Back to Details

heuristic-evaluation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Heuristic Evaluation

启发式评估

Systematic usability review using established principles.
使用成熟原则开展的系统性可用性审核。

When to Trigger

触发时机

  • User shares a screenshot, mockup, or prototype
  • User asks for design feedback or review
  • User asks "what's wrong with this"
  • User wants to improve an interface
  • Before shipping user-facing changes
  • 用户分享截图、mockup 或原型
  • 用户寻求设计反馈或审核
  • 用户询问「这有什么问题」
  • 用户想要优化界面
  • 在面向用户的变更上线前

Quick Start

快速开始

  1. Ask user to share the interface (screenshot, URL, or description)
  2. Ask: "Any specific flows or areas of concern?"
  3. Run evaluation using Nielsen's 10 (default) or requested framework
  1. 请用户分享界面（截图、URL 或文字描述）
  2. 询问：「是否有需要重点关注的特定流程或模块？」
  3. 使用 Nielsen's 10（默认）或用户要求的框架开展评估

Core Workflow

核心流程

Heuristic Evaluation Progress:
- [ ] Step 1: Capture interface context
- [ ] Step 2: Select evaluation framework
- [ ] Step 3: Evaluate against each heuristic
- [ ] Step 4: Score severity of issues
- [ ] Step 5: Prioritize recommendations
Heuristic Evaluation Progress:
- [ ] Step 1: Capture interface context
- [ ] Step 2: Select evaluation framework
- [ ] Step 3: Evaluate against each heuristic
- [ ] Step 4: Score severity of issues
- [ ] Step 5: Prioritize recommendations

Step 1: Capture Context

步骤1：获取上下文

Before evaluating, understand:
  • What is this? (App type, purpose)
  • Who uses it? (Target users, expertise level)
  • What task? (Primary user flow being evaluated)
If not provided, ask: "What are users trying to accomplish here?"
评估前先明确以下信息：
  • 这是什么？（应用类型、核心用途）
  • 目标用户是谁？（目标受众、专业水平）
  • 要完成什么任务？（待评估的核心用户流程）
如果用户未提供相关信息，可询问：「用户在这里想要完成什么操作？」

Step 2: Select Framework

步骤2：选择评估框架

Default: Nielsen's 10 Usability Heuristics
Alternatives (if user requests or context suggests):
  • Shneiderman's 8 Golden Rules — for interaction-heavy interfaces
  • Cognitive Walkthrough — for first-time user experience
  • Custom rubric — if user provides one
See references/frameworks.md for full framework details.
默认框架：Nielsen's 10 可用性启发式原则
替代框架（用户要求或上下文适配时使用）：
  • Shneiderman's 8 Golden Rules —— 适用于交互密集型界面
  • 认知走查 —— 适用于首次用户体验评估
  • 自定义规则 —— 若用户提供了专属评估标准
完整框架说明可查看 references/frameworks.md。

Step 3: Nielsen's 10 Evaluation

步骤3：Nielsen's 10 评估

For each heuristic, identify violations:
#HeuristicWhat to look for
1Visibility of system statusLoading indicators, progress, confirmation, current state
2Match real worldFamiliar language, logical order, conventions from domain
3User control & freedomUndo, cancel, exit, back navigation, escape hatches
4Consistency & standardsSame words/actions mean same things, platform conventions
5Error preventionConfirmations for destructive actions, constraints, defaults
6Recognition over recallVisible options, contextual help, no memorization required
7Flexibility & efficiencyShortcuts, customization, accelerators for experts
8Aesthetic & minimalistNo irrelevant info, clear hierarchy, signal vs noise
9Help users with errorsPlain language errors, specific problem, constructive solution
10Help & documentationSearchable, task-focused, concise, accessible when needed
对照每一条启发式原则，识别违规问题：
#启发式原则检查要点
1系统状态可见性加载指示器、进度提示、确认信息、当前状态展示
2匹配真实世界认知用户熟悉的语言、逻辑排序、对应领域的通用惯例
3用户控制权与自由度撤销、取消、退出、返回导航、应急退出路径
4一致性与标准化相同词汇/操作对应相同含义，符合平台通用规范
5错误预防危险操作二次确认、操作约束、合理默认值
6识别优于回忆可见的操作选项、上下文帮助、无需用户记忆信息
7灵活性与高效性快捷键、自定义设置、面向专家用户的加速操作
8审美与极简设计无冗余信息、清晰的信息层级、区分有效信息与干扰项
9帮助用户识别、处理错误通俗易懂的错误提示、明确的问题说明、可落地的解决方案
10帮助与文档可搜索、面向具体任务、简洁清晰、用户需要时可快速获取

Step 4: Score Severity

步骤4：问题严重度评分

Rate each issue found:
ScoreSeverityDescription
0Not a problemDisagreement with heuristic but not usability issue
1CosmeticFix only if time permits
2MinorLow priority, causes minor friction
3MajorHigh priority, significant impact on task completion
4CatastrophicMust fix before release, prevents task completion
Scoring factors:
  • Frequency: How often does user encounter this?
  • Impact: How much does it block the task?
  • Persistence: Can users work around it?
为每个发现的问题打分：
评分严重等级说明
0无问题与启发式原则有差异但不属于可用性问题
1外观问题时间充裕时再修复
2轻微问题低优先级，仅造成微小操作阻碍
3严重问题高优先级，对任务完成有明显影响
4阻断性问题上线前必须修复，会导致用户无法完成任务
评分参考因素：
  • 出现频率：用户遇到该问题的频次有多高？
  • 影响程度：对任务完成的阻塞程度有多大？
  • 可绕过性：用户是否有办法绕过该问题继续操作？

Step 5: Prioritize Output

步骤5：输出优先级排序

Rank issues by: Severity × Frequency
Group into:
  1. Fix immediately (Severity 4, or Severity 3 + high frequency)
  2. Fix soon (Severity 3, or Severity 2 + high frequency)
  3. Fix later (Severity 1-2, low frequency)
按「严重度 × 出现频率」对问题排序，分为三类：
  1. 立即修复（严重度4，或严重度3 + 高出现频率）
  2. 尽快修复（严重度3，或严重度2 + 高出现频率）
  3. 延后修复（严重度1-2，低出现频率）

Output Template

输出模板

Automatically save the output to 
design/08-heuristic-evaluation.md
using the Write tool while presenting it to the user.
markdown
undefined
向用户展示结果的同时，使用 Write 工具自动将输出保存到 
design/08-heuristic-evaluation.md
。
markdown
undefined

Heuristic Evaluation: [Interface Name]

Heuristic Evaluation: [Interface Name]

Evaluated: [Date] Framework: Nielsen's 10 Usability Heuristics Scope: [Specific flow or screens evaluated]
Evaluated: [Date] Framework: Nielsen's 10 Usability Heuristics Scope: [Specific flow or screens evaluated]

Summary

Summary

  • Critical issues: [count]
  • Major issues: [count]
  • Minor issues: [count]
  • Critical issues: [count]
  • Major issues: [count]
  • Minor issues: [count]

Critical Issues (Fix Immediately)

Critical Issues (Fix Immediately)

Issue 1: [Brief description]

Issue 1: [Brief description]

  • Heuristic violated: #[number] — [name]
  • Location: [Where in the interface]
  • Problem: [What's wrong]
  • Impact: [How it affects users]
  • Recommendation: [How to fix]
  • Severity: [0-4]
[Repeat for each critical issue]
  • Heuristic violated: #[number] — [name]
  • Location: [Where in the interface]
  • Problem: [What's wrong]
  • Impact: [How it affects users]
  • Recommendation: [How to fix]
  • Severity: [0-4]
[Repeat for each critical issue]

Major Issues (Fix Soon)

Major Issues (Fix Soon)

[Same format]
[Same format]

Minor Issues (Fix Later)

Minor Issues (Fix Later)

[Same format, can be condensed to a table]
[Same format, can be condensed to a table]

Strengths Observed

Strengths Observed

  • [What the interface does well]
  • [What the interface does well]

Next Steps

Next Steps

  1. [Prioritized action]
  2. [Prioritized action]
undefined
  1. [Prioritized action]
  2. [Prioritized action]
undefined

Adaptive Behavior

适配逻辑

If user provides a screenshot:
  • Analyze visually
  • Call out specific elements by location
  • Be concrete: "The save button in the top right..." not "buttons should..."
If user describes interface:
  • Ask clarifying questions before evaluating
  • Focus on described pain points first
If user is designer:
  • Skip heuristic definitions
  • Use shorthand: "H4 violation" instead of explaining consistency
If user is developer:
  • Include implementation-aware suggestions
  • Note which fixes are quick wins vs architectural changes
如果用户提供了截图：
  • 开展可视化分析
  • 按位置指出具体元素
  • 表述要具体：「右上角的保存按钮...」而非「按钮应该...」
如果用户仅通过文字描述界面：
  • 评估前先询问明确相关信息
  • 优先关注用户提到的痛点
如果用户是设计师：
  • 跳过启发式原则的定义说明
  • 使用行业简写：「H4违规」而非解释一致性原则的定义
如果用户是开发者：
  • 提供考虑实现成本的优化建议
  • 标注哪些修复是快速可完成的，哪些需要架构层面调整

Handoff

交接

After presenting the evaluation, suggest:
"Use this report to prioritize fixes. Want me to help refine any screens based on these findings?"
Note: File is automatically saved to 
design/08-heuristic-evaluation.md
for reference.
展示完评估结果后，可向用户建议：
"Use this report to prioritize fixes. Want me to help refine any screens based on these findings?"
注意： 评估报告自动保存到 
design/08-heuristic-evaluation.md
可随时查阅。

Integration Points

搭配使用场景

Works well with:
  • assumption-mapping
    — before building, question if the design addresses real needs
  • critique
    — for broader feedback beyond usability
  • accessibility-audit
    — for WCAG-specific evaluation
与以下能力配合使用效果更佳：
  • assumption-mapping
    —— 开发前验证设计是否满足真实用户需求
  • critique
    —— 用于可用性之外的更广泛设计反馈
  • accessibility-audit
    —— 用于 WCAG 合规性专项评估

References

参考资料

  • references/frameworks.md — Full heuristic definitions and alternatives
  • references/examples.md — Sample evaluations
  • references/frameworks.md —— 完整的启发式原则定义与替代框架说明
  • references/examples.md —— 启发式评估示例