spec-to-ui 0.1.0 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +2 -0
- package/README.ko.md +129 -0
- package/README.md +96 -29
- package/RELEASE.md +26 -0
- package/THIRD-PARTY.md +14 -0
- package/bin/cli.mjs +70 -91
- package/bundle-manifest.json +140 -0
- package/package.json +40 -8
- package/plugin.json +16 -0
- package/skills/design-taste-frontend/LICENSE +21 -0
- package/skills/design-taste-frontend/README.md +81 -0
- package/skills/design-taste-frontend/SKILL.md +546 -0
- package/skills/design-taste-frontend/assets/app.css +216 -0
- package/skills/design-taste-frontend/assets/base.css +105 -0
- package/skills/design-taste-frontend/assets/base.js +37 -0
- package/skills/design-taste-frontend/assets/charts.js +619 -0
- package/skills/design-taste-frontend/assets/scenes/stage.css +28 -0
- package/skills/design-taste-frontend/assets/scenes/stage.js +134 -0
- package/skills/design-taste-frontend/evals/evals.json +76 -0
- package/skills/design-taste-frontend/library/app.json +1327 -0
- package/skills/design-taste-frontend/library/directions.json +1078 -0
- package/skills/design-taste-frontend/library/heroes.json +1086 -0
- package/skills/design-taste-frontend/library/motions.json +92 -0
- package/skills/design-taste-frontend/library/palettes.json +1485 -0
- package/skills/design-taste-frontend/library/photos.json +7240 -0
- package/skills/design-taste-frontend/library/sections.json +4429 -0
- package/skills/design-taste-frontend/library/sites.json +8350 -0
- package/skills/design-taste-frontend/library/type.json +2024 -0
- package/skills/design-taste-frontend/references/app-screens.md +1199 -0
- package/skills/design-taste-frontend/references/colour.md +141 -0
- package/skills/design-taste-frontend/references/copy.md +177 -0
- package/skills/design-taste-frontend/references/critique.md +182 -0
- package/skills/design-taste-frontend/references/imagery.md +791 -0
- package/skills/design-taste-frontend/references/layout.md +292 -0
- package/skills/design-taste-frontend/references/motion.md +980 -0
- package/skills/design-taste-frontend/references/research.md +356 -0
- package/skills/design-taste-frontend/references/scenes.md +174 -0
- package/skills/design-taste-frontend/references/tells.md +115 -0
- package/skills/design-taste-frontend/references/type.md +170 -0
- package/skills/design-taste-frontend/scripts/assets.mjs +865 -0
- package/skills/design-taste-frontend/scripts/draw.mjs +584 -0
- package/skills/design-taste-frontend/scripts/inspect.mjs +308 -0
- package/skills/design-taste-frontend/scripts/lib/app-draw.mjs +203 -0
- package/skills/design-taste-frontend/scripts/lib/cdp.mjs +248 -0
- package/skills/design-taste-frontend/scripts/lib/inspection-files.mjs +9 -0
- package/skills/design-taste-frontend/scripts/lib/probe.mjs +929 -0
- package/skills/design-taste-frontend/scripts/lib/rules.mjs +243 -0
- package/skills/design-taste-frontend/scripts/lint.mjs +119 -0
- package/skills/design-taste-frontend/scripts/scenes.mjs +124 -0
- package/skills/spec-to-ui/SKILL.md +61 -0
- package/{skill → skills/spec-to-ui}/references/composition-and-validation.md +6 -0
- package/{skill → skills/spec-to-ui}/references/drafts-and-feedback.md +10 -0
- package/skills/spec-to-ui/references/requirements-supplement.md +21 -0
- package/{skill → skills/spec-to-ui}/references/review-and-handoff.md +9 -0
- package/skills/spec-to-ui/references/skill-composition.md +21 -0
- package/{skill → skills/spec-to-ui}/references/structure-and-decisions.md +4 -0
- package/skills/specframe/NOTICE.md +7 -0
- package/skills/specframe/SKILL.md +58 -0
- package/skills/specframe/agents/openai.yaml +3 -0
- package/skills/specframe/references/operating-contract.md +137 -0
- package/skills/specframe/references/visual.md +3 -0
- package/skills/specframe/references/web.md +15 -0
- package/skills/specframe/scripts/state.py +182 -0
- package/skills/ui-ux-pro-max/LICENSE +21 -0
- package/skills/ui-ux-pro-max/SKILL.md +218 -0
- package/skills/ui-ux-pro-max/data/app-interface.csv +33 -0
- package/skills/ui-ux-pro-max/data/catalog-summary.json +78 -0
- package/skills/ui-ux-pro-max/data/charts.csv +26 -0
- package/skills/ui-ux-pro-max/data/colors.csv +193 -0
- package/skills/ui-ux-pro-max/data/data-provenance.json +1348 -0
- package/skills/ui-ux-pro-max/data/google-font-licenses.json +20185 -0
- package/skills/ui-ux-pro-max/data/google-fonts.csv +1935 -0
- package/skills/ui-ux-pro-max/data/icons.csv +106 -0
- package/skills/ui-ux-pro-max/data/landing.csv +35 -0
- package/skills/ui-ux-pro-max/data/motion.csv +18 -0
- package/skills/ui-ux-pro-max/data/phosphor-icons-upstream.json +32582 -0
- package/skills/ui-ux-pro-max/data/products.csv +193 -0
- package/skills/ui-ux-pro-max/data/react-performance.csv +45 -0
- package/skills/ui-ux-pro-max/data/stacks/angular.csv +51 -0
- package/skills/ui-ux-pro-max/data/stacks/astro.csv +54 -0
- package/skills/ui-ux-pro-max/data/stacks/avalonia.csv +57 -0
- package/skills/ui-ux-pro-max/data/stacks/flutter.csv +53 -0
- package/skills/ui-ux-pro-max/data/stacks/html-tailwind.csv +60 -0
- package/skills/ui-ux-pro-max/data/stacks/javafx.csv +76 -0
- package/skills/ui-ux-pro-max/data/stacks/jetpack-compose.csv +53 -0
- package/skills/ui-ux-pro-max/data/stacks/laravel.csv +51 -0
- package/skills/ui-ux-pro-max/data/stacks/nextjs.csv +62 -0
- package/skills/ui-ux-pro-max/data/stacks/nuxt-ui.csv +84 -0
- package/skills/ui-ux-pro-max/data/stacks/nuxtjs.csv +68 -0
- package/skills/ui-ux-pro-max/data/stacks/react-native.csv +52 -0
- package/skills/ui-ux-pro-max/data/stacks/react.csv +67 -0
- package/skills/ui-ux-pro-max/data/stacks/shadcn.csv +69 -0
- package/skills/ui-ux-pro-max/data/stacks/svelte.csv +56 -0
- package/skills/ui-ux-pro-max/data/stacks/swiftui.csv +51 -0
- package/skills/ui-ux-pro-max/data/stacks/threejs.csv +54 -0
- package/skills/ui-ux-pro-max/data/stacks/uno.csv +60 -0
- package/skills/ui-ux-pro-max/data/stacks/uwp.csv +56 -0
- package/skills/ui-ux-pro-max/data/stacks/vue.csv +50 -0
- package/skills/ui-ux-pro-max/data/stacks/winui.csv +60 -0
- package/skills/ui-ux-pro-max/data/stacks/wpf.csv +57 -0
- package/skills/ui-ux-pro-max/data/styles.csv +89 -0
- package/skills/ui-ux-pro-max/data/typography.csv +75 -0
- package/skills/ui-ux-pro-max/data/ui-reasoning.csv +193 -0
- package/skills/ui-ux-pro-max/data/ux-guidelines.csv +120 -0
- package/skills/ui-ux-pro-max/references/pro-rules.md +117 -0
- package/skills/ui-ux-pro-max/references/quick-reference.md +256 -0
- package/skills/ui-ux-pro-max/scripts/core.py +993 -0
- package/skills/ui-ux-pro-max/scripts/design_system.py +1668 -0
- package/skills/ui-ux-pro-max/scripts/reasoning_contract.py +123 -0
