{ "schemaVersion": 1, "slug": "ui-design-skills-tested", "status": "verified", "capturedAt": "2026-10-25T08:39:09.640Z", "title": { "zh": "4 款 UI 设计 Skill 实测：公开结果", "en": "4 UI Design Skills Tested: Public Results" }, "environment": { "host": "Kimi AgentSwarm", "model": "kimi-1021-preview", "alias": "kimi-cn/kimi-1021-preview", "thinkingEffort": "max", "cli": null, "independentGenerations": 15, "anonymousVisualReviews": 15, "runsPerCondition": 3, "conditionExecution": "Conditions could run in parallel. Runs within each condition were sequential and used fresh agents and workspaces.", "skillAccess": "Read only the assigned SKILL.md once and follow it. No Skill tool or other Skills were allowed. The no-Skill control read none.", "bestOfSelection": false, "wallClockUsedForRanking": false }, "task": { "name": "CommonShelf", "brief": "Build one finished personal tool directory with fixed content, real filtering, saved tools, suggestions, FAQ, failure states and responsive behavior. Deliver one direction only.", "stack": "Plain static HTML, CSS and JavaScript", "contentData": "/comparisons/ui-design-skills-tested/demos/oil-ui/run-1/content.json", "externalRuntimeRequests": 0, "viewports": [ { "name": "desktop", "width": 1440, "height": 900 }, { "name": "mobile", "width": 390, "height": 844 } ], "acceptanceScenarios": [ "desktop-baseline", "mobile-baseline", "interaction-and-persistence", "content-unavailable", "storage-unavailable", "reduced-motion" ] }, "scoreScale": { "totalMax": 100, "dimensions": [ { "key": "visualHierarchyAndReadability", "label": { "zh": "视觉层级与可读性", "en": "Visual hierarchy and readability" }, "max": 20 }, { "key": "productFitAndOriginality", "label": { "zh": "产品契合与原创性", "en": "Product fit and originality" }, "max": 20 }, { "key": "responsive", "label": { "zh": "响应式", "en": "Responsive behavior" }, "max": 15 }, { "key": "interactionAndStateFeedback", "label": { "zh": "交互与状态反馈", "en": "Interaction and state feedback" }, "max": 20 }, { "key": "accessibility", "label": { "zh": "可访问性", "en": "Accessibility" }, "max": 15 }, { "key": "detailAndMotion", "label": { "zh": "细节与动效", "en": "Detail and motion" }, "max": 10 } ], "averageRule": "Exact arithmetic mean of the three run totals; each run total is independently recomputed from its six dimensions.", "displayRule": "Candidate averages are displayed to one decimal place in the article; exact sums and six-decimal averages are preserved here." }, "functionalTotals": { "runs": 15, "passed": 13, "failed": 2 }, "publicMediaPolicy": { "primaryRunIndex": 1, "desktopInitialImages": 15, "mobileInitialImages": 5, "formImagesUsedAsPrimaryVisual": false, "selectionRule": "Run-1 is always the primary image; all three desktop-initial images remain available for every candidate." }, "limitations": [ "One English static CommonShelf brief, one model and three final samples per condition.", "One anonymous visual review per run, not large-scale user research or a statistical-significance experiment.", "Six predefined Chromium acceptance scenario groups, not a complete cross-browser, assistive-technology or WCAG audit.", "No dedicated tablet screenshots; static captures cannot fully describe continuous animation timing.", "Technical interruptions and protocol-bound recovery were not counted as candidate functional failures or used to compare elapsed time." ], "candidates": [ { "id": "oil-ui", "name": "Oil UI open source", "version": "0.24.2", "officialSource": { "name": "Oil UI (open source)", "version": "0.24.2", "repository": "https://github.com/oil-oil/oil-ui", "tag": "v0.24.2", "commit": "a66a177742fd213608cb99d9a6cfc2f357a65d25", "license": "MIT" }, "visualAverage": { "scoreSum": 261, "runCount": 3, "average": 87, "decimal": "87.000000", "display": "87.0", "fraction": "261/3", "dimensionScoreSums": { "visualHierarchyAndReadability": 