ui-refactor
A design review and UI improvement skill for frontend interfaces. This skill should be used when the user asks to "review a design", "review a screenshot", "improve the UI", "make this look better", "fix the design", "check spacing", "improve visual hierarchy", "choose colors", "pick fonts", "review my CSS", "review my Tailwind", "make this more professional", "design feedback", "fix the layout", "improve typography", "check contrast", "add depth", "polish the UI", or is working on frontend code (HTML, CSS, JSX, TSX, Svelte, Vue) where design quality matters.
What this skill does
# UI Refactor — Design Review Skill ## Core Philosophy Design quality comes from specific, learnable decisions — not innate talent. Three principles underpin everything: 1. **Hierarchy is the #1 factor.** An interface where every element competes equally for attention feels chaotic. Deliberately de-emphasize secondary elements before amplifying primary ones. 2. **Constrained choices beat infinite options.** Pre-define systems for spacing, type sizes, colors, and shadows. Pick from the system, never from the infinite continuum. Decision fatigue kills quality. 3. **Start functional, add polish last.** Design features not layouts, work in grayscale before adding color, ship the smallest useful version. Details like shadows and icons are finishing touches, not starting points. ## Review Workflow When reviewing a design (screenshot, code, or description), evaluate across six dimensions in priority order: 1. **Hierarchy & Emphasis** — Can you identify primary, secondary, and tertiary content instantly? Is there a clear visual path? 2. **Spacing & Layout** — Is spacing systematic? Do groups feel cohesive? Is there ambiguous spacing? 3. **Typography** — Is the type scale constrained? Are line-heights proportional? Are line lengths readable? 4. **Color** — Are colors from a defined system? Do greys have temperature? Is contrast accessible? 5. **Depth & Images** — Are shadows from a defined elevation system? Is text readable on images? 6. **Polish & Finishing** — Are defaults supercharged? Are borders overused? Are empty states designed? **Output format:** ``` ## Design Review ### What Works Well - [Specific praise with why it works] ### Issues Found 1. **[Issue Name]** — [Dimension] - What: [Observable problem] - Why: [Principle being violated] - Fix: [Concrete CSS/code change] ### Quick Wins - [Highest-impact, lowest-effort changes] ``` ## Advisory Workflow When answering design questions during development (not reviewing existing work): 1. Identify which dimension the question falls under 2. Load the relevant reference file 3. Provide the specific principle, concrete values, and reasoning 4. If the question spans multiple dimensions, address the highest-priority one first ## Decision Tree — Which Reference to Load Route to the right reference based on the symptom: | Symptom | Load | |---------|------| | "Everything looks the same weight/importance" | `references/hierarchy-and-emphasis.md` | | "It looks cramped" or "spacing feels off" | `references/spacing-and-layout.md` | | "The fonts don't feel right" or "text is hard to read" | `references/typography.md` | | "Colors feel random" or "it looks washed out" | `references/color.md` | | "It feels flat" or "text on images is unreadable" | `references/depth-and-images.md` | | "It looks amateur" or "needs more polish" | `references/polish-and-finishing.md` | | "Where do I even start?" or general design process | `references/design-process.md` | | Reviewing a full screenshot or page | Load `references/hierarchy-and-emphasis.md` first, then others as issues emerge | ## Quick Anti-Pattern Checklist Before loading any reference files, check for these 8 high-signal problems: 1. **Wall of Content** — Everything at the same size/weight/color. No primary-secondary-tertiary distinction. 2. **Ambiguous Spacing** — Equal gaps between a label and its input vs. between form groups. Proximity doesn't signal relationship. 3. **Font Size Soup** — More than 8 distinct font sizes visible. No constrained type scale. 4. **Color Without System** — Ad-hoc hex values. No visible shade palette. Grey text on colored backgrounds using literal grey. 5. **One Shadow Fits All** — Same box-shadow on buttons, cards, and modals. No elevation hierarchy. 6. **Border Everything** — Borders used as the default separator when spacing, background color, or box-shadow would be cleaner. 7. **Full-Width Everything** — Content stretched to fill viewport when a max-width constraint would improve readability. 8. **Ignored Empty States** — Blank screens with just "No items found" — no illustration, no guidance, no call-to-action. If any are detected, load the relevant reference for detailed fixes. ## Reference Files | File | Contents | Load When | |------|----------|-----------| | `references/design-process.md` | Start with features, work low-fidelity, constrain choices, define personality | Starting a new design or asking "where do I begin?" | | `references/hierarchy-and-emphasis.md` | Emphasize by de-emphasizing, weight + color + size for hierarchy, labels as last resort, semantic vs visual hierarchy | Hierarchy issues detected or reviewing any full interface | | `references/spacing-and-layout.md` | Non-linear spacing scale, start with too much whitespace, fixed sidebars, avoid ambiguous spacing | Spacing/layout issues or reviewing component/page structure | | `references/typography.md` | Hand-crafted type scale, proportional line-height, line length, letter-spacing, baseline alignment | Typography issues or text-heavy interfaces | | `references/color.md` | HSL workflow, 8-10 shades per color, hue rotation, warm/cool greys, accessible contrast | Color issues, palette creation, or contrast problems | | `references/depth-and-images.md` | 5-level shadow system, two-part shadows, flat depth, text on images, icon sizing | Depth/shadow issues or image-related problems | | `references/polish-and-finishing.md` | Supercharged defaults, accent borders, fewer borders, empty states, thinking outside the box | "It needs more polish" or finishing a nearly-complete design |
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.