- package/skills/ui-ux-pro-max/scripts/search.py +184 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/google-api.json +36 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/google-catalog.json +33 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/google-existing.csv +3 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/google-metadata.json +17 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/google-overrides.json +7 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/icons-curated.csv +4 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/phosphor-core.json +23 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/phosphor-package.json +13 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/phosphor-react-exports.json +4 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/catalogs/phosphor-react-package.json +5 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/relevance-baseline.json +3366 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/relevance-cases.json +111 -0
- package/skills/ui-ux-pro-max/scripts/tests/fixtures/relevance-thresholds.json +100 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_catalog_refresh.py +354 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_catalog_summary_line_endings.py +78 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_core.py +343 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_core_data_quality.py +198 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_data_contracts.py +421 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_design_system_mode.py +233 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_design_system_stack.py +61 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_native_desktop_stack_freshness.py +179 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_relevance_evaluator.py +182 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_skill_script_paths.py +82 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_style_taxonomy.py +175 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_text_layout_resilience.py +120 -0
- package/skills/ui-ux-pro-max/scripts/tests/test_web_stack_freshness.py +191 -0
- package/skills/ui-ux-pro-max/scripts/validate_data.py +1095 -0
- package/sources.json +58 -0
- package/skill/SKILL.md +0 -68
- package/skill-manifest.json +0 -10
- /package/{skill → skills/spec-to-ui}/LICENSE +0 -0
- /package/{skill → skills/spec-to-ui}/agents/openai.yaml +0 -0
- /package/{skill → skills/spec-to-ui}/references/reference-selection.md +0 -0
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
{
|
|
2
|
+
"schemaVersion": 1,
|
|
3
|
+
"fixtureRevision": "97eb2a2",
|
|
4
|
+
"gradeSemantics": {
|
|
5
|
+
"2": "Directly answers the query and is an expected best result.",
|
|
6
|
+
"1": "Useful and acceptable, but less specific than a grade-2 result.",
|
|
7
|
+
"0": "Not relevant. Every returned row not listed in judgments is implicitly grade 0."
|
|
8
|
+
},
|
|
9
|
+
"globalNegativeApplicability": {
|
|
10
|
+
"tag": "hard-negative",
|
|
11
|
+
"domains": ["style", "color", "chart", "landing", "product", "ux", "typography", "icons", "gsap", "react", "web", "google-fonts"],
|
|
12
|
+
"stacks": ["react", "nextjs", "vue", "svelte", "astro", "swiftui", "react-native", "flutter", "nuxtjs", "nuxt-ui", "html-tailwind", "shadcn", "jetpack-compose", "threejs", "angular", "laravel", "javafx", "wpf", "winui", "avalonia", "uno", "uwp"],
|
|
13
|
+
"interpretation": "Run every hard-negative case against all registered domains and stacks. Any returned row is an implicit grade-0 false positive; aggregate reporting may cap this cross-product separately."
|
|
14
|
+
},
|
|
15
|
+
"cases": [
|
|
16
|
+
{"id":"domain-style-glassmorphism","split":"calibration","mode":"domain","query":"frosted glass transparent blurred layered UI","domain":"style","judgments":[{"identity":{"Style Category":"Glassmorphism"},"grade":2}],"tags":["exact-intent","domain-positive"],"notes":"Canonical visual treatment, expressed through its descriptive attributes."},
|
|
17
|
+
{"id":"domain-style-accessible-paraphrase","split":"held_out","mode":"domain","query":"inclusive high contrast interface with keyboard nav and screen readers","domain":"style","judgments":[{"identity":{"Style Category":"Accessible & Ethical"},"grade":2},{"identity":{"Style Category":"Inclusive Design"},"grade":1}],"tags":["paraphrase","domain-positive"],"notes":"A style request, not an individual UX rule."},
|
|
18
|
+
{"id":"domain-color-spa","split":"calibration","mode":"domain","query":"beauty spa wellness soft pink lavender palette","domain":"color","judgments":[{"identity":{"Product Type":"Beauty/Spa/Wellness Service"},"grade":2}],"tags":["product-palette","domain-positive"],"notes":"Uses the public Product Type as the stable palette identity."},
|
|
19
|
+
{"id":"domain-color-cyber-typo","split":"held_out","mode":"domain","query":"cybersecurty threat dashboard matrix green dark pallete","domain":"color","judgments":[{"identity":{"Product Type":"Cybersecurity Platform"},"grade":2}],"tags":["typo","domain-positive"],"notes":"Deliberately misspells cybersecurity and palette."},
|
|
20
|
+
{"id":"domain-chart-time-series","split":"calibration","mode":"domain","query":"trend over time growth timeline line chart","domain":"chart","judgments":[{"identity":{"Data Type":"Trend Over Time"},"grade":2},{"identity":{"Data Type":"Time-Series Forecast"},"grade":1}],"tags":["exact-intent","domain-positive"],"notes":"Forecasting is acceptable only as a secondary interpretation."},
|
|
21
|
+
{"id":"domain-chart-correlation-paraphrase","split":"held_out","mode":"domain","query":"show whether two measures move together using dots and bubbles","domain":"chart","judgments":[{"identity":{"Data Type":"Correlation / Distribution"},"grade":2}],"tags":["paraphrase","domain-positive"],"notes":"Avoids the canonical words scatter and correlation."},
|
|
22
|
+
{"id":"domain-landing-pricing","split":"calibration","mode":"domain","query":"pricing plans tiers comparison landing CTA","domain":"landing","judgments":[{"identity":{"Pattern Name":"Pricing Page + CTA"},"grade":2},{"identity":{"Pattern Name":"Pricing-Focused Landing"},"grade":2},{"identity":{"Pattern Name":"Comparison Table + CTA"},"grade":1}],"tags":["multi-acceptable","domain-positive"],"notes":"Both dedicated pricing patterns are equally valid."},
|
|
23
|
+
{"id":"domain-landing-enterprise-typo","split":"held_out","mode":"domain","query":"enterprise credibilty trust authority conversion page","domain":"landing","judgments":[{"identity":{"Pattern Name":"Trust & Authority + Conversion"},"grade":2},{"identity":{"Pattern Name":"Enterprise Gateway"},"grade":1}],"tags":["typo","domain-positive"],"notes":"Misspells credibility while preserving the enterprise intent."},
|
|
24
|
+