53, "productFitAndOriginality": 53, "responsive": 40, "interactionAndStateFeedback": 53, "accessibility": 40, "detailAndMotion": 22 }, "dimensionAverages": { "visualHierarchyAndReadability": 17.666667, "productFitAndOriginality": 17.666667, "responsive": 13.333333, "interactionAndStateFeedback": 17.666667, "accessibility": 13.333333, "detailAndMotion": 7.333333 } }, "runs": [ { "runId": "oil-ui/run-1", "runIndex": 1, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 18, "productFitAndOriginality": 17, "responsive": 13, "interactionAndStateFeedback": 18, "accessibility": 14, "detailAndMotion": 8 }, "totalScore": 88, "totalMax": 100 }, "reviewNotes": { "zh": ["工具信息顺序稳定，收藏、空结果、加载失败和字段错误都有具体反馈。手机长表单需要滚动才能看到完整操作行，若干入场帧让后续卡片短暂接近透明，小号等宽辅助文字也偏弱。"], "en": ["Tool information followed a stable order, with concrete feedback for saving, empty results, load failure and field errors. The long mobile form required scrolling to expose all actions, several entry frames left later cards almost transparent, and small monospaced supporting text was weak."] }, "demo": "/comparisons/ui-design-skills-tested/demos/oil-ui/run-1/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/oil-ui-run-1-desktop-initial.png", "mobileInitial": "/comparisons/ui-design-skills-tested/shots/oil-ui-run-1-mobile-initial.png" }, { "runId": "oil-ui/run-2", "runIndex": 2, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 18, "productFitAndOriginality": 18, "responsive": 14, "interactionAndStateFeedback": 19, "accessibility": 14, "detailAndMotion": 7 }, "totalScore": 90, "totalMax": 100 }, "reviewNotes": { "zh": ["连续索引线、保存插片和多通道状态反馈契合个人工具目录，手机弹窗操作完整可见。420ms 入场效果仍让搜索与建议刷新截图出现发白中间帧，小号标签和手机页头纵向开销保留了扣分。"], "en": ["Continuous index rules, saved tabs and multi-channel state feedback suited a personal tool directory, and mobile dialog actions remained visible. The 420ms entry effect still produced washed-out search and suggestion captures, while small labels and the tall mobile header retained deductions."] }, "demo": "/comparisons/ui-design-skills-tested/demos/oil-ui/run-2/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/oil-ui-run-2-desktop-initial.png", "mobileInitial": null }, { "runId": "oil-ui/run-3", "runIndex": 3, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 18, "responsive": 13, "interactionAndStateFeedback": 16, "accessibility": 12, "detailAndMotion": 7 }, "totalScore": 83, "totalMax": 100 }, "reviewNotes": { "zh": ["目录层级、空结果恢复和表单错误说明仍然清楚，但 9–10px 元信息偏小，局部标签与焦点色抽算也低于相应参照。手机错误弹窗的操作行落在首屏之外，需要内部滚动。"], "en": ["Catalog hierarchy, empty-result recovery and form-error guidance remained clear, but 9–10px metadata was small and sampled label and focus colors fell below their respective references. The mobile error dialog’s action row also required internal scrolling."] }, "issues": [ { "id": "repeated-card-opacity-replay", "summary": { "zh": "每次 renderTools() 重建卡片都会重播从 opacity: 0 开始的 180ms card-in 动画。", "en": "Every renderTools() rebuild replayed a 180ms card-in animation from opacity: 0." }, "evidence": { "zh": "搜索画面显示 1 tool 却没有可见结果卡；手机搜索、保存后刷新和建议刷新画面也出现近乎透明的卡片。", "en": "A search capture displayed 1 tool with no visible result card; mobile search, saved-refresh and suggestion-refresh captures also showed nearly transparent cards." }, "scope": { "zh": "这些截图证明反复透明重播削弱反馈，但不能证明结果永久丢失。