# review-design-parity

Compares a built interface with its Figma frame and lists where layout, tokens or interactions drift. Useful before handing off a screen.

- command · `type=command` · Codex, ChatGPT · ★ 7604
- Author: Figma · official OpenAI repository
- License: LicenseRef-Figma-Developer-Terms · policy=link-only · description only; the file stays with the author
- Source: https://github.com/openai/plugins/tree/HEAD/plugins/figma/commands/review-design-parity.md
- Updated: 2026-10-08
- HTML: https://affpapa.org/en/nevibecode/commands/review-design-parity

## What it does

You give the command two things: a Figma frame or component URL, and the local page or component to inspect. It pulls the design context and a screenshot from Figma, then looks at the current implementation and runs whatever local preview or test path applies.

The comparison covers layout, typography, tokens, assets and interactions. Results come back findings-first, ordered by severity, with suggested fixes after. The report also states which evidence was checked — screenshot, local preview, tests — and what was missing that would block a full parity call.

Both arguments are required, so a run without `figma_url` and `target` goes nowhere. No access to the Figma file means the screenshot and design-context step fails, and there is nothing to compare against.

## Requirements
- Works with: Figma

## Install

### Codex (native platform)

**Manually: put the files in place**
- File: `~/.codex/prompts/review-design-parity.md` — Call it with /prompts:review-design-parity. Codex marks this format deprecated in favour of skills

### Claude Code

**Manually: put the files in place**
- File: `.claude/commands/review-design-parity.md` — Call it with /review-design-parity. For all projects use ~/.claude/commands/

### GitHub Copilot

**Manually: put the files in place**
- File: `.github/prompts/review-design-parity.prompt.md`

### Gemini CLI

**Manually: put the files in place**
- File: `.gemini/commands/review-design-parity.toml` — Gemini stores commands as TOML: the prompt text goes into the prompt field

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/openai/plugins/tree/HEAD/plugins/figma/commands/review-design-parity.md

## When to use it
- check a built screen against its Figma frame
- spot spacing and typography drift
- confirm colors and tokens match the design
- catch interaction differences in components
- produce a mismatch report before handoff

## Example prompts
- Review design parity for this page: `figma_url` is the frame link, `target` is `src/pages/Checkout.tsx`
- Compare the Figma component with the local implementation and order findings by severity
- Run review-design-parity on the profile page and tell me what evidence was missing

## Similar
- [checklist-design](https://affpapa.org/en/nevibecode/skills/checklist-design.md) — skill · 1100 installs
- [frontend-design-review](https://affpapa.org/en/nevibecode/skills/dauquangthanh-frontend-design-review.md) — skill · 458 installs
- [design-review](https://affpapa.org/en/nevibecode/skills/design-review.md) — skill · 5800 installs
- [ui-design-review](https://affpapa.org/en/nevibecode/skills/ui-design-review.md) — skill · 1100 installs
- [build-design](https://affpapa.org/en/nevibecode/skills/build-design.md) — skill · 3600 installs
- [figma-generate-design](https://affpapa.org/en/nevibecode/skills/openai-figma-generate-design.md) — skill · 2900 installs

From the same set: [openai/plugins](https://affpapa.org/en/nevibecode/by/openai/plugins.md) — 528 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