{"id":"domain-product-spa","split":"calibration","mode":"domain","query":"salon massage skincare booking and wellness service","domain":"product","judgments":[{"identity":{"Product Type":"Beauty/Spa/Wellness Service"},"grade":2},{"identity":{"Product Type":"Booking & Appointment App"},"grade":1}],"tags":["multi-acceptable","domain-positive"],"notes":"The industry is primary; booking is a supporting capability."},
|
|
25
|
+
{"id":"domain-product-security-paraphrase","split":"held_out","mode":"domain","query":"platform for monitoring digital threats and protecting systems","domain":"product","judgments":[{"identity":{"Product Type":"Cybersecurity Platform"},"grade":2}],"tags":["paraphrase","domain-positive"],"notes":"Avoids the exact keyword cyber."},
|
|
26
|
+
{"id":"domain-ux-keyboard-focus","split":"calibration","mode":"domain","query":"visible focus and complete keyboard navigation for web users","domain":"ux","judgments":[{"identity":{"Category":"Accessibility","Issue":"Keyboard Navigation","Platform":"Web"},"grade":2},{"identity":{"Category":"Interaction","Issue":"Focus States","Platform":"All"},"grade":2}],"tags":["multi-acceptable","domain-positive"],"notes":"Both navigation coverage and visible focus are explicitly requested."},
|
|
27
|
+
{"id":"domain-ux-motion-paraphrase","split":"held_out","mode":"domain","query":"stop animations making people sick and honor their motion preference","domain":"ux","judgments":[{"identity":{"Category":"Animation","Issue":"Reduced Motion","Platform":"All"},"grade":2},{"identity":{"Category":"Animation","Issue":"Excessive Motion","Platform":"All"},"grade":1}],"tags":["paraphrase","accessibility","domain-positive"],"notes":"Preference support is stronger than generic excessive-motion advice."},
|
|
28
|
+
{"id":"domain-typography-luxury","split":"calibration","mode":"domain","query":"elegant luxury serif heading with clean readable body font","domain":"typography","judgments":[{"identity":{"Font Pairing Name":"Classic Elegant"},"grade":2},{"identity":{"Font Pairing Name":"Luxury Serif"},"grade":2},{"identity":{"Font Pairing Name":"Luxury Minimalist"},"grade":1}],"tags":["multi-acceptable","domain-positive"],"notes":"Several curated pairs directly satisfy this intentionally broad mood."},
|
|
29
|
+
{"id":"domain-typography-accessible-typo","split":"held_out","mode":"domain","query":"dyslexia frendly hyperlegible inclusive type pairing","domain":"typography","judgments":[{"identity":{"Font Pairing Name":"Accessibility First"},"grade":2},{"identity":{"Font Pairing Name":"Academic/Research"},"grade":1}],"tags":["typo","accessibility","domain-positive"],"notes":"Misspells friendly; the all-Atkinson pairing is the direct answer."},
|
|
30
|
+
{"id":"domain-icons-search","split":"calibration","mode":"domain","query":"find lookup search icon for a query field","domain":"icons","judgments":[{"identity":{"Category":"Action","Icon Name":"magnifying-glass","Library":"Phosphor"},"grade":2},{"identity":{"Category":"Action","Icon Name":"funnel","Library":"Phosphor"},"grade":1}],"tags":["exact-intent","domain-positive"],"notes":"Filter is useful but not equivalent to search."},
|
|
31
|
+
{"id":"domain-icons-warning-typo","split":"held_out","mode":"domain","query":"warnng caution danger status symbol","domain":"icons","judgments":[{"identity":{"Category":"Status","Icon Name":"warning","Library":"Phosphor"},"grade":2},{"identity":{"Category":"Status","Icon Name":"warning-circle","Library":"Phosphor"},"grade":1}],"tags":["typo","domain-positive"],"notes":"Misspells warning and allows the circled variant as secondary."},
|
|
32
|
+
{"id":"domain-gsap-scroll-reveal","split":"calibration","mode":"domain","query":"GSAP reveal elements when they enter the viewport on scroll","domain":"gsap","judgments":[{"identity":{"Category":"Scroll Reveal","Intensity Tier":"Subtle","Trigger":"scroll (viewport enter)"},"grade":2},{"identity":{"Category":"Scroll Reveal","Intensity Tier":"Standard","Trigger":"scroll (viewport enter)"},"grade":2},{"identity":{"Category":"Scroll Reveal","Intensity Tier":"Complex","Trigger":"scroll (continuous scrub)"},"grade":1}],"tags":["multi-acceptable","domain-positive"],"notes":"Viewport-entry variants are direct; continuous scrub is related but stronger."},
|
|
33
|
+
{"id":"domain-gsap-skeleton-typo","split":"held_out","mode":"domain","query":"skeletn shimmer loader while async content waits","domain":"gsap","judgments":[{"identity":{"Category":"Loading / Skeleton","Intensity Tier":"Subtle","Trigger":"on mount / async wait"},"grade":2},{"identity":{"Category":"Loading / Skeleton","Intensity Tier":"Standard","Trigger":"on mount / async wait"},"grade":1}],"tags":["typo","domain-positive"],"notes":"Misspells skeleton; subtle shimmer is the most exact row."},
|
|
34
|
+
{"id":"domain-react-parallel-promises","split":"calibration","mode":"domain","query":"React Promise.all parallel concurrent requests instead of waterfall","domain":"react","judgments":[{"identity":{"Category":"Async Waterfall","Issue":"Promise.all Parallel","Platform":"React/Next.js"},"grade":2},{"identity":{"Category":"Async Waterfall","Issue":"Dependency Parallelization","Platform":"React/Next.js"},"grade":1}],"tags":["exact-intent","domain-positive"],"notes":"The first row exactly names Promise.all."},
|
|
35
|
+
{"id":"domain-react-dynamic-import-paraphrase","split":"held_out","mode":"domain","query":"load a heavy JavaScript chunk only when the component is needed","domain":"react","judgments":[{"identity":{"Category":"Bundle Size","Issue":"Dynamic Imports","Platform":"React/Next.js"},"grade":2},{"identity":{"Category":"Bundle Size","Issue":"Conditional Loading","Platform":"React/Next.js"},"grade":1}],"tags":["paraphrase","domain-positive"],"notes":"Avoids the canonical term lazy in the main clause."},
|
|
36
|
+
{"id":"domain-web-icon-label","split":"calibration","mode":"domain","query":"accessible name for an icon-only mobile button","domain":"web","judgments":[{"identity":{"Category":"Accessibility","Issue":"Icon Button Labels","Platform":"iOS/Android/React Native"},"grade":2}],"tags":["accessibility","domain-positive"],"notes":"App-interface guidance uses the public web domain key."},
|
|
37
|
+
{"id":"domain-web-virtual-list-paraphrase","split":"held_out","mode":"domain","query":"keep a very long mobile list smooth without rendering every row","domain":"web","judgments":[{"identity":{"Category":"Performance","Issue":"Virtualize Long Lists","Platform":"iOS/Android/React Native"},"grade":2}],"tags":["paraphrase","domain-positive"],"notes":"Describes virtualization without naming FlatList."},
|
|
38
|
+
{"id":"domain-google-fonts-inter","split":"calibration","mode":"domain","query":"Inter variable sans serif Google font family","domain":"google-fonts","judgments":[{"identity":{"Family":"Inter"},"grade":2},{"identity":{"Family":"Inter Tight"},"grade":1}],"tags":["exact-entity","domain-positive"],"notes":"Exact family is preferred over its related Tight family."},