独立功能验收为 6/6 通过，本 run 视觉总分仍为 83。", "en": "The captures establish repeated visibility loss during feedback, not permanent data loss. Independent functional acceptance passed 6/6; this run’s visual total remained 83." } } ], "demo": "/comparisons/ui-design-skills-tested/demos/oil-ui/run-3/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/oil-ui-run-3-desktop-initial.png", "mobileInitial": null } ] }, { "id": "frontend-design", "name": "Anthropic frontend-design", "version": "commit-dbd4588f9e1033efb41dad4bef2f7947c8993d44", "officialSource": { "name": "Anthropic frontend-design", "version": "commit-dbd4588f9e1033efb41dad4bef2f7947c8993d44", "repository": "https://github.com/anthropics/skills", "tag": null, "commit": "dbd4588f9e1033efb41dad4bef2f7947c8993d44", "license": "Apache-2.0" }, "visualAverage": { "scoreSum": 264, "runCount": 3, "average": 88, "decimal": "88.000000", "display": "88.0", "fraction": "264/3", "dimensionScoreSums": { "visualHierarchyAndReadability": 52, "productFitAndOriginality": 51, "responsive": 41, "interactionAndStateFeedback": 54, "accessibility": 41, "detailAndMotion": 25 }, "dimensionAverages": { "visualHierarchyAndReadability": 17.333333, "productFitAndOriginality": 17, "responsive": 13.666667, "interactionAndStateFeedback": 18, "accessibility": 13.666667, "detailAndMotion": 8.333333 } }, "runs": [ { "runId": "frontend-design/run-1", "runIndex": 1, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 17, "responsive": 14, "interactionAndStateFeedback": 18, "accessibility": 13, "detailAndMotion": 8 }, "totalScore": 87, "totalMax": 100 }, "reviewNotes": { "zh": ["冷灰底、标签纸、手绘层架线、书签与工具符号形成统一的工作抽屉方向，保存和异常状态反馈完整。重复顶条与左边线、部分小字和局部偏低对比度保留了扣分。"], "en": ["Cool gray surfaces, label paper, hand-drawn shelf lines, bookmarks and tool symbols formed a coherent work-drawer direction with thorough saved and error states. Repeated top and left rules, small text and sampled low-contrast secondary text retained deductions."] }, "demo": "/comparisons/ui-design-skills-tested/demos/frontend-design/run-1/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/frontend-design-run-1-desktop-initial.png", "mobileInitial": "/comparisons/ui-design-skills-tested/shots/frontend-design-run-1-mobile-initial.png" }, { "runId": "frontend-design/run-2", "runIndex": 2, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 17, "responsive": 13, "interactionAndStateFeedback": 18, "accessibility": 14, "detailAndMotion": 8 }, "totalScore": 87, "totalMax": 100 }, "reviewNotes": { "zh": ["目录层级与保存状态清楚，但 6px 卡片顶条、粗底线和多处左边线叠加后偏繁重。手机错误弹窗需要滚动才能看到取消与保存操作，加载失败的严重度也不够直观。"], "en": ["Catalog hierarchy and saved feedback were clear, but a 6px card top bar, heavy baselines and multiple left rules became visually heavy. The mobile error dialog required scrolling to expose cancel and save, and load-failure severity was less immediate."] }, "demo": "/comparisons/ui-design-skills-tested/demos/frontend-design/run-2/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/frontend-design-run-2-desktop-initial.png", "mobileInitial": null }, { "runId": "frontend-design/run-3", "runIndex": 3, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 18, "productFitAndOriginality": 17, "responsive": 14, "interactionAndStateFeedback": 18, "accessibility": 14, "detailAndMotion": 9 }, "totalScore": 90, "totalMax": 100 }, "reviewNotes": { "zh": ["分类索引片、书签和稳定网格适合工具架主题，状态反馈与基础语义完整。重复的蓝色左边线、12–13px 辅助文字以及手机长表单操作落在首屏之外，仍限制了体验。"], "en": ["Category index tabs, bookmarks and a stable grid suited the tool-shelf theme, with thorough state feedback and baseline semantics. Repeated blue left rules, 12–13px supporting text and mobile long-form actions below the initial viewport still limited the experience."] }, "demo": "/comparisons/ui-design-skills-tested/demos/frontend-design/run-3/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/frontend-design-run-3-desktop-initial.png", "mobileInitial": null } ] }, { "id": "ui-ux-pro-max", "name": "UI UX Pro Max", "version": "2.15.0", "officialSource": { "name": "UI UX Pro Max", "version": "2.15.0", "repository": "https://github.com/nextlevelbuilder/ui-ux-pro-max-skill", "tag": "v2.15.0", "commit": "a38d04c3d5c298c851dbe5e6ee1965ee3de42cb5", "license": "MIT" }, "visualAverage": { "scoreSum": 260, "runCount": 3, "average": 86.66666666666667, "decimal": "86.666667", "display": "86.7", "fraction": "260/3", "dimensionScoreSums": { "visualHierarchyAndReadability": 