Figma Audit logo

Figma Audit

Organization
memi-design
figma-audit

Audit Figma file for design system consistency, accessibility, token adoption, Code Connect coverage

Overview

Publishermemi-design
Repositorydesign-skills
Skill namefigma-audit
Stars
7
Forks
0
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by memi-design on GitHub. Read the source before you install it.

Installation

Install the Figma Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/memi-design/design-skills/tree/main/skills/figma-audit
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/memi-design/design-skills.git /tmp/design-skills
mkdir -p .claude/skills
cp -r /tmp/design-skills/skills/figma-audit .claude/skills/figma-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Figma Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Figma Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Figma Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/figma-audit — Design System Audit & Quality Check

Audit a Figma file for design system consistency, accessibility compliance, token adoption, and Code Connect coverage. Produces actionable findings. Requires /figma-use.

Freedom Level: Read-Only + Report

Audit skills read and analyze but do not modify the canvas. Output is a structured report with severity levels.

When to Use

  • Before a design handoff to development
  • After pulling a design system (memi pull)
  • Periodic design system health checks
  • When components look inconsistent or broken
  • Before establishing Code Connect mappings

Audit Checklist

1. Token Adoption

figma_get_variables → list all defined tokens
get_design_context for each page → check usage

Report:
  ✓ Bound to variable: colors/primary/500
  ✗ Raw hex: #3b82f6 (should be colors/primary/500)
  ✗ Magic number: 16px padding (should be spacing/4)

Metric: % of visual properties bound to variables
Target: 90%+

2. Component Consistency

figma_search_components → list all components
figma_get_component_details for each → check structure

Report:
  ✓ Auto Layout applied
  ✓ Properties documented
  ✓ Variants complete (default, hover, active, disabled, focused)
  ✗ Missing state: Button has no "loading" variant
  ✗ Inconsistent padding: Card uses 16px, CardHeader uses 12px

Metric: % of components with all required states
Target: 100% for atoms, 90% for molecules

3. Atomic Design Compliance

Check each component's classification:
  ✓ Atom: no nested component instances (correct)
  ✗ Atom: Button contains Icon instance (should be molecule or use instance swap)
  ✓ Molecule: FormField composes Label + Input + HelpText
  ✗ Organism: LoginForm classified as molecule (too complex)

Metric: % of components correctly classified
Target: 95%+

4. Accessibility

For each component:
  ✓ Contrast ratio: text on background meets WCAG AA (4.5:1)
  ✗ Touch target: Button is 32px tall (needs 44px minimum)
  ✓ Focus indicator: visible focus ring
  ✗ Missing: no aria-label on icon-only button

For each page:
  ✓ Heading hierarchy: h1 → h2 → h3 (no skips)
  ✗ Missing landmark: no main content area defined
  ✓ Color not sole indicator: error states use icon + color

Metric: WCAG violations per page
Target: 0 critical, <5 minor

5. Code Connect Coverage

get_code_connect_map → current mappings

Report:
  ✓ Mapped: Button → src/components/ui/button.tsx
  ✓ Mapped: Card → src/components/ui/card.tsx
  ✗ Unmapped: MetricCard (no code counterpart)
  ✗ Stale: FormField maps to deleted file

Metric: % of components with valid Code Connect
Target: 80%+ for atoms, 60%+ for molecules

6. Naming Conventions

Check against naming rules:
  ✓ PascalCase: MetricCard, LoginForm
  ✗ Wrong case: metric-card (should be MetricCard)
  ✗ Vague name: "Frame 47" (rename to meaningful name)
  ✓ Token path: colors/primary/500

Metric: % of elements following naming conventions
Target: 100%

7. Auto Layout Health

For each container:
  ✓ Has Auto Layout
  ✗ Uses absolute positioning (should be Auto Layout)
  ✓ Sizing: fill container (correct for content area)
  ✗ Sizing: hug contents (should be fill for responsive element)
  ✓ Spacing uses token values

Metric: % of containers using Auto Layout
Target: 95%+

Output Format

╔══════════════════════════════════════╗
║     Design System Audit Report       ║
╚══════════════════════════════════════╝

Score: 82/100

Token Adoption:      87% ✓
Component Quality:   79% ⚠
Atomic Compliance:   95% ✓
Accessibility:       74% ⚠
Code Connect:        65% ✗
Naming:             92% ✓
Auto Layout:         89% ✓

Critical Issues (fix immediately):
  1. Button has no focus indicator
  2. 23 raw hex values should be variables
  3. FormField Code Connect points to deleted file

Warnings (fix soon):
  1. MetricCard missing "loading" variant
  2. 5 components have inconsistent padding

Recommendations:
  1. Run: memi tokens → re-export and bind
  2. Run: add_code_connect_map for 12 unmapped components
  3. Add missing variant states to 8 components

Integration

  • Save audit results to .memoire/audit.json for tracking over time
  • Compare against previous audits to show improvement
  • Block memi sync if critical issues exceed threshold

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Figma Audit AI skill do?

Audit Figma file for design system consistency, accessibility, token adoption, Code Connect coverage

Why use Figma Audit on TypingMind?

Because you install it once and use it with any model. Figma Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Figma Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/memi-design/design-skills/tree/main/skills/figma-audit. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Figma Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Figma Audit?

As many as you like. As long as a model supports skills, you can use Figma Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Figma Audit AI skill free?

Yes. It is published on GitHub by memi-design under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