|
|
39
|
+
{"id":"domain-google-fonts-atkinson-paraphrase","split":"held_out","mode":"domain","query":"hyperlegible accessible sans typeface for easier reading","domain":"google-fonts","judgments":[{"identity":{"Family":"Atkinson Hyperlegible"},"grade":2},{"identity":{"Family":"Atkinson Hyperlegible Next"},"grade":1}],"tags":["paraphrase","accessibility","domain-positive"],"notes":"The established family is locked; its newer related family is acceptable."},
|
|
40
|
+
|
|
41
|
+
{"id":"stack-angular-standalone","split":"calibration","mode":"stack","query":"standalone Angular components for a new project","stack":"angular","judgments":[{"identity":{"Category":"Components","Guideline":"Use standalone components"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Modern Angular component architecture."},
|
|
42
|
+
{"id":"stack-angular-signals-paraphrase","split":"held_out","mode":"stack","query":"reactive local state with Angular signal primitives","stack":"angular","judgments":[{"identity":{"Category":"Components","Guideline":"Use signals for state"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Held out wording for signals."},
|
|
43
|
+
{"id":"stack-astro-islands","split":"calibration","mode":"stack","query":"Astro islands architecture interactive components","stack":"astro","judgments":[{"identity":{"Category":"Architecture","Guideline":"Use Islands Architecture"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical Astro architecture."},
|
|
44
|
+
{"id":"stack-astro-zero-js-paraphrase","split":"held_out","mode":"stack","query":"ship no browser JavaScript unless interaction requires it","stack":"astro","judgments":[{"identity":{"Category":"Architecture","Guideline":"Default to zero JS"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Describes the zero-JS default."},
|
|
45
|
+
{"id":"stack-avalonia-namespace","split":"calibration","mode":"stack","query":"Avalonia XAML namespace declaration","stack":"avalonia","judgments":[{"identity":{"Category":"XAML","Guideline":"Use Avalonia XAML namespace"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Exact Avalonia XAML setup concern."},
|
|
46
|
+
{"id":"stack-avalonia-compiled-binding","split":"held_out","mode":"stack","query":"type checked compiled binding with x DataType","stack":"avalonia","judgments":[{"identity":{"Category":"XAML","Guideline":"Use compiled bindings with x:DataType"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Punctuation-free paraphrase of x:DataType."},
|
|
47
|
+
{"id":"stack-flutter-stateless","split":"calibration","mode":"stack","query":"prefer StatelessWidget when Flutter UI has no mutable state","stack":"flutter","judgments":[{"identity":{"Category":"Widgets","Guideline":"Use StatelessWidget when possible"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Direct widget choice."},
|
|
48
|
+
{"id":"stack-flutter-const-paraphrase","split":"held_out","mode":"stack","query":"reduce Flutter rebuild cost with immutable compile-time widgets","stack":"flutter","judgments":[{"identity":{"Category":"Widgets","Guideline":"Use const constructors"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Describes const constructor value without copying the title."},
|
|
49
|
+
{"id":"stack-html-tailwind-z-index","split":"calibration","mode":"stack","query":"Tailwind z-index utility scale for layered UI","stack":"html-tailwind","judgments":[{"identity":{"Category":"Z-Index","Guideline":"Use Tailwind z-* scale"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Specific utility-scale guidance."},
|
|
50
|
+
{"id":"stack-html-tailwind-hover","split":"held_out","mode":"stack","query":"smooth transition when a Tailwind element is hovered","stack":"html-tailwind","judgments":[{"identity":{"Category":"Animation","Guideline":"Hover transitions"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Natural language hover-motion request."},
|
|
51
|
+
{"id":"stack-javafx-application","split":"calibration","mode":"stack","query":"launch JavaFX UI from an Application subclass","stack":"javafx","judgments":[{"identity":{"Category":"Application","Guideline":"Start UI from Application subclass"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical JavaFX application lifecycle."},
|
|
52
|
+
{"id":"stack-javafx-threading-paraphrase","split":"held_out","mode":"stack","query":"prevent slow background work from freezing the FX application thread","stack":"javafx","judgments":[{"identity":{"Category":"Threading","Guideline":"Keep work off the FX Application Thread"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Describes the failure mode rather than repeating the title."},
|
|
53
|
+
{"id":"stack-compose-pure-ui","split":"calibration","mode":"stack","query":"pure Jetpack Compose UI composables","stack":"jetpack-compose","judgments":[{"identity":{"Category":"Composable","Guideline":"Pure UI composables"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Direct Compose architecture query."},
|
|
54
|
+
{"id":"stack-compose-single-source","split":"held_out","mode":"stack","query":"one authoritative owner for Compose screen state","stack":"jetpack-compose","judgments":[{"identity":{"Category":"State","Guideline":"Single source of truth"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Paraphrases state ownership."},
|
|
55
|
+
{"id":"stack-laravel-blade-component","split":"calibration","mode":"stack","query":"reusable Laravel Blade UI components","stack":"laravel","judgments":[{"identity":{"Category":"Blade Templates","Guideline":"Use Blade components for reusable UI"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Direct Blade reuse guidance."},
|
|
56
|
+
{"id":"stack-laravel-props","split":"held_out","mode":"stack","query":"declare typed inputs for a Blade component using props","stack":"laravel","judgments":[{"identity":{"Category":"Blade Templates","Guideline":"Use @props for component type-safety"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Natural wording around @props."},
|
|
57
|
+
{"id":"stack-nextjs-app-router","split":"calibration","mode":"stack","query":"Next.js App Router for a new project","stack":"nextjs","judgments":[{"identity":{"Category":"Routing","Guideline":"Use App Router for new projects"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Current routing architecture."},
|
|
58
|
+
{"id":"stack-nextjs-server-components","split":"held_out","mode":"stack","query":"render on the server by default and opt into client boundaries","stack":"nextjs","judgments":[{"identity":{"Category":"Rendering","Guideline":"Use Server Components by default"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Held-out RSC wording."},