52, "productFitAndOriginality": 48, "responsive": 42, "interactionAndStateFeedback": 54, "accessibility": 40, "detailAndMotion": 24 }, "dimensionAverages": { "visualHierarchyAndReadability": 17.333333, "productFitAndOriginality": 16, "responsive": 14, "interactionAndStateFeedback": 18, "accessibility": 13.333333, "detailAndMotion": 8 } }, "runs": [ { "runId": "ui-ux-pro-max/run-1", "runIndex": 1, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 15, "responsive": 14, "interactionAndStateFeedback": 18, "accessibility": 14, "detailAndMotion": 8 }, "totalScore": 86, "totalMax": 100 }, "reviewNotes": { "zh": ["三栏卡片的信息顺序一致，保存、空结果、加载失败、存储警告和 FAQ 焦点都有具体设计。配色与结构的产品契合尚可，但原创性得分相对保守，静态素材也不能证明完整动效体验。"], "en": ["The three-column cards used a consistent information order, with concrete saving, empty-result, load-failure, storage-warning and FAQ-focus states. Product fit was sound while originality was scored conservatively; static evidence could not establish the full motion experience."] }, "demo": "/comparisons/ui-design-skills-tested/demos/ui-ux-pro-max/run-1/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/ui-ux-pro-max-run-1-desktop-initial.png", "mobileInitial": "/comparisons/ui-design-skills-tested/shots/ui-ux-pro-max-run-1-mobile-initial.png" }, { "runId": "ui-ux-pro-max/run-2", "runIndex": 2, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 18, "productFitAndOriginality": 17, "responsive": 14, "interactionAndStateFeedback": 18, "accessibility": 13, "detailAndMotion": 8 }, "totalScore": 88, "totalMax": 100 }, "reviewNotes": { "zh": ["个人工作索引的定位与状态反馈清楚，手机筛选能合理换行。工具卡 4px 顶条、建议项与规格左线重复出现，12px 小字偏多；手机错误弹窗的保存与取消需要滚动到达。"], "en": ["The personal working-index direction and state feedback were clear, and mobile filters wrapped sensibly. A 4px card top bar and additional suggestion and specification rules became repetitive, 12px text was frequent, and mobile error-dialog actions required scrolling."] }, "demo": "/comparisons/ui-design-skills-tested/demos/ui-ux-pro-max/run-2/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/ui-ux-pro-max-run-2-desktop-initial.png", "mobileInitial": null }, { "runId": "ui-ux-pro-max/run-3", "runIndex": 3, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 16, "responsive": 14, "interactionAndStateFeedback": 18, "accessibility": 13, "detailAndMotion": 8 }, "totalScore": 86, "totalMax": 100 }, "reviewNotes": { "zh": ["深青、薄荷白与少量橙色保持稳定，状态反馈完整。手机首屏约到 712px 才出现第一张工具卡，完整页约 4695px；长错误表单的操作按钮需要滚动寻找，辅助文字与次要区块也偏重。"], "en": ["Deep teal, mint white and restrained orange formed a stable system with thorough state feedback. The first mobile tool card began around 712px and the full page was about 4695px tall; long error forms required scrolling to find actions, while small text and secondary regions carried considerable weight."] }, "demo": "/comparisons/ui-design-skills-tested/demos/ui-ux-pro-max/run-3/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/ui-ux-pro-max-run-3-desktop-initial.png", "mobileInitial": null } ] }, { "id": "impeccable", "name": "Impeccable", "version": "4.7.0", "officialSource": { "name": "Impeccable", "version": "4.7.0", "repository": "https://github.com/pbakaus/impeccable", "tag": "skill-v4.7.0", "commit": "aeeb3d8c30b5f95aeeb3e893b0f1a308af8fdb8f", "license": "Apache-2.0" }, "visualAverage": { "scoreSum": 264, "runCount": 3, "average": 88, "decimal": "88.000000", "display": "88.0", "fraction": "264/3", "dimensionScoreSums": { "visualHierarchyAndReadability": 52, "productFitAndOriginality": 51, "responsive": 41, "interactionAndStateFeedback": 55, "accessibility": 41, "detailAndMotion": 24 }, "dimensionAverages": { "visualHierarchyAndReadability": 17.333333, "productFitAndOriginality": 17, "responsive": 13.666667, "interactionAndStateFeedback": 18.333333, "accessibility": 13.666667, "detailAndMotion": 8 } }, "runs": [ { "runId": "impeccable/run-1", "runIndex": 1, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 18, "productFitAndOriginality": 16, "responsive": 14, "interactionAndStateFeedback": 18, "accessibility": 14, "detailAndMotion": 8 }, "totalScore": 88, "totalMax": 100 }, "reviewNotes": { "zh": ["票样打孔、虚线与缝合标记形成统一方向，保存和错误反馈不是只靠颜色。