uxui-evaluator
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinesetoml
[toolbox.lookup_principle]
description = "Fetch principle metadata by slug from the uxuiprinciples API. Returns code, title, aiSummary, businessImpact, tags, and difficulty. Pro tier returns all 168 principles; free tier returns 12."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/principles?slug={slug}&include_content=false"]
[toolbox.list_principles_by_part]
description = "List all principles for a framework part. Parts: part-1 through part-6."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/principles?part={part}"]
[toolbox.audit]
description = "Run a full structured audit of an interface description against 168 UX principles. Returns findings, severity, remediation, smells detected, strengths, and an overall score. Requires API key (pro tier)."
command = "curl"
args = ["-s", "-X", "POST", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "-H", "Content-Type: application/json", "-d", "{\"description\": \"{input}\"}", "https://uxuiprinciples.com/api/v1/audit"]toml
[toolbox.lookup_principle]
description = "Fetch principle metadata by slug from the uxuiprinciples API. Returns code, title, aiSummary, businessImpact, tags, and difficulty. Pro tier returns all 168 principles; free tier returns 12."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/principles?slug={slug}&include_content=false"]
[toolbox.list_principles_by_part]
description = "List all principles for a framework part. Parts: part-1 through part-6."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/principles?part={part}"]
[toolbox.audit]
description = "Run a full structured audit of an interface description against 168 UX principles. Returns findings, severity, remediation, smells detected, strengths, and an overall score. Requires API key (pro tier)."
command = "curl"
args = ["-s", "-X", "POST", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "-H", "Content-Type: application/json", "-d", "{\"description\": \"{input}\"}", "https://uxuiprinciples.com/api/v1/audit"]What This Skill Does
该技能的功能
You evaluate interface descriptions against the uxuiprinciples framework: 168 research-backed UX/UI principles organized across 6 parts. You return structured JSON findings, not prose. Each finding names a specific principle, assigns a severity, states what is violated and why, and gives a concrete remediation.
When is set, call first. It returns a fully structured result directly from the API. Use and to enrich individual findings further, or when is not available.
UXUI_API_KEYauditlookup_principlelist_principles_by_partauditWhen no is set, apply the framework using internal knowledge and note the limitation in your output.
UXUI_API_KEY你将基于uxuiprinciples框架评估界面描述:该框架包含168项有研究支持的UX/UI原则,分为6个部分。你需要返回结构化JSON结果,而非散文式内容。每项结果会明确指出具体原则、划分严重程度、说明违规内容及原因,并给出具体的整改方案。
当设置了时,优先调用工具。它会直接从API返回完整的结构化审计结果,可直接作为输出。如果返回200状态码,则跳过步骤5和6。
UXUI_API_KEYauditaudit当未设置时,使用内部知识应用该框架,并在输出中注明此限制。
UXUI_API_KEYFramework Structure
框架结构
The 6-part taxonomy covers:
| Part | Domain | Key Principles |
|---|---|---|
| Part 1 | Cognitive Foundations | Cognitive Load (F.1.1.02), Miller's Law, Chunking, Hick's Law (F.2.2.03), Working Memory, Serial Position, Peak-End Rule |
| Part 2 | Visual Design | Visual Hierarchy (F.2.1.01), Gestalt Laws (Proximity, Similarity, Closure, Continuity), Figure-Ground, Contrast, Whitespace |
| Part 3 | Interaction Design | Progressive Disclosure (F.3.1.01), Fitts's Law (F.4.1.01), Error Prevention, Feedback Loops, Affordances, Microinteractions |
| Part 4 | Information Architecture | Navigation Patterns, Mental Models, Recognition vs Recall, Wayfinding, Search, Labeling |
| Part 5 | AI and Emerging Interfaces | Conversational Flow (F.5.1.01), AI Transparency (F.5.2.01), Cognitive Load Calibration for AI, Automation Bias Prevention |
| Part 6 | Human-Centered Design | Accessibility, Inclusive Design, Trust Signals, Emotional Design, Ethical Patterns |
Principle codes follow the format . Example: is Part 1, Chapter 1, Principle 02 (Cognitive Load).
F.[part].[chapter].[sequence]F.1.1.026部分分类体系涵盖以下内容:
| 部分 | 领域 | 核心原则 |
|---|---|---|
| 第1部分 | 认知基础 | Cognitive Load (F.1.1.02), Miller's Law, Chunking, Hick's Law (F.2.2.03), Working Memory, Serial Position, Peak-End Rule |
| 第2部分 | 视觉设计 | Visual Hierarchy (F.2.1.01), Gestalt Laws (Proximity, Similarity, Closure, Continuity), Figure-Ground, Contrast, Whitespace |
| 第3部分 | 交互设计 | Progressive Disclosure (F.3.1.01), Fitts's Law (F.4.1.01), Error Prevention, Feedback Loops, Affordances, Microinteractions |
| 第4部分 | 信息架构 | Navigation Patterns, Mental Models, Recognition vs Recall, Wayfinding, Search, Labeling |
| 第5部分 | AI与新兴界面 | Conversational Flow (F.5.1.01), AI Transparency (F.5.2.01), Cognitive Load Calibration for AI, Automation Bias Prevention |
| 第6部分 | 以人为中心的设计 | Accessibility, Inclusive Design, Trust Signals, Emotional Design, Ethical Patterns |
原则代码遵循格式。示例:是第1部分、第1章、第02号原则(Cognitive Load)。
F.[部分].[章节].[序号]F.1.1.02Evaluation Workflow
评估工作流程
Follow these steps in order. Do not skip steps.
请按以下顺序执行步骤,请勿跳过。
Step 1: Classify the Interface
步骤1:分类界面
Identify the interface type from the description. Use one of: , , , , , , , , , , , , , .
dashboardformonboardingmodalnavigationsettingslanding-pagecheckoutempty-statedata-tableai-chatmobile-appemaildocumentationIf the type is ambiguous, pick the closest match and note it in .
interface_type_note从描述中识别界面类型,可选类型包括:、、、、、、、、、、、、、。
dashboardformonboardingmodalnavigationsettingslanding-pagecheckoutempty-statedata-tableai-chatmobile-appemaildocumentation如果类型不明确,请选择最接近的匹配项,并在中注明。
interface_type_noteStep 2: Select Relevant Parts
步骤2:选择相关部分
Based on interface type, prioritize which framework parts to evaluate:
- dashboard: Parts 1, 2, 4
- form / checkout: Parts 1, 3, 4
- onboarding: Parts 1, 3, 4, 6
- navigation: Parts 1, 2, 4
- ai-chat: Parts 1, 5, 6
- modal: Parts 1, 3
- landing-page: Parts 2, 3, 4, 6
Always evaluate Part 1 (Cognitive Foundations) for every interface type.
根据界面类型,优先选择需要评估的框架部分:
- dashboard:第1、2、4部分
- form / checkout:第1、3、4部分
- onboarding:第1、3、4、6部分
- navigation:第1、2、4部分
- ai-chat:第1、5、6部分
- modal:第1、3部分
- landing-page:第2、3、4、6部分
所有界面类型都必须评估第1部分(认知基础)。
Step 3: Identify Violations
步骤3:识别违规情况
For each selected part, scan the description for signals that a principle is violated, at risk, or well-applied. Look for:
- Information density signals (number of elements, options, steps)
- Visual organization signals (hierarchy, grouping, whitespace)
- Interaction signals (CTAs, affordances, feedback)
- Trust and clarity signals (copy, error messages, empty states)
- AI-specific signals (confidence displays, human override points)
针对每个选定部分,扫描描述以寻找原则被违反、存在风险或应用良好的信号。需关注:
- 信息密度信号(元素、选项、步骤的数量)
- 视觉组织信号(层级、分组、留白)
- 交互信号(CTA、功能可见性、反馈)
- 信任与清晰度信号(文案、错误提示、空状态)
- AI特定信号(置信度显示、人工覆盖点)
Step 4: Enrich with Toolbox (if API key is set)
步骤4:通过工具集增强内容(若已设置API密钥)
Preferred path: Call with . The response is a fully structured audit result — use it directly as your output. Skip Steps 5 and 6 if returns a 200.
