Agent skill

Design Review

by jezweb in jezweb/claude-skills

Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour.

MITAuto-check passedFrontend & Design

Install Design Review

skills CLI
$ npx skills add jezweb/claude-skills --skill design-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jezweb/claude-skills design-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jezweb/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/frontend/skills/design-review .claude/skills/design-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
design-review
GitHub stars
1.1k
Token cost
~2.1k tokens
SKILL.md length
975 words
Files
1
Skills in repo
52
Repo updated
First seen
Licence
MIT

At a glance

Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour.

  • Works in 7 steps: Layout and Spacing → Typography → Colour and Contrast → …
  • Tasks that involve Design review and critique
  • SKILL.md covers When to Use, Browser Tool Detection, URL Resolution and What to Check, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Design Review is an agent skill from jezweb/claude-skills. Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots. Triggers: 'design review', 'does this look good', 'review the design', 'check the layout', 'is this polished', 'visual review', 'design audit', 'make it look better', 'it looks off'.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: claude-code-only

It sits in Frontend & Design, covering Design review and critique, UI design and UX design. The repository describes itself as: Skills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations. The licence is MIT.

When your agent uses it

  • Tasks that involve Design review and critique
  • Tasks that involve UI design
  • Tasks that involve UX design

Example prompts

  • “design review”
  • “does this look good”
  • “review the design”
  • “/design-review”

Requirements

  • Compatibility (from SKILL.md): claude-code-only

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Layout and Spacing
  2. Typography
  3. Colour and Contrast
  4. Visual Hierarchy
  5. Component Consistency
  6. Interaction Design
  7. Responsive Quality

What it can do on your machine

Read from SKILL.md and the folder at commit 1260fa7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    claude-code-only

    From compatibility in the SKILL.md frontmatter.

Context cost

Design Review loads about 2.1k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 975 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~127
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jezweb/claude-skills at commit 1260fa7, republished under its MIT licence (© jezweb). 975 words, ~2,140 tokens.

Download SKILL.mdSave it as .claude/skills/design-review/SKILL.md (or your agent's skills folder).
name
design-review
description
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots. Triggers: 'design review', 'does this look good', 'review the design', 'check the layout', 'is this polished', 'visual review', 'design audit', 'make it look better', 'it looks off'.
compatibility
claude-code-only

Design Review

Review a web app or page for visual design quality. This is not a UX audit (usability, workflow, friction) — this checks whether the design is professional, consistent, and polished.

The goal: would a design-conscious person look at this and think "this is well made" or "this looks like a developer designed it"?

When to Use

  • Before showing something to a client or team
  • When something "looks off" but you can't pinpoint why
  • After building a feature, before calling it done
  • Periodic quality check on a shipped product
  • After a UX audit — this is the visual companion

Browser Tool Detection

Same as ux-audit — Chrome MCP, Playwright MCP, or playwright-cli.

URL Resolution

Same as ux-audit — prefer deployed/live over localhost.