部分同排卡片内部基线错位，12px 元信息偏弱，手机错误弹窗的操作也需要额外滚动。"], "en": ["Perforations, dashed rules and stitch marks formed a coherent ticket-swatch direction, and saved and error feedback did not rely on color alone. Some same-row card baselines were misaligned, 12px metadata was weak, and mobile error-dialog actions required additional scrolling."] }, "demo": "/comparisons/ui-design-skills-tested/demos/impeccable/run-1/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/impeccable-run-1-desktop-initial.png", "mobileInitial": "/comparisons/ui-design-skills-tested/shots/impeccable-run-1-mobile-initial.png" }, { "runId": "impeccable/run-2", "runIndex": 2, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 17, "responsive": 13, "interactionAndStateFeedback": 19, "accessibility": 13, "detailAndMotion": 8 }, "totalScore": 87, "totalMax": 100 }, "reviewNotes": { "zh": ["六张桌面卡片的信息与操作容易扫描，保存、空结果、加载失败、存储降级和 FAQ 状态都较完整。高页头与多层筛选压缩了手机首屏工具操作，整页为 3149px，长表单仍需下滚到操作区。"], "en": ["Six desktop cards were easy to scan, and saved, empty, load-failure, storage-degradation and FAQ states were thorough. A tall header and multiple filter layers reduced mobile first-screen tool actions, the page reached 3149px, and the long form still required scrolling to its actions."] }, "demo": "/comparisons/ui-design-skills-tested/demos/impeccable/run-2/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/impeccable-run-2-desktop-initial.png", "mobileInitial": null }, { "runId": "impeccable/run-3", "runIndex": 3, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 18, "responsive": 14, "interactionAndStateFeedback": 18, "accessibility": 14, "detailAndMotion": 8 }, "totalScore": 89, "totalMax": 100 }, "reviewNotes": { "zh": ["Catalog register 会随搜索、保存和筛选改变线型，识别元素与真实状态相关。11px 标尺数字和部分淡化过滤项影响可读性，手机错误弹窗的保存操作仍落在首屏之外。"], "en": ["The Catalog register changed line styles with search, saving and filtering, tying identity details to real state. An 11px register and faded filter items hurt readability, and the mobile error dialog’s save action remained outside the initial viewport."] }, "demo": "/comparisons/ui-design-skills-tested/demos/impeccable/run-3/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/impeccable-run-3-desktop-initial.png", "mobileInitial": null } ] }, { "id": "no-skill", "name": "No Skill control", "version": null, "officialSource": { "name": "No Skill control", "version": null, "repository": null, "tag": null, "commit": null, "license": null, "note": "No upstream Skill or license was supplied." }, "visualAverage": { "scoreSum": 253, "runCount": 3, "average": 84.33333333333333, "decimal": "84.333333", "display": "84.3", "fraction": "253/3", "dimensionScoreSums": { "visualHierarchyAndReadability": 51, "productFitAndOriginality": 51, "responsive": 40, "interactionAndStateFeedback": 50, "accessibility": 37, "detailAndMotion": 24 }, "dimensionAverages": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 17, "responsive": 13.333333, "interactionAndStateFeedback": 16.666667, "accessibility": 12.333333, "detailAndMotion": 8 } }, "runs": [ { "runId": "no-skill/run-1", "runIndex": 1, "generationStatus": "completed", "functional": { "status": "failed", "scenariosPassed": 5, "scenariosTotal": 6, "scenariosFailed": 1, "screenshots": 16, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0, "failure": { "scenarioId": "interaction-and-persistence", "assertion": "Exact #toast text", "expected": "Suggestion saved.", "actual": "✓\n Suggestion saved.", "interpretation": { "zh": "精确文本断言失败，总状态必须保留 failed（5/6）。