返回技能列表

review-ux-ui

pjt222
更新于 2 days ago
8 次查看
17
2
17
在 GitHub 上查看
设计design

关于

This skill performs comprehensive UX/UI reviews by applying Nielsen's heuristics, WCAG 2.1 accessibility standards, and user flow analysis. It's designed for developers to audit interfaces for usability, accessibility, and cognitive load before release. Use it for heuristic evaluations, accessibility compliance checks, and form usability assessments.

快速安装

Claude Code

推荐
主要方式
npx skills add pjt222/agent-almanac -a claude-code
插件命令备选方式
/plugin add https://github.com/pjt222/agent-almanac
Git 克隆备选方式
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/review-ux-ui

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Review UX/UI

Evaluate UX and UI for usability, accessibility, and effectiveness.

When to Use

  • Usability review before release
  • Accessibility audit (WCAG 2.1 AA or AAA)
  • User flow evaluation for efficiency and error prevention
  • Form review for usability and conversion
  • Heuristic evaluation of an existing interface
  • Cognitive load and information architecture assessment

Inputs

  • Required: Application to review (URL, prototype, or source)
  • Required: Target user (roles, technical proficiency, context)
  • Optional: User research (interviews, surveys, analytics)
  • Optional: WCAG target (A, AA, or AAA)
  • Optional: Specific user flows to evaluate
  • Optional: Assistive tech to test with (screen reader, switch access)

Procedure

Step 1: Heuristic Evaluation (Nielsen's 10 Heuristics)

Evaluate against each heuristic:

#HeuristicKey QuestionRating
1Visibility of system statusDoes the system always inform users about what is happening?
2Match between system and real worldDoes the system use familiar language and concepts?
3User control and freedomCan users easily undo, redo, or exit unwanted states?
4Consistency and standardsDo similar elements behave the same way throughout?
5Error preventionDoes the design prevent errors before they occur?
6Recognition rather than recallAre options, actions, and information visible or easily retrievable?
7Flexibility and efficiency of useAre there shortcuts for experienced users without confusing novices?
8Aesthetic and minimalist designDoes every element serve a purpose? Is there unnecessary clutter?
9Help users recognize, diagnose, and recover from errorsAre error messages clear, specific, and constructive?
10Help and documentationIs help available and easy to find when needed?

Rate violation severity:

SeverityDescription
0Not a usability problem
1Cosmetic — fix if time allows
2Minor — low priority
3Major — high priority
4Catastrophic — must fix before release
## Heuristic Evaluation Findings
| # | Heuristic | Severity | Finding | Location |
|---|-----------|----------|---------|----------|
| 1 | System status | 3 | No loading indicator during data fetch — users click repeatedly | Dashboard page |
| 3 | User control | 2 | No undo for item deletion — only a confirmation dialog | Item list |
| 5 | Error prevention | 3 | Date field accepts invalid dates (Feb 30) | Booking form |
| 9 | Error recovery | 4 | Form submission error clears all fields | Registration |

Got: All 10 heuristics evaluated with findings and severity ratings. If fail: If short on time, focus on heuristics 1, 3, 5, and 9.

Step 2: Accessibility Audit (WCAG 2.1)

Perceivable

  • 1.1.1 Non-text content: Images have alt text (decorative use alt="")
  • 1.3.1 Info and relationships: Semantic HTML (headings, lists, tables, landmarks)
  • 1.3.2 Meaningful sequence: DOM order matches visual order
  • 1.4.1 Use of colour: Colour is not the only means of conveying information
  • 1.4.3 Contrast: Text contrast ≥ 4.5:1 (normal), ≥ 3:1 (large)
  • 1.4.4 Resize text: Text resizes to 200% without loss of function
  • 1.4.11 Non-text contrast: UI components and graphics ≥ 3:1 contrast
  • 1.4.12 Text spacing: Works with line height 1.5x, letter spacing 0.12em, word spacing 0.16em

Operable

  • 2.1.1 Keyboard: All functionality operable via keyboard
  • 2.1.2 No keyboard trap: Focus never trapped
  • 2.4.1 Skip links: Skip navigation link present
  • 2.4.3 Focus order: Tab order follows logical sequence
  • 2.4.7 Focus visible: Keyboard focus indicator visible
  • 2.4.11 Focus not obscured: Focused element not hidden behind sticky headers/overlays
  • 2.5.5 Target size: Targets ≥ 24x24px (44x44px on touch)

