic token chain resolution (usage → semantic → primitive) for the Ureca Shadcn team library → Next.js 16 + shadcn/ui workflow, including Light/Dark mode fidelity, token auditing via figma-token-auditor, and visual fidelity review via figma-fidelity-reviewer.

Use cases: design, frontend, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
Implement Figma → Next.js 16 + shadcn/ui
Description
This skill should be used when the user shares a Figma URL or node and asks to "구현해줘", "코드로 만들어줘", "Figma 컴포넌트 구현", "implement this Figma component", "Figma to code", "Figma shadcn 변환", "디자인 구현", "Figma 코드 변환", "implement figma design", "shadcn으로 구현", "이 피그마 shadcn으로 만들어줘", "피그마 디자인 코드 변환", or when the user provides a figma.com URL (with or without an explicit instruction). This skill enforces deterministic token chain resolution (usage → semantic → primitive) for the Ureca Shadcn team library → Next.js 16 + shadcn/ui workflow, including Light/Dark mode fidelity, token auditing via figma-token-auditor, and visual fidelity review via figma-fidelity-reviewer.
License
MIT
Instructions
266 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed
  • name: "Implement Figma → Next.js 16 + shadcn/ui" does not match folder "implement-figma-shadcn-next16"

Files (7)

  • SKILL.md
  • button-base-component.tsx · examples/
  • base-vs-template.md · references/
  • subagent-specs.md · references/
  • token-chain-rules.md · references/
  • IMPLEMENTATION_REPORT.template.md · templates/
  • figma-project.local.example.md · templates/

SKILL.md (first lines)

# Implement Figma → Next.js 16 + shadcn/ui

## Purpose

Convert Figma designs from the Ureca Shadcn team library into production-ready
Next.js 16 + shadcn/ui component code with deterministic token chain resolution,
Light/Dark mode fidelity, and visual verification.

## Three Immutable Rules

These rules apply to every implementation without exception:

1. **`codeSyntax.WEB` is the only canonical key** — never use `codeSyntax.ANDROID`, raw hex, or
   variable names directly as class names
2. **Token resolution order: `usage → semantic → primitive`** — always trace the full chain
   before falling back to raw values
3. **Mode branching only in `semantic` collection** — Light/Dark splits happen exclusively at the
   semantic layer; primitives are mode-neutral

Violation of any of these rules is a defect, not a style choice.

---

## Step 1: Verify Figma MCP Connection

Confirm `mcp__figma__get_metadata` is callable before doing anything else. If the tool is
unavailable, stop immediately and inform the user:

> "Figma MCP가 이 세션에서 연결되어 있지 않습니다. ~/.claude/mcp.json 또는 프로젝트
> .mcp.json에 Figma MCP 설정을 확인해주세요."

Do not attempt any Figma reads without MCP access.

---

## Step 2: Parse Figma Input

Extract `fileKey` and `nodeId` from the user input:

- `figma.com/design/:fileKey/:title?node-id=:nodeId` → convert `-` to `:` in nodeId
- `figma.com/design/:fileKey/branch/:branchKey/...` → use branchKey as fileKey
- `figma.com/make/:makeFileKey/:title` → use makeFileKey as fileKey
- If only fileKey given without nodeId → ask the user which node to implement before continuing

---

## Step 3: Read Figma Data

Call all four tools before analysis — do not interleave reads with interpretation:

```
1. mcp__figma__get_metadata(fileKey, nodeId)
   → node name, type, parent frame, dimensions

2. mcp__figma__get_variable_defs(fileKey)
   → all variable collections: usage / semantic / primitive + codeSyntax.WEB for each

3. mcp__figma__get_design_context(fileKey, nodeId)
   → component structure, boundVariables, named styles, fills, strokes, effects

4. mcp__figma__get_screenshot(fileKey, nodeId)
   → visual reference image (save URL/path for fidelity reviewer)
```

**MCP Error Handling:**

If any individual tool call fails:
- `get_metadata` fails → stop; node cannot be identified. Report error and ask user to verify the URL.
- `get_variable_defs` fails → continue without token data. Mark all tokens as unresolved. Use raw values only and note in report.
- `get_design_context` fails → stop; component structure cannot be determined. Report error to user.
- `get_screenshot` fails → continue. Note "automated fidelity review unavailable" in IMPLEMENTATION_REPORT.md.

---

## Step 4: Classify Node — Base Component or Template

Determine the node type before generating any code. See `references/base-vs-template.md`
for full criteria.

**Base component signals:**
- Lives in a component set or is a main component in the team library
- Single, well-defined interaction pattern (Button, Input, Badge, Select, etc.)
- Has defined component properties (variant, size, disabled, icon booleans)

**Template / Example signals:**
- Frame named "Example", "Preview", "Usage", "Demo", "Playground", or similar
- Composition of multiple base components arranged in a page-like layout
- Contains placeholder text, sample data, or lorem ipsum
- No component properties defined

If classified as **template/example**, report before proceeding:

> "⚠️ 이 노드는 base library component가 아닌 example/template composition입니다.
> 포함된 base component: [list]
> 각 base component를 개별 구현할지, 전체 composition을 구현할지 선택해주세요."

Wait for explicit user confirmation.

---

## Step 5: Resolve Token Chain

For every visual property (fill, stroke, effect, spacing, radius, typography):

**Resolution priority:**

```
1. boundVariables → follow variable ID to get_variable_defs entry
   └─ check codeSyntax.WEB → usage alias (e.g. "bg-background") → USE DIRECTLY

2. If codeSyntax.WEB points to another variable (alias chain):
   └─ resolve to semantic variable → check semantic collection modes
      ├─ Light mode value: semantic → primitive → codeSyntax.WEB
      └─ Dark mode value: same path via dark mode entry

3. Named text/effect styles → use style's codeSyntax.WEB

4. Raw fills/strokes/effects → use inline value + mark as "raw: no token binding"
```

From ureca-corp/claude, MIT.

More from ureca-corp/claude

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 24, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from ureca-corp

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Implement Figma → Next.js 16 + shadcn/ui running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying Implement Figma → Next.js 16 + shadcn/ui?

CallGet help
Cite this page

Implement Figma → Next.js 16 + shadcn/ui skill. Agent Mart. https://agentmart.dev/skills/ureca-corp-implement-figma-next-js-16-shadcn-ui-e75d7e (last updated 2026-10-24)