Skip to content

notque/vexjoy-agent / skills/frontend/frontend

frontend

Unverified

Frontend: UI design, distinctive visual styles, HTML artifacts, Three.js 3D, TypeScript/React/Next.js apps, e-commerce, portfolios, React Native, web performance.

FileKindSize
SKILL.mdskill md22.5 KB
SPEC.mdmarkdown4.3 KB
agents/html-builder.mdmarkdown5.9 KB
assets/base-template.htmlother495 B
references/design-refs/accessibility-review.mdmarkdown13.0 KB
references/design-refs/design-critique.mdmarkdown10.4 KB
references/design-refs/design-handoff.mdmarkdown9.9 KB
references/design-refs/design-systems.mdmarkdown9.3 KB
references/design-refs/llm-design-failure-modes.mdmarkdown9.1 KB
references/design-refs/ux-copy.mdmarkdown9.5 KB
references/distinctive-frontend-design-refs/animation-patterns.mdmarkdown10.5 KB
references/distinctive-frontend-design-refs/background-techniques.mdmarkdown10.5 KB
references/distinctive-frontend-design-refs/balatro-shader-breakdown.mdmarkdown14.9 KB
references/distinctive-frontend-design-refs/card-shader-patterns.mdmarkdown10.9 KB
references/distinctive-frontend-design-refs/color-inspirations.jsonconfig9.4 KB
references/distinctive-frontend-design-refs/css-audit-patterns.mdmarkdown4.7 KB
references/distinctive-frontend-design-refs/font-catalog.jsonconfig9.7 KB
references/distinctive-frontend-design-refs/game-ui-polish.mdmarkdown6.3 KB
references/distinctive-frontend-design-refs/honest-placeholders.mdmarkdown3.2 KB
references/distinctive-frontend-design-refs/implementation-examples.mdmarkdown7.7 KB
references/distinctive-frontend-design-refs/macrostructure-catalog.mdmarkdown9.3 KB
references/distinctive-frontend-design-refs/oklch-color-harmony.mdmarkdown7.3 KB
references/distinctive-frontend-design-refs/performance-budgets.mdmarkdown10.6 KB
references/distinctive-frontend-design-refs/phase-details.mdmarkdown4.8 KB
references/distinctive-frontend-design-refs/pptx-conversion.mdmarkdown9.7 KB
references/distinctive-frontend-design-refs/roll-text.mdmarkdown7.2 KB
references/distinctive-frontend-design-refs/shader-integration-react.mdmarkdown16.7 KB
references/distinctive-frontend-design-refs/slide-controller.mdmarkdown9.4 KB
references/distinctive-frontend-design-refs/text-animation-patterns.mdmarkdown4.3 KB
references/html-artifact-refs/design-system.mdmarkdown10.2 KB
references/html-artifact-refs/diagram-layering.mdmarkdown3.9 KB
references/html-artifact-refs/infographic-layouts.mdmarkdown4.9 KB
references/html-artifact-refs/pdf-export.mdmarkdown6.0 KB
references/html-artifact-refs/pptx-export.mdmarkdown10.2 KB
references/html-artifact-refs/shape-diagram-illustration.mdmarkdown4.3 KB
references/nextjs-ecommerce.mdmarkdown3.4 KB
references/nextjs-ecommerce/admin-dashboard.mdmarkdown9.8 KB
references/nextjs-ecommerce/error-catalog.mdmarkdown7.9 KB
references/nextjs-ecommerce/expertise.mdmarkdown5.1 KB
references/nextjs-ecommerce/patterns-and-errors.mdmarkdown4.6 KB
references/nextjs-ecommerce/preferred-patterns.mdmarkdown8.0 KB
references/nextjs-ecommerce/shopping-cart-patterns.mdmarkdown7.7 KB
references/nextjs-ecommerce/stripe-integration.mdmarkdown9.5 KB
references/performance-optimization.mdmarkdown9.9 KB
references/performance-optimization/browser-dom-optimizations.mdmarkdown6.0 KB