Understandable

  • 3.1.1 Language of page: lang attribute set on <html>
  • 3.2.1 On focus: Focus does not trigger unexpected changes
  • 3.2.2 On input: Input does not trigger unexpected changes without warning
  • 3.3.1 Error identification: Errors clearly described in text
  • 3.3.2 Labels or instructions: Form inputs have visible labels
  • 3.3.3 Error suggestion: Error messages suggest fixes

Robust

  • 4.1.1 Parsing: HTML valid (no duplicate IDs, proper nesting)
  • 4.1.2 Name, role, value: Custom components have ARIA roles
  • 4.1.3 Status messages: Dynamic content changes announced to screen readers

Got: WCAG 2.1 AA criteria checked with pass/fail per criterion. If fail: Use axe-core or Lighthouse for initial scan, then manual testing for criteria needing human judgement.

Step 3: Keyboard and Screen Reader Audit

Keyboard Navigation Test

Using only Tab, Shift+Tab, Enter, Space, Arrow keys, Escape:

## Keyboard Navigation Audit
| Task | Completable? | Issues |
|------|-------------|--------|
| Navigate to main content | Yes — skip link works | None |
| Open dropdown menu | Yes | Arrow keys don't work within menu |
| Submit a form | Yes | Tab order skips the submit button |
| Close a modal | No | Escape doesn't close, no visible close button in tab order |
| Use date picker | No | Custom date picker not keyboard accessible |

Screen Reader Test

Test with NVDA (Windows), VoiceOver (macOS/iOS), or TalkBack (Android):

## Screen Reader Audit
| Element | Announced As | Expected | Issue |
|---------|-------------|----------|-------|
| Logo link | "link, image" | "Home, link" | Missing alt text on logo |
| Search input | "edit, search" | "Search products, edit" | Missing label association |
| Nav menu | "navigation, main" | Correct | None |
| Error message | (not announced) | "Error: email is required" | Missing live region |
| Loading spinner | (not announced) | "Loading, please wait" | Missing aria-live or role="status" |

Got: Task flows tested with keyboard-only and screen reader. If fail: If screen reader unavailable, inspect ARIA attributes and semantic HTML as proxy.

Step 4: Analyse User Flows

Map and evaluate key user flows:

## User Flow: Complete a Purchase

### Steps
1. Browse products → 2. View product → 3. Add to cart → 4. View cart →
5. Enter shipping → 6. Enter payment → 7. Review order → 8. Confirm

### Assessment
| Step | Friction | Severity | Notes |
|------|---------|----------|-------|
| 1→2 | Low | - | Clear product cards |
| 2→3 | Medium | 2 | "Add to cart" button below the fold on mobile |
| 3→4 | Low | - | Cart icon updates with count |
| 4→5 | High | 3 | Must create account — no guest checkout |
| 5→6 | Low | - | Address autocomplete works well |
| 6→7 | Medium | 2 | Card number field doesn't auto-format |
| 7→8 | Low | - | Clear order summary |

### Flow Efficiency
- **Steps**: 8 (acceptable for e-commerce)
- **Required fields**: 14 (could reduce with address autocomplete + saved payment)
- **Decision points**: 2 (size selection, shipping method)
- **Potential drop-off points**: Step 4→5 (forced account creation)

Got: Critical user flows mapped with friction points rated. If fail: Without analytics, assess flows by task complexity and step count.

Step 5: Assess Cognitive Load

  • Information density: Amount of information per screen appropriate?
  • Progressive disclosure: Complex information revealed gradually?
  • Chunking: Related items grouped visually (Gestalt principles)?
  • Recognition over recall: Users see options rather than remember them?
  • Consistent patterns: Similar tasks use similar interaction patterns?
  • Decision fatigue: Too many choices at once? (Hick's law)
  • Working memory: Users need to remember information across steps?

Got: Cognitive load assessed with overload or underload areas identified. If fail: Use the "squint test" — squint at the screen and check if structure and hierarchy remain apparent.

Step 6: Review Form Usability

For each form:

  • Labels: Every input has a visible, associated label
  • Placeholder text: Used for examples only, not as labels
  • Input types: Correct HTML input types (email, tel, number, date)
  • Validation timing: Errors shown on blur or submit, not every keystroke
  • Error messages: Specific ("Email must include @") not generic ("Invalid input")
  • Required fields: Clearly marked
  • Field grouping: Related fields visually grouped
  • Autocomplete: autocomplete attributes for standard fields (name, email, address, cc-number)
  • Tab order: Logical flow matching visual layout
  • Multi-step forms: Progress indicator shows current and total steps
  • Persistence: Form data preserved if user navigates away and returns

Got: Each form assessed against the checklist with issues documented. If fail: With many forms, prioritize highest-traffic ones (registration, checkout, contact).

Step 7: Write the UX/UI Review

## UX/UI Review Report

### Executive Summary
[2-3 sentences: overall usability, most critical issues, strongest aspects]

### Heuristic Evaluation Summary
| Heuristic | Severity | Key Finding |
|-----------|----------|-------------|
[Summary table from Step 1]

### Accessibility Compliance
- **Target**: WCAG 2.1 AA
- **Status**: [X of Y criteria pass]
- **Critical failures**: [List]

### User Flow Analysis
[Key friction points with severity and recommendations]

### Top 5 Improvements (Prioritised)
1. **[Issue]** — Severity: [N] — [Specific recommendation]
2. ...

### What Works Well
1. [Specific positive observation]
2. ...

Got: Review provides prioritised, actionable recommendations with severity ratings. If fail: With too many issues, categorise into "must fix" (severity 3-4) and "should fix" (severity 1-2).

Validation

  • All 10 Nielsen heuristics evaluated with severity ratings
  • WCAG 2.1 criteria checked (at minimum: 1.1.1, 1.4.3, 2.1.1, 2.4.7, 3.3.1, 4.1.2)
  • Keyboard navigation tested for key user flows
  • Screen reader tested (or ARIA/semantic HTML reviewed as proxy)
  • At least one critical user flow analysed for friction
  • Cognitive load assessed
  • Form usability evaluated
  • Findings prioritised by severity with actionable recommendations

Pitfalls

  • Confusing UX with visual design: UX is how it works; visual is how it looks. Beautiful interfaces can have terrible UX. Evaluate both but distinguish them.
  • Testing only the happy path: Error states, empty states, loading states, and edge cases are where UX problems hide.
  • Ignoring real devices: Browser dev tools responsive mode is a proxy. Real device testing catches touch, performance, and viewport issues.
  • Accessibility as an afterthought: Accessibility issues found late are expensive to fix. Evaluate early and continuously.
  • Personal preference as UX feedback: "I would prefer..." is not UX feedback. Cite heuristics, research, or established patterns.

Related Skills

  • review-web-design — visual design review (layout, typography, colour)
  • scaffold-nextjs-app — Next.js application scaffolding
  • setup-tailwind-typescript — Tailwind CSS for design system

GitHub 仓库

pjt222/agent-almanac
路径: i18n/caveman-lite/skills/review-ux-ui
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

相关推荐技能

executing-plans

设计

该Skill用于当开发者提供完整实施计划时,以受控批次方式执行代码实现。它会先审阅计划并提出疑问,然后分批次执行任务(默认每批3个任务),并在批次间暂停等待审查。关键特性包括分批次执行、内置检查点和架构师审查机制,确保复杂系统实现的可控性。

查看技能

requesting-code-review

设计

该Skill可在完成任务、实现主要功能或合并代码前自动调度代码审查子代理,确保实现符合需求和计划。它支持通过指定git SHA范围进行精准的代码变更审查,帮助开发者在关键节点及时发现潜在问题。核心原则是"早审查、勤审查",适用于开发流程的各个关键阶段。

查看技能

connect-mcp-server

设计

这个Skill指导开发者如何将MCP服务器连接到Claude Code,支持HTTP、stdio和SSE三种传输协议。它涵盖了从安装配置到认证安全的完整流程,适用于集成GitHub、Notion、数据库等外部服务。当开发者需要添加集成、配置外部工具或提及MCP相关功能时,这个Skill能提供实用的操作指南。

查看技能

web-cli-teleport

设计

该Skill帮助开发者根据任务特性选择Claude Code的Web或CLI界面,并指导如何在两种环境间无缝迁移会话。它能分析任务复杂度、迭代需求等要素,推荐最优工作界面和工作流。关键特性包括会话状态管理、环境切换指导和上下文优化建议。

查看技能