|
|
59
|
+
{"id":"stack-nuxt-ui-module","split":"calibration","mode":"stack","query":"install the Nuxt UI module","stack":"nuxt-ui","judgments":[{"identity":{"Category":"Installation","Guideline":"Add Nuxt UI module"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Basic Nuxt UI setup."},
|
|
60
|
+
{"id":"stack-nuxt-ui-semantic-color","split":"held_out","mode":"stack","query":"style Nuxt UI components through meaning-based color props","stack":"nuxt-ui","judgments":[{"identity":{"Category":"Components","Guideline":"Use semantic color props"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Avoids copying semantic exactly except its concept."},
|
|
61
|
+
{"id":"stack-nuxtjs-file-routing","split":"calibration","mode":"stack","query":"Nuxt file-based page routing","stack":"nuxtjs","judgments":[{"identity":{"Category":"Routing","Guideline":"Use file-based routing"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical Nuxt routing convention."},
|
|
62
|
+
{"id":"stack-nuxtjs-ssr","split":"held_out","mode":"stack","query":"server render Nuxt pages unless a client-only boundary is necessary","stack":"nuxtjs","judgments":[{"identity":{"Category":"Rendering","Guideline":"Use SSR by default"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Describes the SSR default."},
|
|
63
|
+
{"id":"stack-react-native-functional","split":"calibration","mode":"stack","query":"functional React Native components","stack":"react-native","judgments":[{"identity":{"Category":"Components","Guideline":"Use functional components"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Direct component style."},
|
|
64
|
+
{"id":"stack-react-native-stylesheet","split":"held_out","mode":"stack","query":"define reusable native styles outside render instead of inline objects","stack":"react-native","judgments":[{"identity":{"Category":"Styling","Guideline":"Use StyleSheet.create"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Describes StyleSheet.create without naming it."},
|
|
65
|
+
{"id":"stack-react-usestate","split":"calibration","mode":"stack","query":"React useState for component local state","stack":"react","judgments":[{"identity":{"Category":"State","Guideline":"Use useState for local state"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical local state hook."},
|
|
66
|
+
{"id":"stack-react-effect-cleanup","split":"held_out","mode":"stack","query":"remove subscriptions and timers when a React effect unmounts","stack":"react","judgments":[{"identity":{"Category":"Effects","Guideline":"Clean up effects"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Describes cleanup behavior."},
|
|
67
|
+
{"id":"stack-shadcn-cli","split":"calibration","mode":"stack","query":"install shadcn components with the CLI","stack":"shadcn","judgments":[{"identity":{"Category":"Setup","Guideline":"Use CLI for installation"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical setup path."},
|
|
68
|
+
{"id":"stack-shadcn-css-vars","split":"held_out","mode":"stack","query":"theme shadcn semantic colors through custom properties","stack":"shadcn","judgments":[{"identity":{"Category":"Theming","Guideline":"Use CSS variables for colors"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Uses custom properties as a synonym for CSS variables."},
|
|
69
|
+
{"id":"stack-svelte-state","split":"calibration","mode":"stack","query":"Svelte 5 $state rune for reactive state","stack":"svelte","judgments":[{"identity":{"Category":"Reactivity","Guideline":"Use $state in Svelte 5"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Specific Svelte 5 primitive."},
|
|
70
|
+
{"id":"stack-svelte-effect","split":"held_out","mode":"stack","query":"run a Svelte 5 side effect when reactive dependencies change","stack":"svelte","judgments":[{"identity":{"Category":"Reactivity","Guideline":"Use $effect for side effects"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Behavioral wording for $effect."},
|
|
71
|
+
{"id":"stack-swiftui-state","split":"calibration","mode":"stack","query":"SwiftUI @State for view-local value state","stack":"swiftui","judgments":[{"identity":{"Category":"State","Guideline":"Use @State for local state"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical property wrapper choice."},
|
|
72
|
+
{"id":"stack-swiftui-navigation","split":"held_out","mode":"stack","query":"modern value-driven iOS navigation container replacing NavigationView","stack":"swiftui","judgments":[{"identity":{"Category":"Navigation","Guideline":"Use NavigationStack or NavigationSplitView (iOS 16+)"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Describes NavigationStack migration intent."},
|
|
73
|
+
{"id":"stack-threejs-orbitcontrols","split":"calibration","mode":"stack","query":"Three.js OrbitControls must be imported separately","stack":"threejs","judgments":[{"identity":{"Category":"Setup","Guideline":"Import OrbitControls from Three.js Addons"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Common setup failure."},
|
|
74
|
+
{"id":"stack-threejs-pixel-ratio","split":"held_out","mode":"stack","query":"avoid excessive GPU work on retina screens by limiting renderer DPR","stack":"threejs","judgments":[{"identity":{"Category":"Setup","Guideline":"Pixel Ratio Cap at 2"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Uses DPR and performance wording."},
|
|
75
|
+
{"id":"stack-uno-winui-xaml","split":"calibration","mode":"stack","query":"Uno Platform WinUI XAML API surface","stack":"uno","judgments":[{"identity":{"Category":"XAML","Guideline":"Use WinUI XAML API surface"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical cross-platform XAML surface."},
|
|
76
|
+
{"id":"stack-uno-package-paraphrase","split":"held_out","mode":"stack","query":"choose the modern Uno WinUI package instead of the legacy Uno UI package","stack":"uno","judgments":[{"identity":{"Category":"XAML","Guideline":"Use Uno.WinUI not Uno.UI for new projects"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Natural package-selection wording."},
|
|
77
|
+
{"id":"stack-uwp-xbind","split":"calibration","mode":"stack","query":"UWP compiled x:Bind data binding","stack":"uwp","judgments":[{"identity":{"Category":"XAML","Guideline":"Use x:Bind for compiled bindings"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical compiled binding guidance."},
|
|
78
|
+
{"id":"stack-uwp-migration","split":"held_out","mode":"stack","query":"which Windows UI framework should a brand new app choose instead of legacy UWP","stack":"uwp","judgments":[{"identity":{"Category":"Architecture","Guideline":"Prefer WinUI 3 for new projects"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Tests that legacy-stack guidance can recommend the successor."},
|
|
79
|
+