references/performance-optimization/bundle-optimization.mdmarkdown7.9 KB
references/performance-optimization/core-web-vitals.mdmarkdown9.6 KB
references/performance-optimization/js-algorithm-optimizations.mdmarkdown9.6 KB
references/performance-optimization/metrics-and-monitoring.mdmarkdown8.8 KB
references/performance-optimization/nextjs-optimization.mdmarkdown10.6 KB
references/performance-optimization/performance-testing.mdmarkdown9.6 KB
references/performance-optimization/preferred-patterns.mdmarkdown7.4 KB
references/performance-optimization/react-async-patterns.mdmarkdown7.0 KB
references/performance-optimization/react-bundle-optimization.mdmarkdown6.3 KB
references/performance-optimization/react-rendering-performance.mdmarkdown12.0 KB
references/react-native.mdmarkdown4.4 KB
references/react-native/animation-patterns.mdmarkdown3.9 KB
references/react-native/error-handling.mdmarkdown7.7 KB
references/react-native/list-performance.mdmarkdown5.4 KB
references/react-native/monorepo-config.mdmarkdown2.3 KB
references/react-native/navigation-patterns.mdmarkdown2.0 KB
references/react-native/rendering-patterns.mdmarkdown3.2 KB
references/react-native/state-management.mdmarkdown3.3 KB
references/react-native/testing.mdmarkdown6.2 KB
references/react-native/ui-patterns.mdmarkdown5.0 KB
references/react-portfolio.mdmarkdown7.7 KB
references/react-portfolio/gallery-patterns.mdmarkdown2.5 KB
references/react-portfolio/image-optimization.mdmarkdown3.4 KB
references/react-portfolio/lightbox-patterns.mdmarkdown6.1 KB
references/react-portfolio/nextjs-app-router.mdmarkdown4.9 KB
references/react-portfolio/performance.mdmarkdown3.9 KB
references/react-portfolio/portfolio-seo.mdmarkdown4.8 KB
references/react-portfolio/responsive-design.mdmarkdown3.3 KB
references/threejs-builder-refs/advanced-animation.mdmarkdown12.1 KB
references/threejs-builder-refs/advanced-topics.mdmarkdown11.0 KB
references/threejs-builder-refs/build-recipes.mdmarkdown7.4 KB
references/threejs-builder-refs/game-architecture.mdmarkdown10.4 KB
references/threejs-builder-refs/game-patterns.mdmarkdown12.5 KB
references/threejs-builder-refs/gltf-loading.mdmarkdown8.6 KB
references/threejs-builder-refs/performance-patterns.mdmarkdown11.8 KB
references/threejs-builder-refs/react-three-fiber.mdmarkdown17.8 KB
references/threejs-builder-refs/shader-patterns.mdmarkdown15.0 KB
references/threejs-builder-refs/visual-polish.mdmarkdown16.3 KB
references/threejs-builder-refs/webgpu.mdmarkdown20.4 KB
references/typescript-frontend.mdmarkdown5.3 KB
references/typescript-frontend/engineering-rules.mdmarkdown7.8 KB
references/typescript-frontend/nextjs-security.mdmarkdown2.6 KB
references/typescript-frontend/react-view-transitions.mdmarkdown5.4 KB
references/ui-design.mdmarkdown10.2 KB
references/ui-design/ai-slop-detection.mdmarkdown8.5 KB
references/ui-design/design-conventions.mdmarkdown2.8 KB
references/ui-design/motion-and-interaction.mdmarkdown5.6 KB
scripts-distinctive-frontend-design/css_slop_rules.pyscript15.3 KB
scripts-distinctive-frontend-design/tests/test_css_slop_rules.pyscript6.9 KB
scripts-distinctive-frontend-design/tests/test_validate_design_advisory.pyscript3.3 KB
scripts-distinctive-frontend-design/tests/test_validate_design_macro.pyscript4.3 KB
scripts-distinctive-frontend-design/validate_design.pyscript22.2 KB