What to Check

1. Layout and Spacing
CheckGoodBad
Consistent spacingSame gap between all cards in a grid, same padding in all sectionsSome cards have 16px gap, others 24px. Header padding differs from body
AlignmentLeft edges of content align vertically across sectionsHeading starts at one indent, body text at another, cards at a third
Breathing roomGenerous whitespace around content, elements don't feel crampedText touching container edges, buttons crowded against inputs
Grid disciplineContent follows a clear column gridElements placed freely, no underlying structure
Responsive proportionsSidebar/content ratio looks intentional at every widthSidebar takes 50% on tablet, content is squeezed
Vertical rhythmConsistent vertical spacing pattern (e.g. 8px/16px/24px/32px scale)Random spacing: 13px here, 27px there, 8px somewhere else
2. Typography
CheckGoodBad
HierarchyClear visual difference between h1 → h2 → h3 → bodyHeadings and body text look the same size/weight
Line lengthBody text 50-75 characters per lineFull-width text running 150+ characters — hard to read
Line heightBody text 1.5-1.7, headings 1.1-1.3Cramped text or excessive line height
Font sizesConsistent scale (e.g. 14/16/20/24/32)Random sizes: 15px, 17px, 22px with no relationship
Weight usageRegular for body, medium for labels, semibold for headings, bold sparinglyEverything bold, or everything regular with no hierarchy
TruncationLong text truncates with ellipsis, title attribute shows full textText overflows container, wraps awkwardly, or is cut off without ellipsis
3. Colour and Contrast
CheckGoodBad
Semantic colourUsing design tokens (bg-primary, text-muted-foreground)Raw Tailwind colours (bg-blue-500, text-gray-300)
Contrast ratioText meets WCAG AA (4.5:1 for body, 3:1 for large text)Light grey text on white, or dark text on dark backgrounds
Colour consistencySame blue means the same thing everywhere (primary = action)Blue means "clickable" in one place and "informational" in another
Dark modeAll elements visible, borders defined, no invisible textElements disappear, text becomes unreadable, images look wrong
Status coloursGreen=success, yellow=warning, red=error consistentlyGreen used for both success and "active" with different meanings
Colour overuse2-3 colours + neutralsRainbow of colours with no clear hierarchy
4. Visual Hierarchy
CheckGoodBad
Primary actionOne clear CTA per page, visually dominantThree equally styled buttons competing for attention
Squint testSquinting at the page, the most important element stands outEverything is the same visual weight — nothing draws the eye
Progressive disclosureMost important info visible, details available on interactionEverything shown at once — overwhelming
GroupingRelated items are visually grouped (proximity, borders, backgrounds)Related items scattered, unrelated items touching
Negative spaceIntentional empty space that frames contentEmpty space that looks accidental (uneven, trapped white space)
Show full SKILL.md (421 more words)Show less
5. Component Consistency
CheckGoodBad
Button stylesOne primary style, one secondary, one destructive — used consistently5 different button styles across the app
Card stylesAll cards have the same border-radius, shadow, paddingSome cards rounded, some sharp, some with shadows, some without
Form inputsAll inputs same height, same border style, same focus ringMix of heights, border styles, focus behaviours
Icon styleOne icon family (Lucide, Heroicons), consistent size and strokeMixed icon families, different sizes, some filled some outlined
Border radiusConsistent radius scale (e.g. 4px inputs, 8px cards, 12px modals)Random radius values: 3px, 7px, 10px, 16px
ShadowOne or two shadow levels used consistentlyEvery component has a different shadow depth
6. Interaction Design
CheckGoodBad
Hover statesButtons, links, and clickable cards change on hoverNo hover feedback — user unsure what's clickable
Focus statesKeyboard focus visible on all interactive elementsFocus ring missing or invisible against background
Active statesNav items, tabs, sidebar links show current selectionActive item looks the same as inactive
TransitionsSubtle transitions on hover/focus (150-200ms ease)No transitions (jarring) or slow transitions (laggy)
Loading indicatorsSkeleton screens or spinners during async operationsContent pops in without warning, layout shifts
Disabled statesDisabled elements are visually muted, cursor changesDisabled buttons look clickable, no cursor change
7. Responsive Quality
CheckGoodBad
Mobile navClean hamburger/sheet menu, easy to tapDesktop nav squished into mobile, tiny tap targets
Image scalingImages fill containers proportionallyImages stretched, cropped badly, or overflowing
Table responsivenessHorizontal scroll on mobile, or stack to cardsTable wider than screen with no way to see columns
Touch targetsAt least 44x44px on mobileTiny links, close buttons, checkboxes
TabletLayout works at 768px (not just desktop and phone)Layout breaks at tablet widths, awkward gaps

Severity Guide

LevelMeaningExample
HighLooks broken or unprofessionalInvisible text in dark mode, buttons different heights inline
MediumLooks unpolishedInconsistent spacing, mixed icon styles, truncation without ellipsis
LowNitpick1-2px alignment, slightly different border-radius, shadow too strong

Output

Write findings to .jez/artifacts/design-review.md:

markdown
# Design Review: [App Name]
**Date**: YYYY-MM-DD
**URL**: [url]

## Overall Impression
[1-2 sentences — professional / unpolished / inconsistent / clean]

## Findings

### High
- **[issue]** at [page/component] — [what's wrong] → [fix]

### Medium
- **[issue]** at [page/component] — [what's wrong] → [fix]

### Low
- **[issue]** — [description]

## What Looks Good
[Patterns that are well-executed and should be preserved]

## Top 3 Fixes
1. [highest visual impact change]
2. [second]
3. [third]

Take screenshots of findings where the issue is visual (most of them).

Tips

  • Check dark mode AND light mode — most issues appear in one but not the other
  • The squint test is the fastest way to find hierarchy problems
  • Component inconsistency is the most common issue in dev-built UIs
  • "Looks off" usually means spacing — check margins and padding first
  • If you can't identify the issue, compare to a well-designed app in the same category

© jezweb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/frontend/skills/design-review of jezweb/claude-skills.