{"id":"stack-vue-composition","split":"calibration","mode":"stack","query":"Vue Composition API for a new project","stack":"vue","judgments":[{"identity":{"Category":"Composition","Guideline":"Use Composition API for new projects"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical Vue architecture."},
|
|
80
|
+
{"id":"stack-vue-pinia","split":"held_out","mode":"stack","query":"central shared Vue application state store","stack":"vue","judgments":[{"identity":{"Category":"State","Guideline":"Use Pinia for global state"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Avoids naming Pinia in the query."},
|
|
81
|
+
{"id":"stack-winui-infobar","split":"calibration","mode":"stack","query":"WinUI InfoBar for status messages","stack":"winui","judgments":[{"identity":{"Category":"Controls","Guideline":"Use InfoBar for status messages"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Specific WinUI control selection."},
|
|
82
|
+
{"id":"stack-winui-dispatcherqueue","split":"held_out","mode":"stack","query":"marshal a WinUI update back onto the UI thread with the modern dispatcher","stack":"winui","judgments":[{"identity":{"Category":"Threading","Guideline":"Use DispatcherQueue not Dispatcher"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Describes DispatcherQueue without copying its name."},
|
|
83
|
+
{"id":"stack-wpf-property-change","split":"calibration","mode":"stack","query":"WPF INotifyPropertyChanged data binding updates","stack":"wpf","judgments":[{"identity":{"Category":"Data Binding","Guideline":"Implement INotifyPropertyChanged"},"grade":2}],"tags":["stack-positive","exact-intent"],"notes":"Canonical MVVM notification contract."},
|
|
84
|
+
{"id":"stack-wpf-virtualization","split":"held_out","mode":"stack","query":"keep a huge WPF list responsive by only creating visible item containers","stack":"wpf","judgments":[{"identity":{"Category":"Performance","Guideline":"Use VirtualizingStackPanel for large lists"},"grade":2}],"tags":["stack-positive","paraphrase"],"notes":"Behavioral description of list virtualization."},
|
|
85
|
+
|
|
86
|
+
{"id":"auto-route-accessibility","split":"calibration","mode":"auto","query":"WCAG keyboard accessibility and visible focus","expectedRoute":"ux","judgments":[{"identity":{"Category":"Accessibility","Issue":"Keyboard Navigation","Platform":"Web"},"grade":2},{"identity":{"Category":"Interaction","Issue":"Focus States","Platform":"All"},"grade":1}],"tags":["auto-router","routing-positive"],"notes":"Specific accessibility intent should outrank generic style terms."},
|
|
87
|
+
{"id":"auto-route-color","split":"calibration","mode":"auto","query":"hex color palette accent foreground destructive tokens","expectedRoute":"color","judgments":[{"identity":{"Product Type":"Design System/Component Library"},"grade":2}],"tags":["auto-router","routing-positive"],"notes":"Color vocabulary should route to palettes."},
|
|
88
|
+
{"id":"auto-route-chart","split":"calibration","mode":"auto","query":"scatter chart for correlation distribution","expectedRoute":"chart","judgments":[{"identity":{"Data Type":"Correlation / Distribution"},"grade":2}],"tags":["auto-router","routing-positive"],"notes":"Explicit chart type and analytic intent."},
|
|
89
|
+
{"id":"auto-route-landing","split":"held_out","mode":"auto","query":"hero testimonials CTA conversion landing page","expectedRoute":"landing","judgments":[{"identity":{"Pattern Name":"Hero + Testimonials + CTA"},"grade":2},{"identity":{"Pattern Name":"Hero + Features + CTA"},"grade":1}],"tags":["auto-router","routing-positive","held-out-route"],"notes":"Multiple landing-specific terms should dominate product routing."},
|
|
90
|
+
{"id":"auto-route-fonts","split":"held_out","mode":"auto","query":"JetBrains Mono Google font family variable styles","expectedRoute":"google-fonts","judgments":[{"identity":{"Family":"JetBrains Mono"},"grade":2}],"tags":["auto-router","routing-positive","held-out-route"],"notes":"Entity lookup in the large Google Fonts catalog."},
|
|
91
|
+
{"id":"auto-route-icons","split":"calibration","mode":"auto","query":"Phosphor warning icon glyph for danger status","expectedRoute":"icons","judgments":[{"identity":{"Category":"Status","Icon Name":"warning","Library":"Phosphor"},"grade":2},{"identity":{"Category":"Status","Icon Name":"warning-circle","Library":"Phosphor"},"grade":1}],"tags":["auto-router","routing-positive"],"notes":"Explicit icon/glyph vocabulary."},
|
|
92
|
+
{"id":"auto-route-gsap","split":"held_out","mode":"auto","query":"GSAP ScrollTrigger stagger reveal animation","expectedRoute":"gsap","judgments":[{"identity":{"Category":"Scroll Reveal","Intensity Tier":"Standard","Trigger":"scroll (viewport enter)"},"grade":2},{"identity":{"Category":"Stagger List","Intensity Tier":"Standard","Trigger":"load or scroll"},"grade":1}],"tags":["auto-router","routing-positive","held-out-route"],"notes":"GSAP vocabulary is unambiguous even with generic animation."},
|
|
93
|
+
{"id":"auto-route-react","split":"calibration","mode":"auto","query":"React Suspense waterfall bundle rerender optimization","expectedRoute":"react","judgments":[{"identity":{"Category":"Async Waterfall","Issue":"Suspense Boundaries","Platform":"React/Next.js"},"grade":2}],"tags":["auto-router","routing-positive"],"notes":"React performance terms should not route to generic UX."},
|
|
94
|
+
|
|
95
|
+
{"id":"negative-gibberish-alpha","split":"calibration","mode":"auto","query":"zzqqxx plmokn qvtrz","judgments":[],"tags":["hard-negative","gibberish","abstention"],"notes":"No catalog row is relevant; suggestions and returned rows are false positives for measurement."},
|
|
96
|
+
{"id":"negative-gibberish-numeric","split":"held_out","mode":"auto","query":"7391 qzxv 0044 nmnq","judgments":[],"tags":["hard-negative","gibberish","abstention"],"notes":"Held-out alphanumeric noise."},
|
|
97
|
+
{"id":"negative-geography-fact","split":"calibration","mode":"auto","query":"capital of Mongolia population census","judgments":[],"tags":["hard-negative","out-of-scope","abstention"],"notes":"A factual geography question, not a design request."},
|
|
98
|
+
{"id":"negative-math-proof","split":"held_out","mode":"auto","query":"prove there are infinitely many prime numbers","judgments":[],"tags":["hard-negative","out-of-scope","abstention"],"notes":"A mathematics request with no relevant catalog guidance."},
|
|
99
|
+
{"id":"negative-cooking","split":"calibration","mode":"auto","query":"sourdough starter feeding schedule at room temperature","judgments":[],"tags":["hard-negative","out-of-scope","abstention"],"notes":"A cooking instruction request; product-category overlap must not count as relevance."},
|
|
100
|
+
{"id":"negative-biology","split":"held_out","mode":"auto","query":"photosynthesis equation for freshwater algae","judgments":[],"tags":["hard-negative","out-of-scope","abstention"],"notes":"A science question with no UI intent."},
|
|
101
|
+
|
|
102
|
+
{"id":"design-system-spa","split":"calibration","mode":"design-system","query":"beauty spa wellness booking landing page","judgments":[{"identity":{"Product Type":"Beauty/Spa/Wellness Service"},"grade":2}],"coherence":{"productCategory":"Beauty/Spa/Wellness Service","styleNames":["Soft UI Evolution","Neumorphism","Glassmorphism"],"patternNames":["Hero-Centric + Social Proof","Hero-Centric Design","Hero + Testimonials + CTA"],"colorMode":"light"},"tags":["design-system","coherence","readme-example"],"notes":"Industry, calming style, social proof pattern, and light palette should agree."},
|
|
103
|
+
{"id":"design-system-cybersecurity-dark","split":"calibration","mode":"design-system","query":"cybersecurity threat monitoring platform dark mode","judgments":[{"identity":{"Product Type":"Cybersecurity Platform"},"grade":2}],"coherence":{"productCategory":"Cybersecurity Platform","styleNames":["Cyberpunk UI","Dark Mode (OLED)","HUD / Sci-Fi FUI"],"patternNames":["Trust & Authority + Real-Time","Trust & Authority + Conversion","Real-Time / Operations Landing","Enterprise Gateway"],"colorMode":"dark"},"tags":["design-system","coherence","dark-mode"],"notes":"Security, real-time operations, technical style, and dark palette form one coherent system."},
|
|
104
|
+
{"id":"design-system-saas","split":"calibration","mode":"design-system","query":"SaaS dashboard for a B2B cloud product","judgments":[{"identity":{"Product Type":"SaaS (General)"},"grade":2},{"identity":{"Product Type":"B2B Service"},"grade":1}],"coherence":{"productCategory":"SaaS (General)","styleNames":["Glassmorphism","Flat Design","Minimalism & Swiss Style","Soft UI Evolution"],"patternNames":["Hero + Features + CTA","Feature-Rich Showcase"],"colorMode":"light"},"tags":["design-system","coherence","readme-example"],"notes":"Locks the README's broad SaaS example to a maintainable B2B system."},
|
|
105
|
+
{"id":"design-system-healthcare","split":"calibration","mode":"design-system","query":"accessible healthcare analytics dashboard for patients","judgments":[{"identity":{"Product Type":"Healthcare App"},"grade":2},{"identity":{"Product Type":"Patient Portal / Health Records"},"grade":1}],"coherence":{"productCategory":"Healthcare App","styleNames":["Accessible & Ethical","Inclusive Design","Neumorphism","Soft UI Evolution"],"patternNames":["Social Proof-Focused","Hero + Testimonials + CTA","Trust & Authority + Conversion"],"colorMode":"light"},"tags":["design-system","coherence","accessibility","readme-example"],"notes":"Accessibility and patient trust are stronger constraints than decorative dashboard styling."},
|
|
106
|
+
{"id":"design-system-portfolio-dark","split":"held_out","mode":"design-system","query":"creative portfolio website with dark mode and scroll storytelling","judgments":[{"identity":{"Product Type":"Portfolio/Personal"},"grade":2}],"coherence":{"productCategory":"Portfolio/Personal","styleNames":["Motion-Driven","Brutalism","Dark Mode (OLED)","Minimalism & Swiss Style","Interactive Cursor Design"],"patternNames":["Storytelling-Driven","Scroll-Triggered Storytelling","Portfolio Grid","Horizontal Scroll Journey"],"colorMode":"dark","colorProductTypes":["Portfolio/Personal"]},"tags":["design-system","coherence","dark-mode","readme-example"],"notes":"Explicit creative intent activates the curated Brutalism rule; the derived dark surface must retain the Portfolio/Personal palette identity."},
|
|
107
|
+
{"id":"design-system-fintech-dark","split":"held_out","mode":"design-system","query":"fintech banking app with a secure dark dashboard","judgments":[{"identity":{"Product Type":"Fintech/Crypto"},"grade":2},{"identity":{"Product Type":"Banking/Traditional Finance"},"grade":1}],"coherence":{"productCategory":"Fintech/Crypto","styleNames":["Dark Mode (OLED)","Glassmorphism","Accessible & Ethical","Minimalism & Swiss Style"],"patternNames":["Trust & Authority","Trust & Authority + Conversion","Enterprise Gateway"],"colorMode":"dark"},"tags":["design-system","coherence","dark-mode","readme-example"],"notes":"Explicit dark mode must not conflict with the palette or anti-pattern advice."},
|
|
108
|
+
{"id":"design-system-spa-paraphrase","split":"held_out","mode":"design-system","query":"calming salon for massages facials and appointment reservations","judgments":[{"identity":{"Product Type":"Beauty/Spa/Wellness Service"},"grade":2},{"identity":{"Product Type":"Booking & Appointment App"},"grade":1}],"coherence":{"productCategory":"Beauty/Spa/Wellness Service","styleNames":["Soft UI Evolution","Neumorphism","Organic Biophilic","Nature Distilled"],"patternNames":["Hero-Centric + Social Proof","Hero-Centric Design","Hero + Testimonials + CTA"],"colorMode":"light"},"tags":["design-system","coherence","paraphrase"],"notes":"Held-out industry paraphrase without the exact words beauty, spa, or wellness."},
|
|
109
|
+
{"id":"design-system-cyber-typo","split":"held_out","mode":"design-system","query":"cybersecurty operatons center with live threat alerts and OLED UI","judgments":[{"identity":{"Product Type":"Cybersecurity Platform"},"grade":2}],"coherence":{"productCategory":"Cybersecurity Platform","styleNames":["Cyberpunk UI","Dark Mode (OLED)","HUD / Sci-Fi FUI"],"patternNames":["Trust & Authority + Real-Time","Real-Time / Operations Landing","Trust & Authority + Conversion"],"colorMode":"dark"},"tags":["design-system","coherence","typo","dark-mode"],"notes":"Typos plus an OLED constraint test end-to-end recovery and agreement."}
|
|
110
|
+
]
|
|
111
|
+
}
|
|
@@ -0,0 +1,100 @@
|
|
|
1
|
+
{
|
|
2
|
+
"schemaVersion": 1,
|
|
3
|
+
"status": "provisional-baseline-regression-gate",
|
|
4
|
+
"baselineRevision": "97eb2a2",
|
|
5
|
+
"runtimeFingerprint": "28aeb1a443663f8e9d27ea5f58ee4307031e92058bbe29162652c9e2d8d7c0ce",
|
|
6
|
+
"oracleFingerprint": "02e7226428c64a995ec24ae104ce4d186f5f91bf0f062556e90ef9b0fcb6d67a",
|
|
7
|
+
"approvingMaintainer": "repository maintainer approved Phase 1 testing checkpoint; second judgment review remains required before final-target promotion",
|
|
8
|
+
"units": "All metrics are ratios in [0,1]. Precision treats missing ranks as non-relevant. Negative abstention is measured across the hard-negative by domain/stack cross-product.",
|
|
9
|
+
"splitPolicy": {
|
|
10
|
+
"calibration": "May be inspected while tuning retrieval.",
|
|
11
|
+
"held_out": "Must not be inspected to tune ranking weights; used for final confirmation.",
|
|
12
|
+
"varianceAndConfidence": "Corpus is deterministic and has no sampling variance. Report exact ratios and sample counts; do not claim population confidence intervals from this curated set."