scripts-html-artifact/assemble-template.pyscript7.5 KB
scripts-html-artifact/css_slop_rules.pyscript15.4 KB
scripts-html-artifact/detect-shape.pyscript7.0 KB
scripts-html-artifact/fill-template.pyscript5.5 KB
scripts-html-artifact/pptx-bridge/__init__.pyscript490 B
scripts-html-artifact/pptx-bridge/_pptx_engine.pyscript26.4 KB
scripts-html-artifact/pptx-bridge/extract_slides.pyscript13.5 KB
scripts-html-artifact/pptx-bridge/render_pptx.pyscript6.9 KB
scripts-html-artifact/pptx-bridge/run-unified.pyscript11.6 KB
scripts-html-artifact/render-github-issues.pyscript7.5 KB
scripts-html-artifact/tests/test_assemble_template.pyscript29.5 KB
scripts-html-artifact/tests/test_css_slop_emission.pyscript7.9 KB
scripts-html-artifact/tests/test_detect_shape.pyscript5.3 KB
scripts-html-artifact/tests/test_fill_template.pyscript5.2 KB
scripts-html-artifact/tests/test_to_pdf.pyscript13.3 KB
scripts-html-artifact/tests/test_validate_artifact.pyscript13.6 KB
scripts-html-artifact/to-pdf.pyscript12.5 KB
scripts-html-artifact/validate-artifact.pyscript11.0 KB
templates/base-reset.cssother1.2 KB
templates/components/collapsible.cssother1.1 KB
templates/components/collapsible.jsscript516 B
templates/components/copy-button.cssother534 B
templates/components/copy-button.jsscript334 B
templates/components/drag-drop.cssother612 B
templates/components/drag-drop.jsscript1.1 KB
templates/components/filter.cssother1.1 KB
templates/components/filter.jsscript987 B
templates/components/keyboard-nav.cssother249 B
templates/components/keyboard-nav.jsscript900 B
templates/components/scrollytelling.cssother1.5 KB
templates/components/scrollytelling.jsscript2.0 KB
templates/components/slider.cssother848 B
templates/components/tabs.cssother770 B
templates/components/tabs.jsscript508 B
templates/components/theme-toggle.cssother1.2 KB
templates/components/theme-toggle.jsscript178 B
templates/fonts/ArchivoBlack-OFL.txtmarkdown4.4 KB
templates/fonts/archivo-black.cssother13.7 KB
templates/print/code-review-print.cssother1.9 KB
templates/print/data-viz-print.cssother1.5 KB
templates/print/deck-print.cssother1.5 KB
templates/print/default-print.cssother1.6 KB
templates/print/diagram-print.cssother1.6 KB
templates/print/editor-print.cssother2.1 KB
templates/print/prototype-print.cssother1.4 KB
templates/print/report-print.cssother1.8 KB
templates/print/spec-print.cssother1.4 KB
templates/saved/README.mdmarkdown1.8 KB
templates/saved/business-review.htmlother17.1 KB
templates/saved/business-review.slots.jsonconfig1.5 KB
templates/saved/github-issues.htmlother34.0 KB
templates/saved/project-kickoff.htmlother17.3 KB
templates/saved/project-kickoff.slots.jsonconfig1.7 KB
templates/saved/system-design.htmlother16.9 KB
templates/saved/system-design.slots.jsonconfig1.6 KB
templates/shapes/code-review.cssother2.7 KB
templates/shapes/data-viz.cssother2.3 KB
templates/shapes/deck.cssother1.9 KB
templates/shapes/diagram.cssother2.7 KB
templates/shapes/editor.cssother2.8 KB
templates/shapes/prototype.cssother2.7 KB
templates/shapes/report.cssother2.9 KB
templates/shapes/spec.cssother3.0 KB
templates/themes/birchline.cssother2.4 KB
templates/themes/dark-focus.cssother2.6 KB
templates/themes/interactive-warm.cssother4.5 KB
templates/themes/minimal-document.cssother2.6 KB

references/design-refs/llm-design-failure-modes.md

View on GitHub
# LLM Design Failure Modes

Specific ways LLMs fail at design tasks. Each failure mode includes detection signals and concrete defenses. Load this reference for every design mode, after `skills/shared-patterns/ui-design-judgment.md`. Visual tells of generated UI (gradients, card mosaics, emoji icons, overcorrection) live in that doc's section 9 and are not repeated here.

> **Shared base**: Universal LLM failure modes (hallucination, overconfidence, generic output, arithmetic errors, stale knowledge) are documented in `skills/shared-patterns/llm-domain-failure-modes-base.md`. This file covers design-specific failures only.

---

## 1. Generic Copy Without Product Context

Core rules: `ui-design-judgment.md` section 8. Detection: the copy would work unchanged for a banking app and a game, or a competitor could ship the same words. Defense: ask for existing terminology and voice first; name the user's actual object ("No invoices yet", "Create invoice").

---

## 2. Inaccessible Color Suggestions

Core rules: `ui-design-judgment.md` section 5 (4.5:1 body, 3:1 large text and UI). Common misses: white text on mid-tone brand colors (500 shades and lighter), gray text lighter than #767676 on white, status colors used as text on white, placeholder text. Defense: state the ratio for every pair you recommend; safe anchors are gray-800 on white (14.72:1) and gray-600 on white (7.45:1).

---

## 3. Platform-Blind Critique

**What happens**: LLM applies desktop web conventions to mobile designs, or iOS patterns to Android, or web patterns to native apps.

**Detection signals**:
- Suggesting hover states for mobile interfaces
- Recommending hamburger menu for an iOS app (use tab bar instead)
- Applying web-style dropdowns to native mobile (use bottom sheets)
- Suggesting right-click context menus for touch interfaces
- Recommending text sizes below 16px for mobile body text

**Defense**:
- Identify the target platform before critiquing
- Apply platform-specific conventions:

| Platform | Key Conventions |
|----------|----------------|
| iOS | Tab bar (bottom), navigation bar (top), system sheets, swipe gestures, SF Symbols, 44pt touch targets |
| Android | Bottom navigation, FAB, Material Design components, back button, 48dp touch targets |
| Web Desktop | Sidebar nav, hover states, right-click menus, keyboard shortcuts, cursor states |
| Web Mobile | Bottom navigation, thumb-zone awareness, touch targets 44px+, no hover dependency |

- When platform is ambiguous, ask. "Is this for web or native mobile?"

---

## 4. Missing Edge Cases in Specs

**What happens**: LLM generates clean specs for the happy path — a well-formed form, a list with 5-10 items, a short username. Real products encounter extremes.

**Detection signals**:
- No empty state documented
- No loading state specified
- No error state designed
- No mention of content overflow
- No slow/offline connection handling
- "The user enters their name" but no spec for a 200-character name

**Defense**:
Use this checklist for every spec:

| Category | Edge Cases to Cover |
|----------|-------------------|
| Content length | Empty (0), one, minimum, typical, maximum, overflow |
| Data states | Loading (initial), loading (more), loading (action), success, error (inline), error (page), offline, stale |
| User input | Valid, invalid format, empty required, max length, special characters, paste, autofill |
| List/collection | 0 items, 1 item, typical count, maximum count, filtered to 0 |
| Permissions | Admin, editor, viewer, no access, expired access |
| Timing | Instant response, slow response (2-5s), timeout (30s+), rate-limited |
| i18n | Text 40% longer, RTL layout, locale-specific formatting |

---

## 5. Surface-Level Critique

Detection: adjectives with no element ("clean", "modern", "intuitive"); feedback that fits any design. Defense: the finding format in `ui-design-judgment.md` section 10: element, problem, effect, fix. "The 32px section spacing creates consistent rhythm" is feedback; "clean layout" is not. Say what works and which principle it applies.

---

## 6. Fabricated Research Findings

**What happens**: LLM invents plausible user quotes, statistics, persona details, or research findings that sound authoritative but have no source.