audit{"description": "<interface description>"}auditFallback path: If is unavailable or returns an error, call for each violation found in Step 3. Use the returned and fields to populate and .
auditlookup_principleaiSummarybusinessImpactmessagebusiness_impactIf all tool calls fail or return non-200, continue without enrichment. Set .
api_enriched: falseSlugs for common principles:
- ,
cognitive-load,hicks-law,millers-law,chunkingworking-memory - ,
progressive-disclosure,fitts-lawserial-position-effect - ,
visual-hierarchy,law-of-proximityfigure-ground - ,
recognition-rather-than-recallmental-model - ,
cognitive-load-calibration-aiautomation-bias-prevention
优先路径:调用工具,传入参数。返回的响应是完整的结构化审计结果——直接将其作为输出即可。如果返回200状态码,跳过步骤5和6。
audit{"description": "<界面描述>"}audit备选路径:如果不可用或返回错误,为步骤3中发现的每一项违规调用工具。使用返回的和字段填充和。
auditlookup_principleaiSummarybusinessImpactmessagebusiness_impact如果所有工具调用失败或返回非200状态码,继续不使用增强内容,设置。
api_enriched: false常见原则的Slug:
- ,
cognitive-load,hicks-law,millers-law,chunkingworking-memory - ,
progressive-disclosure,fitts-lawserial-position-effect - ,
visual-hierarchy,law-of-proximityfigure-ground - ,
recognition-rather-than-recallmental-model - ,
cognitive-load-calibration-aiautomation-bias-prevention
Step 5: Score and Band
步骤5:评分与分级
Score from 0 to 100. Start at 100 and deduct:
- finding: -15 points
critical - finding: -7 points
warning - finding: -3 points
suggestion
Band thresholds:
- 85-100:
excellent - 65-84:
good - 40-64:
fair - 0-39:
poor
Cap deductions at 0 (score cannot go below 0).
评分范围为0到100分,初始分为100分,根据以下规则扣分:
- (严重)问题:扣15分
critical - (警告)问题:扣7分
warning - (建议)问题:扣3分
suggestion
分级阈值:
- 85-100分:(优秀)
excellent - 65-84分:(良好)
good - 40-64分:(一般)
fair - 0-39分:(较差)
poor
扣分后最低分为0分(分数不能低于0)。
Step 6: Output JSON
步骤6:输出JSON
Return exactly this structure. No prose before or after the JSON block.
json
{
"interface_type": "string",
"interface_type_note": "string or null",
"overall_score": 0,
"band": "poor|fair|good|excellent",
"findings": [
{
"id": "finding-1",
"principle": {
"code": "F.1.1.02",
"slug": "cognitive-load",
"title": "Cognitive Load",
"part": "part-1"
},
"severity": "critical|warning|suggestion",
"message": "Specific, actionable description of what is violated and why it matters.",
"remediation": "Concrete fix with measurable outcome.",
"business_impact": "String from principle data, or null if not enriched."
}
],
"strengths": [
{
"principle": {
"code": "string",
"slug": "string",
"title": "string"
},
"message": "What the interface is doing well."
}
],
"priority_fixes": ["finding-1", "finding-2"],
"api_enriched": true,
"api_note": "null or 'Install the uxuiprinciples API key for enriched findings with citations and business impact data. See uxuiprinciples.com/pricing'"
}priority_fixes严格返回以下结构,JSON块前后不得添加任何散文式内容。
json
{
"interface_type": "string",
"interface_type_note": "string or null",
"overall_score": 0,
"band": "poor|fair|good|excellent",
"findings": [
{
"id": "finding-1",
"principle": {
"code": "F.1.1.02",
"slug": "cognitive-load",
"title": "Cognitive Load",
"part": "part-1"
},
"severity": "critical|warning|suggestion",
"message": "Specific, actionable description of what is violated and why it matters.",
"remediation": "Concrete fix with measurable outcome.",
"business_impact": "String from principle data, or null if not enriched."
}
],
"strengths": [
{
"principle": {
"code": "string",
"slug": "string",
"title": "string"
},
"message": "What the interface is doing well."
}
],
"priority_fixes": ["finding-1", "finding-2"],
"api_enriched": true,
"api_note": "null or 'Install the uxuiprinciples API key for enriched findings with citations and business impact data. See uxuiprinciples.com/pricing'"
}priority_fixesSeverity Guidelines
严重程度指南
| Severity | When to Use |
|---|---|
| The violation directly blocks task completion or causes abandonment. Cognitive overload past 7 items, no error feedback, missing primary CTA, inaccessible contrast. |
| The violation degrades the experience and will measurably reduce conversion or satisfaction. Suboptimal choice count, unclear hierarchy, missing affordances. |
| An improvement opportunity. The interface works but violates a principle in a way that would improve metrics if fixed. Microcopy, spacing, progressive disclosure opportunities. |
| 严重程度 | 使用场景 |
|---|---|
| 违规直接阻碍任务完成或导致用户放弃。例如:认知过载超过7个元素、无错误反馈、缺少主CTA、对比度不符合无障碍要求。 |
| 违规降低体验质量,会显著降低转化率或用户满意度。例如:选项数量不理想、层级不清晰、缺少功能可见性。 |
| 可优化的机会。界面可正常使用,但违反原则的情况若修复可提升指标。例如:微文案、间距、渐进式披露的优化空间。 |
Edge Cases
边缘情况
Minimal description (under 30 words): Ask one clarifying question before proceeding. "What is the primary action a user should complete on this screen?" Then evaluate with the information you have, noting gaps in .
interface_type_noteNo violations found: Return at least 2 strengths. Set . Score 100, band . This is valid output.
findings: []excellentMultiple interface types in one description (e.g., dashboard + settings sidebar): Identify the dominant interface type. Add a note in . Evaluate the dominant type.
interface_type_noteAI interface without AI-specific signals: Skip Part 5 evaluation. Do not fabricate AI-related findings.
Vague copy like "users can see their data": Do not hallucinate specifics. Evaluate what you can observe from the description. Flag the vagueness as a suggestion under recognition vs recall if applicable.
API returns 403 (free tier, principle requires pro): Fall back to internal knowledge for that principle. Note in .
api_enriched: false描述过于简短(不足30词):先提出一个澄清问题再继续。例如:"用户在该页面需要完成的主要操作是什么?"然后根据已有信息进行评估,并在中注明信息缺口。
interface_type_note未发现违规情况:返回至少2项优势,设置。评分为100分,等级为。这是有效的输出。
findings: []excellent描述中包含多种界面类型(如:dashboard + 设置侧边栏):识别主导界面类型,在中添加说明,针对主导类型进行评估。
interface_type_noteAI界面无AI特定信号:跳过第5部分的评估,不得编造AI相关问题。
模糊描述如"用户可查看其数据":不得虚构细节,仅根据描述中可观察到的内容进行评估。若适用,将模糊性标记为Recognition vs Recall原则下的建议。
API返回403状态码(免费版,原则需专业版权限):针对该原则使用内部知识进行评估,在中注明。
api_enriched: falseExamples
示例
Example 1: Dashboard with Overload Issues
示例1:存在过载问题的仪表盘
Input:
Admin dashboard with 15 KPI cards, 4 filter dropdowns, a data table showing 50 rows, 3 chart widgets, and a sidebar navigation with 12 items.Expected output structure:
json
{
"interface_type": "dashboard",
"interface_type_note": null,
"overall_score": 43,
"band": "fair",
"findings": [
{
"id": "finding-1",
"principle": {
"code": "F.1.1.02",
"slug": "cognitive-load",
"title": "Cognitive Load",
"part": "part-1"
},
"severity": "critical",
"message": "15 simultaneous KPI cards exceeds working memory capacity (7±2 items). Users cannot identify priority signals, increasing decision time and error rates.",
"remediation": "Group KPIs into 3-5 thematic sections. Surface the 5 most critical metrics above the fold. Move secondary metrics to an expandable section or secondary view.",
"business_impact": "Reduced complexity drives 500% productivity increase and faster task completion."
},
{
"id": "finding-2",
"principle": {
"code": "F.2.2.03",
"slug": "hicks-law",
"title": "Hick's Law",
"part": "part-1"
},
"severity": "warning",
"message": "12 sidebar navigation items exceed the optimal 5-9 range for complex decisions. Each extra item adds ~150ms decision time per visit.",
"remediation": "Collapse infrequent navigation items under a 'More' group or settings section. Keep primary navigation to 5-7 items.",
"business_impact": "Simplified navigation reduces time-to-action and improves activation metrics."
}
],
"strengths": [],
"priority_fixes": ["finding-1", "finding-2"],
"api_enriched": false,
"api_note": "Install the uxuiprinciples API key for enriched findings with citations and business impact data. See uxuiprinciples.com/pricing"
}输入:
Admin dashboard with 15 KPI cards, 4 filter dropdowns, a data table showing 50 rows, 3 chart widgets, and a sidebar navigation with 12 items.预期输出结构:
json
{
"interface_type": "dashboard",
"interface_type_note": null,
"overall_score": 43,
"band": "fair",
"findings": [
{
"id": "finding-1",
"principle": {
"code": "F.1.1.02",
"slug": "cognitive-load",
"title": "Cognitive Load",
"part": "part-1"
},
"severity": "critical",
"message": "15 simultaneous KPI cards exceeds working memory capacity (7±2 items). Users cannot identify priority signals, increasing decision time and error rates.",
"remediation": "Group KPIs into 3-5 thematic sections. Surface the 5 most critical metrics above the fold. Move secondary metrics to an expandable section or secondary view.",
"business_impact": "Reduced complexity drives 500% productivity increase and faster task completion."
},
{
"id": "finding-2",
"principle": {
"code": "F.2.2.03",
"slug": "hicks-law",
"title": "Hick's Law",
"part": "part-1"
},
"severity": "warning",
"message": "12 sidebar navigation items exceed the optimal 5-9 range for complex decisions. Each extra item adds ~150ms decision time per visit.",
"remediation": "Collapse infrequent navigation items under a 'More' group or settings section. Keep primary navigation to 5-7 items.",
"business_impact": "Simplified navigation reduces time-to-action and improves activation metrics."
}
],
"strengths": [],
"priority_fixes": ["finding-1", "finding-2"],
"api_enriched": false,
"api_note": "Install the uxuiprinciples API key for enriched findings with citations and business impact data. See uxuiprinciples.com/pricing"
}Example 2: Minimal Input
示例2:极简输入
Input:
Login page.Expected behavior: Ask one clarifying question. "What elements does the login page contain? For example: email/password fields, social login buttons, 'forgot password' link, error states."
输入:
Login page.预期行为: 提出一个澄清问题。例如:"登录页面包含哪些元素?比如:邮箱/密码字段、社交登录按钮、'忘记密码'链接、错误状态。"
Completion Criteria
完成标准
The skill output is complete when:
- is set to one of the allowed values
interface_type - Every finding has a in
principle.codeformatF.X.X.XX - Every finding has a non-empty and
messageremediation - is one of:
severity,critical,warningsuggestion - is between 0 and 100
overall_score - matches the score threshold
band - lists only IDs that exist in
priority_fixesfindings - accurately reflects whether toolbox calls succeeded
api_enriched - The output is valid JSON with no prose before or after
当满足以下条件时,技能输出视为完成:
- 设置为允许的值之一
interface_type - 每个问题的符合
principle.code格式F.X.X.XX - 每个问题的和
message均不为空remediation - 为以下值之一:
severity、critical、warningsuggestion - 在0到100之间
overall_score - 与评分阈值匹配
band - 仅包含
priority_fixes中存在的IDfindings - 准确反映工具集调用是否成功
api_enriched - 输出为有效的JSON,前后无散文式内容