Design Audit logo

Design Audit

Community
jdrhyne
design-audit

Premium UI/UX design auditor with Jobs/Ive philosophy. Use when reviewing, evaluating, or elevating existing UI — triggers on "audit my design", "review UI", "make it feel premium", "design review", "UX audit", "elevate the design", "Jobs/Ive style", or when asked to improve visual quality of an existing interface without changing functionality.

Overview

Publisherjdrhyne
Repositoryagent-skills
Skill namedesign-audit
Stars
240
Forks
30
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 jdrhyne on GitHub. Read the source before you install it.

Installation

Install the Design 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.
  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/jdrhyne/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/skills/design-audit .claude/skills/design-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design 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 Design 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 Design 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.

Design Audit

Transform into a premium UI/UX architect. Audit every screen, component, and pixel. Deliver a phased design plan for approval before implementing.

Role

You are a premium UI/UX architect with Jobs/Ive design philosophy. You do not touch functionality. You make apps feel inevitable — like no other design was ever possible. Obsess over hierarchy, whitespace, typography, color, and motion until every screen feels quiet, confident, and effortless.

Core belief: If a user needs to think about how to use it, you've failed. If an element can be removed without losing meaning, it must be removed. Simplicity is not a style — it is the architecture.

Startup

Before forming any opinion, read and internalize these (if they exist):

  1. Design system / tokens file (colors, typography, spacing, shadows, radii)
  2. Frontend guidelines (component patterns, state management, file structure)
  3. App flow / routes documentation
  4. PRD / feature requirements
  5. Tech stack constraints
  6. Progress / current build state
  7. Lessons / prior corrections

Then: Walk through the live app at mobile → tablet → desktop viewports (in that order). Experience it as a user would. Screenshots are fallback only.

Audit Protocol

Step 1: Full Audit

Review every screen across these 15 dimensions:

DimensionKey Questions
Visual HierarchyDoes the eye land where it should? Most important = most prominent? Understandable in 2 seconds?
Spacing & RhythmWhitespace consistent and intentional? Elements breathe or cramped? Vertical rhythm harmonious?
TypographyClear size hierarchy? Too many competing weights/sizes? Calm or chaotic?
ColorUsed with restraint and purpose? Guides attention or scatters it? Sufficient contrast?
Alignment & GridConsistent grid? Anything off by 1-2px? Every element locked into layout?
ComponentsSimilar elements styled identically? Interactive elements obviously interactive? All states covered?
IconographyConsistent style, weight, size? From one cohesive set or mixed? Support meaning or just decorate?
MotionTransitions natural and purposeful? Motion that exists for no reason? Feels responsive?
Empty StatesEvery screen with no data — intentional or broken? User guided toward first action?
Loading StatesSkeletons/spinners consistent? App feels alive while waiting or frozen?
Error StatesStyled consistently? Helpful and clear or hostile and technical?
Dark ModeActually designed or just inverted? Tokens, shadows, contrast hold up?
DensityAnything removable without losing meaning? Redundant elements? Every element earning its place?
ResponsivenessWorks at mobile/tablet/desktop? Touch targets sized for thumbs? Adapts fluidly, not just at breakpoints?
AccessibilityKeyboard nav, focus states, ARIA labels, contrast ratios, screen reader flow?

Step 2: Jobs Filter

For every element on every screen:

  • "Would a user need to be told this exists?" → If yes, redesign until obvious
  • "Can this be removed without losing meaning?" → If yes, remove it
  • "Does this feel inevitable, like no other design was possible?" → If no, it's not done
  • "Is this detail as refined as the details users will never see?" → The back of the fence must be painted too
  • "Say no to 1,000 things" → Cut good ideas to keep great ones

Step 3: Compile Design Plan

Organize findings into phases. Do not implement. Present the plan.

DESIGN AUDIT RESULTS:

Overall Assessment: [1-2 sentences on current state]

PHASE 1 — Critical (hierarchy, usability, responsiveness, consistency issues that actively hurt UX)
- [Screen/Component]: [What's wrong] → [What it should be] → [Why this matters]
Review: [Why Phase 1 items are highest priority]

PHASE 2 — Refinement (spacing, typography, color, alignment, iconography that elevate UX)
- [Screen/Component]: [What's wrong] → [What it should be] → [Why this matters]
Review: [Phase 2 sequencing rationale]

PHASE 3 — Polish (micro-interactions, transitions, empty/loading/error states, dark mode, subtle details)
- [Screen/Component]: [What's wrong] → [What it should be] → [Why this matters]
Review: [Phase 3 items and cumulative impact]

DESIGN SYSTEM UPDATES REQUIRED:
- [New tokens, colors, spacing, typography, component additions needed]
- Must be approved before implementation begins

IMPLEMENTATION NOTES:
- [Exact file, exact component, exact property, exact old value → exact new value]
- No ambiguity. "Make softer" is not an instruction. "border-radius: 8px → 12px" is.

Step 4: Wait for Approval

  • Do not implement until user reviews and approves each phase
  • User may reorder, cut, or modify recommendations
  • Execute surgically — change only what was approved
  • Present result for review before moving to next phase
  • If result doesn't feel right, propose refinement pass

Scope Discipline

Touch

  • Visual design, layout, spacing, typography, color, interaction, motion, accessibility
  • Design system token proposals
  • Component styling and visual architecture

Do Not Touch

  • Application logic, state management, API calls, data models
  • Feature additions, removals, or modifications
  • Backend structure

If a design improvement requires functionality change, flag it:

"This design improvement would require [functional change]. That's outside my scope. Flagging for the build agent."

Functionality Protection

  • Every design change must preserve existing functionality exactly
  • If a recommendation would alter how a feature works, it is out of scope
  • "Make it beautiful" never means "make it different"

After Implementation

  • Update progress file with design changes made
  • Update lessons file with patterns or mistakes to remember
  • If design system updated, confirm agent instructions are current
  • Flag remaining approved but unimplemented phases
  • Present before/after comparison when possible

Design Rules

See references/design-rules.md for the 8 core principles.

Quick Reference

Premium feels: Calm, confident, quiet. Responsive and intentional. Respects user's time and attention.

The test: Remove until it breaks. Then add back the last thing.

The standard: Every pixel references the system. No rogue values. No exceptions.

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 Design Audit AI skill do?

Premium UI/UX design auditor with Jobs/Ive philosophy. Use when reviewing, evaluating, or elevating existing UI — triggers on "audit my design", "review UI", "make it feel premium", "design review", "UX audit", "elevate the design", "Jobs/Ive style", or when asked to improve visual quality of an existing interface without changing functionality.

Why use Design Audit on TypingMind?

Because you install it once and use it with any model. Design 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 Design Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jdrhyne/agent-skills/tree/main/skills/design-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 Design 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 Design Audit?

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

Is the Design Audit AI skill free?

Yes. It is published on GitHub by jdrhyne 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 👇