**Detection signals**:
- Specific statistics without source: "73% of users prefer..."
- User quotes that sound polished rather than natural
- Persona details too detailed to derive from the input data
- Confident claims about user behavior with no evidence trail
- "Research shows..." without citing which research

**Defense**:
- Every finding traces to specific user-provided data. If no data was provided, state the limitation.
- Use participant type attribution: "3 of 5 enterprise admins mentioned..." — not invented names
- Flag confidence levels: HIGH (multiple sources, behavioral data), MEDIUM (single source, self-reported), LOW (inferred, limited data)
- Mark assumptions explicitly: "Assumption: users complete this flow in a single session. Validate with session data."
- When asked about user behavior with no data, say so. "I don't have behavioral data on this. Here's what the design implies about expected behavior."

---

## 7. Token-Value Confusion

**What happens**: LLM specs use raw values (`#3B82F6`, `16px`, `0.5rem`) instead of design token references (`color-primary`, `spacing-4`, `space-2`).

**Detection signals**:
- Hex codes in the spec where token names should be
- Pixel values without corresponding token names
- Font specifications using raw values instead of type scale tokens
- Inconsistent values that should reference the same token

**Defense**:
- Ask for the design system's token naming convention before writing specs
- Every value in a spec should be a token reference: `color-primary` not `#3B82F6`
- When the token system is unknown, use conventional names and flag them: "Assuming token naming convention. Verify against your design system."
- Flag any raw value with: "Needs token mapping — verify [value] maps to [suggested token name]"
- If a value does not fit any existing token, call it out: "No existing token matches this value. Consider creating `spacing-section-header: 28px` or adjusting to nearest token `spacing-8: 32px`."

---

## 8. Framework Dumping

**What happens**: LLM lists all 10 Nielsen heuristics, all WCAG criteria, or all design principles as a checklist without applying them to the specific design.

**Detection signals**:
- All 10 heuristics listed regardless of relevance
- WCAG criteria listed without checking specific elements
- Design principles stated abstractly: "Contrast is important for hierarchy"
- No specific design elements referenced in the analysis
- Equal depth on all points instead of focusing on actual issues

**Defense**:
- Apply each criterion to the actual design. Skip criteria that do not apply.
- Focus depth on actual findings. A design with great keyboard support and poor contrast deserves a paragraph on contrast and a sentence on keyboard.
- Cite the specific element that passes or fails each criterion
- "WCAG 1.4.3 Contrast: The body text (#6B7280 on #FFFFFF) passes at 4.63:1." — not "Contrast should be at least 4.5:1 for normal text."

---

## 9. Ignoring Design System Constraints

**What happens**: LLM suggests components or patterns that conflict with the product's existing design system, introducing visual inconsistency.

**Detection signals**:
- Recommending a component variant that does not exist in the system
- Suggesting custom styling instead of using existing component props
- Proposing a new pattern when an existing one would work
- Mixing conventions from different design systems (Material + Apple HIG)

**Defense**:
- Ask what design system the product uses before making recommendations
- Recommend existing components and variants first. Propose new ones only when existing components cannot solve the problem.
- When suggesting a new pattern, show its relationship to existing patterns: "This extends the existing Card component with a new `featured` variant"
- Flag when a recommendation might conflict with existing patterns: "Check if your design system already has a notification component before building this custom one"

---

## 10. Treating Mobile as Smaller Desktop

**What happens**: LLM applies desktop interaction patterns to mobile, resulting in designs that ignore how mobile users actually hold and interact with their devices.

**Detection signals**:
- Small touch targets (below 44px)
- Hover-dependent interactions
- Dense information layouts without mobile-specific reorganization
- No consideration of thumb zone (reachability)
- Desktop-style dropdowns instead of mobile-native bottom sheets

**Defense**:
- Thumb zone awareness: primary actions in the bottom half of the screen (easy reach), secondary in the top half
- Touch targets: minimum 44x44 CSS pixels, with 8px spacing between targets
- Interaction patterns: bottom sheets over dropdowns, swipe gestures for common actions, pull-to-refresh
- Content density: reduce visible items, use progressive disclosure, larger type sizes (minimum 16px body)
- Text input: minimize typing, use pickers/selectors where possible, auto-capitalize, appropriate keyboard type (`type="email"`, `type="tel"`)
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall