# figma-code-connect-components

Maps published Figma design components to codebase implementations using Figma Code Connect. It inspects component properties and pairs them with repository files.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2700 installs · ★ 28329
- Author: openai · official OpenAI repository
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/openai/skills/tree/HEAD/skills/.curated/figma-code-connect-components/SKILL.md
- Updated: 2026-09-08
- HTML: https://affpapa.org/en/nevibecode/skills/openai-figma-code-connect-components

## What it does

The skill coordinates Code Connect integration between design files and local source code. It calls `get_code_connect_suggestions` to detect unmapped elements in the target Figma node, collecting component names, variants, and thumbnails while skipping items already linked.

Next, the agent scans directories like `src/components/` to match component structures and prop signatures in TypeScript or JavaScript. After the user reviews and confirms the suggested matches, the skill executes `send_code_connect_mappings` in a single batch.

When using `figma-desktop` MCP, the active canvas selection is read directly without passing URLs. For web links, the `node-id` query parameter is mandatory. The workflow requires a Figma Organization or Enterprise plan and published team library components.

## Requirements
- Works with: Figma

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/skills --skill figma-code-connect-components -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/figma-code-connect-components/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/figma-code-connect-components/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/skills --skill figma-code-connect-components -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/figma-code-connect-components/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/skills --skill figma-code-connect-components -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/figma-code-connect-components/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install openai/skills figma-code-connect-components
```

2. **Manually: put the files in place**
- File: `.github/skills/figma-code-connect-components/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/skills --skill figma-code-connect-components -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/openai/skills --path skills/.curated/figma-code-connect-components
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/figma-code-connect-components/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add openai/skills --skill figma-code-connect-components -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/openai/skills/tree/HEAD/skills/.curated/figma-code-connect-components/SKILL.md

## When to use it
- detect unmapped design components within a Figma node
- match Figma variant properties to code component props
- register Code Connect mappings in batches via MCP
- locate matching UI files across the project codebase

## Example prompts
- Connect this selected Figma component to our code using Code Connect
- Map unlinked components from the Figma URL to our repository UI elements
- Find matching codebase components for the selected Figma node and establish Code Connect links

## Similar
- [pcf-code-components](https://affpapa.org/en/nevibecode/rules/pcf-code-components.md) — rule · ★ 40451
- [pcf-sample-components](https://affpapa.org/en/nevibecode/rules/pcf-sample-components.md) — rule · ★ 40451
- [stitch::react-components](https://affpapa.org/en/nevibecode/skills/stitchreact-components.md) — skill · 50400 installs
- [frontend-design](https://affpapa.org/en/nevibecode/skills/frontend-design.md) — skill · 1025790 installs
- [grill-me](https://affpapa.org/en/nevibecode/skills/grill-me.md) — skill · 1424476 installs
- [design-taste-frontend](https://affpapa.org/en/nevibecode/skills/design-taste-frontend.md) — skill · 678700 installs
- [prototype](https://affpapa.org/en/nevibecode/skills/prototype.md) — skill · 986201 installs
- [grilling](https://affpapa.org/en/nevibecode/skills/grilling.md) — skill · 979543 installs

From the same set: [openai/skills](https://affpapa.org/en/nevibecode/by/openai/skills.md) — 25 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