Open the folder on GitHubat commit 1260fa7

Compare with similar skills

Design Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Design Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design Review this skilljezweb/claude-skills1.1k—~2.1kAutomated safety check: PassMIT
Design Critiquemohitagw15856/pm-claude-skills1.4k—~1.5kAutomated safety check: PassMIT
Interface Design for Dashboards and Appsholaboss-ai/holaOS11k3 repos~6kAutomated safety check: PassMIT
Product Design Workflow BundleXiaomiMiMo/MiMo-Code14k—~721Automated safety check: PassMIT
UI Reviewespennilsen/pi122—~1.4kAutomated safety check: PassMIT
Steve Jobs Design Reviewwondelai/skills2.4k—~4.5kAutomated safety check: PassMIT

Similar skills

  • Design Critique

    mohitagw15856/pm-claude-skills

    Give structured, constructive feedback on any design using UX frameworks.

    1.4k GitHub stars~1.5k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Pushes an agent past generic defaults when designing dashboards, admin panels, SaaS apps and tools, with attention to structure, type, navigation and how data is shown.

    11k GitHub starsUsed in 3 repos~6k tokens
    Frontend & DesignAuto-check passed
  • Product Design Workflow Bundle

    XiaomiMiMo/MiMo-Code

    Entry point to a bundle of product design workflows covering context, research, audits, ideation, URL or image to code, design QA and sharing a prototype.

    14k GitHub stars~721 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • UI Review

    espennilsen/pi

    Review UI designs and implementations for accessibility, consistency, usability, and visual quality.

    122 GitHub stars~1.4k tokensUpdated 19 days ago
    Frontend & DesignAuto-check passed
  • Review designs, products, and features with Steve Jobs' standards: ruthless simplicity, focus, and end-to-end excellence.

    2.4k GitHub stars~4.5k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Om UX Review PR

    go-musicfox/go-musicfox

    Evidence-first design review of a PR's UI. An agent skill from go-musicfox/go-musicfox.

    2.6k GitHub starsUsed in 1 repo~1.4k tokens
    Frontend & DesignAuto-check: notes

More from jezweb/claude-skills

All 52 skills in this repo
  • Favicon Gen

    jezweb/claude-skills

    Generate custom favicons from logos, text, or brand colours.

    1.1k GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Tailwind Theme Builder

    jezweb/claude-skills

    Set up Tailwind v4 + shadcn/ui themed UI with dark mode. An agent skill from jezweb/claude-skills.

    1.1k GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed
  • Elevenlabs Agents

    jezweb/claude-skills

    Build conversational AI voice agents on the ElevenLabs platform.

    1.1k GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Responsiveness Check

    jezweb/claude-skills

    Test website responsiveness across viewport widths using browser automation.

    1.1k GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • MCP Builder

    jezweb/claude-skills

    Build MCP servers in Python with FastMCP. An agent skill from jezweb/claude-skills.

    1.1k GitHub stars~3.1k tokensUpdated yesterday
    Auto-check: notes
  • GitHub Release

    jezweb/claude-skills

    Prepare and publish GitHub releases. An agent skill from jezweb/claude-skills.

    1.1k GitHub stars~944 tokensUpdated yesterday
    Auto-check: notes

Questions about Design Review

What does Design Review do?

Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Design Review is an agent skill from jezweb/claude-skills. Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour.

When should I use Design Review?

Design Review fits situations like: tasks that involve Design review and critique; tasks that involve UI design; tasks that involve UX design.

How do I install Design Review in Claude Code?

Run `npx skills add jezweb/claude-skills --skill design-review -a claude-code`. Or copy the skill folder (plugins/frontend/skills/design-review in jezweb/claude-skills) into .claude/skills/design-review in your project. Claude Code loads it when a task matches its description.

How do I install Design Review in Codex?

Run `npx skills add jezweb/claude-skills --skill design-review -a codex`. Or copy the skill folder (plugins/frontend/skills/design-review in jezweb/claude-skills) into .agents/skills/design-review in your project. Codex loads it when a task matches its description.

Can I use Design Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jezweb/claude-skills --skill design-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-review, .gemini/skills/design-review, .github/skills/design-review and .opencode/skills/design-review in your project.

What does Design Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Design Review is instructions for the agent only. Compatibility (from SKILL.md): claude-code-only.

Does Design Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Design Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Design Review use?

Design Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Design Review use?

About 2.1k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Design Review?

Skills that share tags, products or a category with Design Review: Design Critique (mohitagw15856/pm-claude-skills, 1.4k stars), Interface Design for Dashboards and Apps (holaboss-ai/holaOS, 11k stars), Product Design Workflow Bundle (XiaomiMiMo/MiMo-Code, 14k stars) and UI Review (espennilsen/pi, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design Review?

jezweb (a GitHub user) maintains it in jezweb/claude-skills, which has 1,055 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 9, 2026.

Source: jezweb/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.