Skip to main content
skill CX Codex

audit-frontend-design — Claude Code skill: UI audit

Audits React and Next.js interfaces against the source tree and ties findings to files. Use it before changing UI so proposed fixes have code evidence.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add memi-design/memi --skill audit-frontend-design -a claude-code
Open on GitHub

What audit-frontend-design does

The skill checks accessibility, visual hierarchy, design tokens, component states, and responsive behavior before UI edits. It asks the agent to rank findings by user impact, verify each fix against the cited file and local tokens, then rerun the same audit after changes.

Run memi diagnose . --json --no-write --fail-on none for the main scan. Separate memi ux audit and memi craft audit commands add detail on interaction behavior and visual craft. Findings should include priorities, source evidence, and code-level changes. A screenshot alone does not mean pixel analysis took place; use browser or image tools to inspect rendered pages.

The recipes target 2.8.0-beta.2, so the local memi must report that version. npm availability does not guarantee that the native binary will work.

What it helps with

  • catch accessibility issues before UI changes
  • check hierarchy and design tokens in the source
  • tie each finding to a file and rule
  • rerun the audit and surface unresolved issues

Example prompts for the agent

  • Audit the settings page in src/app before I change its layout.
  • Check this React component for accessibility and responsive issues, with findings linked to source files.
  • Rerun the audit after my edits and list the remaining findings.

How to install audit-frontend-design

1Skills CLI (Vercel)

npx skills add memi-design/memi --skill audit-frontend-design -a claude-code

2Manually: put the files in place

~/.claude/skills/audit-frontend-design/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/audit-frontend-design/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about audit-frontend-design

How do I install audit-frontend-design in Claude Code?

Run npx skills add memi-design/memi --skill audit-frontend-design -a claude-code. The skill file is available at ~/.claude/skills/audit-frontend-design/SKILL.md.

What does audit-frontend-design do?

It checks interface code and links findings to source files, then suggests specific fixes. After edits, it reruns the same check.

What is required to run the audit?

The local memi must be version 2.8.0-beta.2. For rendered-page checks, use browser or image tools; a supplied screenshot is not proof of pixel analysis.

Source text

SKILL.md · MIT
---
name: audit-frontend-design
description: Use when reviewing or changing a React, Next.js, Tailwind, or shadcn interface and you need evidence-backed findings for accessibility, hierarchy, tokens, states, and responsive design before editing code.
---

# Audit Frontend Design

Audit the real source tree before proposing UI changes. Memi's checks are deterministic and file-anchored; no Figma connection or background process is required.

This workflow targets published beta **2.8.0-beta.2**. Use `npx -y @memi-design/[email protected] --version` to verify the exact package; a local `memi` must report that same version before these recipes run. The independent stable compatibility baseline is **2.7.9**. See [current release state](https://github.com/memi-design/memi/blob/main/docs/CURRENT_RELEASE.md) and [known limitations](https://github.com/memi-design/memi/blob/main/docs/trust/KNOWN_LIMITATIONS.md). npm availability alone does not establish native-binary success.

## Run The Audit

From the repository root:

```bash
memi diagnose . --json --no-write --fail-on none
```

For UX behavior and visual craft detail, run only the relevant follow-up:

```bash
memi ux audit . --json --no-write
memi craft audit . --json --no-write
```

A supplied screenshot is context, not proof that Memi performed pixel analysis. Use the harness browser or image tools for actual rendered checks. Use `memi diagnose . --receipt-only --fail-on none` when the output must exclude source content.

## Workflow

1. Read repository instructions and identify the requested route or component.
2. Run `diagnose` before broad UI edits.
3. Group findings by user impact, not by checker name.
4. Verify each proposed fix against the cited file and local design tokens.
5. Implement only fixes relevant to the user's request.
6. Re-run the same command and report assessed quality, category coverage, scan omissions, and remaining findings.

## Output

Lead with actionable findings:

| Priority | Evidence | Change |
| --- | --- | --- |
| High | `path/to/file.tsx:line` and rule id | Specific code-level fix |

Include the command run, before/after score, files changed, and unresolved risks. Never replace source evidence with generic taste advice.

© memi-design · MIT · memi-design/memi

Similar skills

All skills for Frontend and UI →

From the same set5

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor