Skip to content
Development
Command

/design-review

Review existing UI for issues and improvements

From plugin
agents
42k93 skills137 agents93 commands
$ npx -y skills add wshobson/agents --agent claude-code

Command definition

design-review.md
description: "Review existing UI for issues and improvements"
argument-hint: "[file-path|component-name]"

Design Review

Review existing UI code for design issues, usability problems, and improvement opportunities. Provides actionable recommendations.

Pre-flight Checks

1. Check if `.ui-design/` directory exists:

  • If not: Create `.ui-design/` directory
  • Create `.ui-design/reviews/` subdirectory for storing review results

2. Load project context if available:

  • Check for `conductor/product.md` for product context
  • Check for `conductor/tech-stack.md` for framework info
  • Check for `.ui-design/design-system.json` for design tokens

Target Identification

If argument provided:

  • If file path: Validate file exists, read the file
  • If component name: Search codebase for matching component files
  • If not found: Display error with suggestions

If no argument:

Ask user to specify target:

What would you like me to review?

1. A specific component (provide name or path)
2. A page/route (provide path)
3. The entire UI directory
4. Recent changes (last commit)

Enter number or provide a file path:

Interactive Review Configuration

**CRITICAL RULES:**

  • Ask ONE question per turn
  • Wait for user response before proceeding
  • Gather context to provide relevant feedback

Q1: Review Focus

What aspects should I focus on?

1. Visual design (spacing, alignment, typography, colors)
2. Usability (interaction patterns, accessibility basics)
3. Code quality (patterns, maintainability, reusability)
4. Performance (render optimization, bundle size)
5. Comprehensive (all of the above)

Enter number:

Q2: Design Context (if visual/usability selected)

What is this UI's primary purpose?

1. Data display (dashboards, tables, reports)
2. Data entry (forms, wizards, editors)
3. Navigation (menus, sidebars, breadcrumbs)
4. Content consumption (articles, media, feeds)
5. E-commerce (product display, checkout)
6. Other (describe)

Enter number or description:

Q3: Target Platform

What platform(s) should I consider?

1. Desktop only
2. Mobile only
3. Responsive (desktop + mobile)
4. All platforms (desktop, tablet, mobile)

Enter number:

State Management

Create/update `.ui-design/reviews/review_state.json`:

{
  "review_id": "{target}_{YYYYMMDD_HHMMSS}",
  "target": "{file_path_or_component}",
  "focus_areas": ["visual", "usability", "code", "performance"],
  "context": "{purpose}",
  "platform": "{platform}",
  "status": "in_progress",
  "started_at": "ISO_TIMESTAMP",
  "issues_found": 0,
  "severity_counts": {
    "critical": 0,
    "major": 0,
    "minor": 0,
    "suggestion": 0
  }
}

Review Execution

1. Code Analysis

Read and analyze the target files:

  • Parse component structure
  • Identify styling approach (CSS, Tailwind, styled-components, etc.)
  • Detect framework (React, Vue, Svelte, etc.)
  • Note component composition patterns

2. Visual Design Review

Check for:

**Spacing & Layout:**

  • Inconsistent margins/padding
  • Misaligned elements
  • Unbalanced whitespace
  • Magic numbers vs. design tokens

**Typography:**

  • Font size consistency
  • Line height appropriateness
  • Text contrast ratios
  • Font weight usage

**Colors:**

  • Color contrast accessibility
  • Consistent color usage
  • Semantic color application
  • Dark mode support (if applicable)

**Visual Hierarchy:**

  • Clear primary actions
  • Appropriate emphasis
  • Scannable content structure

3. Usability Review

Check for:

**Interaction Patterns:**

  • Clear clickable/tappable areas
  • Appropriate hover/focus states
  • Loading state indicators
  • Error state handling
  • Empty state handling

**User Flow:**

  • Logical tab order
  • Clear call-to-action
  • Predictable behavior
  • Feedback on actions

**Cognitive Load:**

  • Information density
  • Progressive disclosure
  • Clear labels and instructions
  • Consistent patterns

4. Code Quality Review

Check for:

**Component Patterns:**

  • Single responsibility
  • Prop drilling depth
  • State management appropriateness
  • Component reusability

**Styling Patterns:**

  • Consistent naming conventions
  • Reusable style definitions
  • Media query organization
  • CSS specificity issues

**Maintainability:**

  • Clear component boundaries
  • Documentation/comments
  • Test coverage
  • Accessibility attributes

5. Performance Review

Check for:

**Render Optimization:**

  • Unnecessary re-renders
  • Missing memoization
  • Large component trees
  • Expensive computations in render

**Asset Optimization:**

  • Image sizes and formats
  • Icon implementation
  • Font loading strategy
  • Code splitting opportunities

Output Format

Generate review report in `.ui-design/reviews/{review_id}.md`:

# Design Review: {Component/File Name}

**Review ID:** {review_id}
**Reviewed:** {YYYY-MM-DD HH:MM}
**Target:** {file_path}
**Focus:** {focus_areas}

## Summary

{2-3 sentence overview of findings}

**Issues Found:** {total_count}

- Critical: {count}
- Major: {count}
- Minor: {count}
- Suggestions: {count}

## Critical Issues

### Issue 1: {Title}

**Severity:** Critical
**Location:** {file}:{line}
**Category:** {Visual|Usability|Code|Performance}

**Problem:**
{Description of the issue}

**Impact:**
{Why this matters for users/maintainability}

**Recommendation:**
{Specific fix suggestion}

**Code Example:**

```{language}
// Before
{current_code}

// After
{suggested_code}

---

## Major Issues

### Issue 2: {Title}

...

## Minor Issues

### Issue 3: {Title}

...

## Suggestions

### Suggestion 1: {Title}

...

## Positive Observations

{List things done well to reinforce good patterns}

- {Positive observation 1}
- {Positive observation 2}

## Next Steps

1. {Prioritized action 1}
2. {Prioritized action 2}
3. {Prioritized action 3}

---

_Generated by UI Design Review. Run `/ui-design:design-review` again after fixes._

Completion

After generating report:

1. Update `review_state.json`:

  • Set `stat
Read more
@wshobson
Ships withagents

Use one collection of plugins, agents, skills, and commands across Claude Code, OpenAI Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi. A harness is the coding tool that loads and runs the components.

42k185 skills137 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
42.4k
Star history of wshobson/agents on GitHub, a chart by star-history.com

Other commands on agents.

accessibility-audit

accessibility-audit

Command

Audit web accessibility for WCAG compliance with automated axe-core tests, keyboard and screen reader checks, and remediation…

@wshobson@wshobsonInstall Command
improve-agent

improve-agent

Command

Improve an existing agent through performance baselines, prompt engineering, A/B testing, and staged rollout

@wshobson@wshobsonInstall Command
multi-agent-optimize

multi-agent-optimize

Command

Optimize multi-agent system performance through profiling, context window tuning, coordination efficiency, and cost and latency…

@wshobson@wshobsonInstall Command
team-debug

team-debug

Command

Debug issues using competing hypotheses with parallel investigation by multiple agents

@wshobson@wshobsonInstall Command
team-delegate

team-delegate

Command

Task delegation dashboard for managing team workload, assignments, and rebalancing

@wshobson@wshobsonInstall Command
team-feature

team-feature

Command

Develop features in parallel with multiple agents using file ownership boundaries and dependency management

@wshobson@wshobsonInstall Command

More commands from other plugins.

build
Auto-invoked

build

Command

Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.

@addyosmani@addyosmaniInstall Command