这不能扩大为所有保存或持久化均失败，失败后的同场景步骤也不能算作通过。", "en": "The exact-text assertion failed, so the run remains failed at 5/6. This does not establish that all saving or persistence failed, and later steps in the same scenario cannot be counted as accepted." } } }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 17, "responsive": 13, "interactionAndStateFeedback": 16, "accessibility": 12, "detailAndMotion": 8 }, "totalScore": 83, "totalMax": 100 }, "reviewNotes": { "zh": ["编辑部录与收藏、空结果、异常状态保持统一，手机没有明显横向裁切。介绍与筛选占据大部分手机首屏，小字与淡色辅助信息偏多，错误弹窗操作不在初始可视区内。"], "en": ["The editorial catalog remained consistent across saved, empty and error states, with no obvious mobile horizontal clipping. Introduction and filters occupied most of the first mobile screen, small and faint supporting text was frequent, and error-dialog actions were outside the initial visible area."] }, "demo": "/comparisons/ui-design-skills-tested/demos/no-skill/run-1/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/no-skill-run-1-desktop-initial.png", "mobileInitial": "/comparisons/ui-design-skills-tested/shots/no-skill-run-1-mobile-initial.png" }, { "runId": "no-skill/run-2", "runIndex": 2, "generationStatus": "completed", "functional": { "status": "passed", "scenariosPassed": 6, "scenariosTotal": 6, "scenariosFailed": 0, "screenshots": 17, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0 }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 17, "responsive": 14, "interactionAndStateFeedback": 17, "accessibility": 13, "detailAndMotion": 8 }, "totalScore": 86, "totalMax": 100 }, "reviewNotes": { "zh": ["个人工作索引与状态反馈完整，390px 下各区域能顺序重排，功能验收通过。10–12px 元信息、手机首屏较低的工具内容比例，以及长错误表单操作落在首屏之外仍有扣分。"], "en": ["The personal working index and state feedback were complete, regions reflowed in order at 390px, and functional acceptance passed. Ten-to-twelve-pixel metadata, limited tool content in the first mobile viewport and long-form actions below the initial view still drew deductions."] }, "demo": "/comparisons/ui-design-skills-tested/demos/no-skill/run-2/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/no-skill-run-2-desktop-initial.png", "mobileInitial": null }, { "runId": "no-skill/run-3", "runIndex": 3, "generationStatus": "completed", "functional": { "status": "failed", "scenariosPassed": 5, "scenariosTotal": 6, "scenariosFailed": 1, "screenshots": 16, "consoleErrors": 0, "httpErrors": 0, "externalRequests": 0, "pageErrors": 0, "failure": { "scenarioId": "interaction-and-persistence", "assertion": "Exact #toast text", "expected": "Suggestion saved.", "actual": "✓\n Suggestion saved.", "decorativeCheckMarkAriaHidden": true, "interpretation": { "zh": "装饰勾号标为 aria-hidden，但精确文本断言仍失败，总状态必须保留 failed（5/6）。不能扩大为所有保存或持久化均失败，失败后的同场景步骤也不能算作通过。", "en": "The decorative check mark was aria-hidden, but the exact-text assertion still failed, so the run remains failed at 5/6. This does not establish total save or persistence failure, and later steps in the same scenario cannot be counted as accepted." } } }, "visual": { "scores": { "visualHierarchyAndReadability": 17, "productFitAndOriginality": 17, "responsive": 13, "interactionAndStateFeedback": 17, "accessibility": 12, "detailAndMotion": 8 }, "totalScore": 84, "totalMax": 100 }, "reviewNotes": { "zh": ["带批注的卡片目录方向与产品任务一致，焦点和减少动态效果有实现证据。多个标签仅 8–12px，工具序号与占位符局部对比不足，手机错误弹窗底部操作只露出上沿。"], "en": ["The annotated card-catalog direction fit the product task, with evidence for visible focus and reduced motion. Several labels were only 8–12px, sampled tool-number and placeholder contrast was weak, and only the upper edge of the mobile error dialog’s bottom actions was initially visible."] }, "demo": "/comparisons/ui-design-skills-tested/demos/no-skill/run-3/index.html", "desktopInitial": "/comparisons/ui-design-skills-tested/shots/no-skill-run-3-desktop-initial.png", "mobileInitial": null } ] } ] }