|
|
13
|
+
},
|
|
14
|
+
"tolerancePolicy": "A 1e-12 numeric tolerance permits floating-point representation only. Current known failures remain visible in relevance-baseline.json; the gate prevents regressions and does not claim final quality targets are met.",
|
|
15
|
+
"metrics": {
|
|
16
|
+
"routingAccuracy": {"floor": 0.875, "tolerance": 1e-12},
|
|
17
|
+
"precisionAt1": {"floor": 0.7631578947368421, "tolerance": 1e-12},
|
|
18
|
+
"precisionAt3": {"floor": 0.3815789473684211, "tolerance": 1e-12},
|
|
19
|
+
"mrrAt3": {"floor": 0.8355263157894737, "tolerance": 1e-12},
|
|
20
|
+
"ndcgAt3": {"floor": 0.8366350964266653, "tolerance": 1e-12},
|
|
21
|
+
"negativeAbstention": {"floor": 0.9117647058823529, "tolerance": 1e-12},
|
|
22
|
+
"typoRecoveryAt3": {"floor": 1.0, "tolerance": 1e-12},
|
|
23
|
+
"designSystemCoherence": {"floor": 0.71875, "tolerance": 1e-12}
|
|
24
|
+
},
|
|
25
|
+
"sampleMinimums": {
|
|
26
|
+
"cases": 90,
|
|
27
|
+
"retrieval": 76,
|
|
28
|
+
"routing": 8,
|
|
29
|
+
"negativeChecks": 204,
|
|
30
|
+
"typo": 5,
|
|
31
|
+
"designSystem": 8,
|
|
32
|
+
"domain:style": 2,
|
|
33
|
+
"domain:color": 2,
|
|
34
|
+
"domain:chart": 2,
|
|
35
|
+
"domain:landing": 2,
|
|
36
|
+
"domain:product": 2,
|
|
37
|
+
"domain:ux": 2,
|
|
38
|
+
"domain:typography": 2,
|
|
39
|
+
"domain:icons": 2,
|
|
40
|
+
"domain:gsap": 2,
|
|
41
|
+
"domain:react": 2,
|
|
42
|
+
"domain:web": 2,
|
|
43
|
+
"domain:google-fonts": 2
|
|
44
|
+
},
|
|
45
|
+
"splits": {
|
|
46
|
+
"calibration": {
|
|
47
|
+
"metrics": {
|
|
48
|
+
"routingAccuracy": {"floor": 0.8, "tolerance": 1e-12},
|
|
49
|
+
"precisionAt1": {"floor": 0.8974358974358975, "tolerance": 1e-12},
|
|
50
|
+
"precisionAt3": {"floor": 0.40170940170940167, "tolerance": 1e-12},
|
|
51
|
+
"mrrAt3": {"floor": 0.9230769230769231, "tolerance": 1e-12},
|
|
52
|
+
"ndcgAt3": {"floor": 0.9103072109232644, "tolerance": 1e-12},
|
|
53
|
+
"negativeAbstention": {"floor": 0.9411764705882353, "tolerance": 1e-12},
|
|
54
|
+
"typoRecoveryAt3": {"floor": 0.0, "tolerance": 1e-12},
|
|
55
|
+
"designSystemCoherence": {"floor": 0.6875, "tolerance": 1e-12}
|
|
56
|
+
},
|
|
57
|
+
"sampleMinimums": {"cases": 46, "retrieval": 39, "routing": 5, "negativeChecks": 102, "typo": 0, "designSystem": 4}
|
|
58
|
+
},
|
|
59
|
+
"held_out": {
|
|
60
|
+
"metrics": {
|
|
61
|
+
"routingAccuracy": {"floor": 1.0, "tolerance": 1e-12},
|
|
62
|
+
"precisionAt1": {"floor": 0.6216216216216216, "tolerance": 1e-12},
|
|
63
|
+
"precisionAt3": {"floor": 0.36036036036036034, "tolerance": 1e-12},
|
|
64
|
+
"mrrAt3": {"floor": 0.7432432432432432, "tolerance": 1e-12},
|
|
65
|
+
"ndcgAt3": {"floor": 0.7589807054707906, "tolerance": 1e-12},
|
|
66
|
+
"negativeAbstention": {"floor": 0.8823529411764706, "tolerance": 1e-12},
|
|
67
|
+
"typoRecoveryAt3": {"floor": 1.0, "tolerance": 1e-12},
|
|
68
|
+
"designSystemCoherence": {"floor": 0.75, "tolerance": 1e-12}
|
|
69
|
+
},
|
|
70
|
+
"sampleMinimums": {"cases": 44, "retrieval": 37, "routing": 3, "negativeChecks": 102, "typo": 5, "designSystem": 4}
|
|
71
|
+
}
|
|
72
|
+
},
|
|
73
|
+
"lockedCases": {
|
|
74
|
+
"domain-style-glassmorphism": {"withinTop": 1, "minimumGrade": 2},
|
|
75
|
+
"domain-color-spa": {"withinTop": 1, "minimumGrade": 2},
|
|
76
|
+
"domain-chart-time-series": {"withinTop": 1, "minimumGrade": 2},
|
|
77
|
+
"domain-landing-pricing": {"withinTop": 1, "minimumGrade": 2},
|
|
78
|
+
"domain-product-spa": {"withinTop": 1, "minimumGrade": 2},
|
|
79
|
+
"domain-ux-keyboard-focus": {"withinTop": 1, "minimumGrade": 2},
|
|
80
|
+
"domain-typography-luxury": {"withinTop": 1, "minimumGrade": 2},
|
|
81
|
+
"domain-icons-search": {"withinTop": 1, "minimumGrade": 2},
|
|
82
|
+
"domain-gsap-scroll-reveal": {"withinTop": 1, "minimumGrade": 2},
|
|
83
|
+
"domain-react-parallel-promises": {"withinTop": 1, "minimumGrade": 2},
|
|
84
|
+
"domain-web-icon-label": {"withinTop": 1, "minimumGrade": 2},
|
|
85
|
+
"domain-google-fonts-inter": {"withinTop": 1, "minimumGrade": 2},
|
|
86
|
+
"stack-swiftui-navigation": {"withinTop": 1, "minimumGrade": 2},
|
|
87
|
+
"stack-threejs-orbitcontrols": {"withinTop": 1, "minimumGrade": 2},
|
|
88
|
+
"stack-uwp-migration": {"withinTop": 1, "minimumGrade": 2},
|
|
89
|
+
"stack-winui-dispatcherqueue": {"withinTop": 1, "minimumGrade": 2}
|
|
90
|
+
},
|
|
91
|
+
"proposedFinalTargets": {
|
|
92
|
+
"routingAccuracy": 0.93,
|
|
93
|
+
"precisionAt1": 0.8,
|
|
94
|
+
"mrrAt3": 0.88,
|
|
95
|
+
"ndcgAt3": 0.92,
|
|
96
|
+
"negativeAbstention": 0.95,
|
|
97
|
+
"typoRecoveryAt3": 0.85,
|
|
98
|
+
"designSystemCoherence": 0.9
|
|
99
|
+
}
|
|
100
|
+
}
|