ui-ux-polish
Iterative UI/UX polishing workflow for web applications. The exact prompt and methodology for achieving Stripe-level visual polish through multiple passes.
What this skill does
# UI/UX Polish — Iterative Enhancement Workflow
> **When to Use:** This is for when your site/app already works and looks decent and you want to improve it. There's a different approach when it looks bad and needs a complete overhaul.
>
> **Key Insight:** Something about asking for agreement from the model ("don't you agree?") somehow motivates it to polish things up better. Also, instructing it to separately think through desktop vs mobile leads to much better outcomes.
---
## The Workflow
### Overview
1. App already works and looks decent
2. Run the polish prompt
3. Agent makes incremental improvements
4. Repeat many times (10+ iterations)
5. Each pass adds small improvements that compound
### Why Multiple Passes Work
- Each time, it tries to make some incremental improvement, even if it's minor
- These really add up after 10 iterations!
- Multiple agents can work on this simultaneously
- Cumulative effect is dramatic
---
## THE EXACT PROMPT — UI/UX Polish
This prompt is used so frequently it's worth putting on a Stream Deck button:
```
I still think there are strong opportunities to enhance the UI/UX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI/UX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI/UX and mobile UI/UX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way. Use ultrathink.
```
---
## Why This Prompt Works
### 1. Asks for Agreement
The phrase "don't you agree?" engages the model's reasoning about whether improvements are possible, rather than just executing instructions.
### 2. Separates Desktop and Mobile
```
"carefully consider desktop UI/UX and mobile UI/UX separately...
hyper-optimize for both separately to play to the specifics of each modality"
```
This prevents the model from making compromises that work "okay" on both but great on neither.
### 3. Sets High Standards
References:
- "world class"
- "best practices like those used by Stripe"
- "makes people gasp at how stunning and perfect it is"
These anchors push the model toward higher quality than generic "make it better" instructions.
### 4. Uses Ultrathink
Extended thinking allows the model to:
- Analyze the current state thoroughly
- Consider multiple improvement options
- Choose the highest-impact changes
- Think through edge cases
---
## Best Models for This Task
| Model | Effectiveness |
|-------|---------------|
| **Claude Code + Opus 4.5** | Excellent |
| **Codex + GPT 5.2** (High/Extra-High reasoning) | Excellent |
| **Gemini CLI** | Good |
---
## Tech Stack Compatibility
This prompt works with:
- Next.js 16 + React 19 + Tailwind 4
- Any modern web framework
- Applications using Framer Motion or similar animation libraries
- Pretty much anything—it's generic enough to adapt
---
## Iteration Protocol
### Single Agent
```
# First pass
[Run the UI/UX polish prompt]
# Review changes
[Agent makes improvements]
# Second pass
[Run the same prompt again]
# Repeat 10+ times until changes become minimal
```
### Multiple Agents
You can have more than one agent working on UI/UX polish simultaneously:
- They'll focus on different areas
- Use file reservations to avoid conflicts
- Compound improvements faster
---
## When to Use vs. When NOT to Use
### USE This Prompt When:
- App works correctly
- Basic styling is in place
- You want to elevate from "decent" to "world-class"
- Ready for iterative refinement
- Want to optimize for both desktop and mobile
### DON'T Use This Prompt When:
- App is broken or buggy (fix bugs first)
- Styling is fundamentally wrong (need complete overhaul)
- No basic design system in place
- Starting from scratch
For complete overhauls, use a different approach focused on establishing a design system and component library first.
---
## What the Model Typically Improves
### Visual Polish
- Spacing and padding consistency
- Typography hierarchy
- Color contrast and accessibility
- Shadow and depth effects
- Border radius consistency
- Hover/focus states
### Interaction Design
- Button feedback
- Loading states
- Transitions and animations
- Error state handling
- Empty state design
### Mobile Optimization
- Touch target sizes
- Responsive breakpoints
- Mobile-specific navigation
- Gesture support
- Performance on mobile devices
### Desktop Optimization
- Keyboard navigation
- Hover states
- Multi-column layouts
- Sidebar navigation
- Power user shortcuts
---
## Tracking Progress
After each iteration, you might notice:
- Subtle shadow improvements
- Better spacing rhythm
- More consistent typography
- Smoother animations
- Better responsive behavior
These small changes compound. An app after 10 passes looks dramatically better than after 1 pass.
---
## Integration with Beads
For systematic UI/UX work, create beads:
```bash
bd create "Polish homepage UI/UX for desktop" -t enhancement -p 2
bd create "Polish homepage UI/UX for mobile" -t enhancement -p 2
bd create "Polish dashboard UI/UX for desktop" -t enhancement -p 2
bd create "Polish dashboard UI/UX for mobile" -t enhancement -p 2
```
This lets agents work on UI/UX polish as part of the normal bead workflow.
---
## Complete Prompt Reference
### Main Polish Prompt
```
I still think there are strong opportunities to enhance the UI/UX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI/UX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI/UX and mobile UI/UX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way. Use ultrathink.
```
### Alternative: General Scrutiny (from agent-swarm-workflow)
```
Great, now I want you to super carefully scrutinize every aspect of the application workflow and implementation and look for things that just seem sub-optimal or even wrong/mistaken to you, things that could very obviously be improved from a user-friendliness and intuitiveness standpoint, places where our UI/UX could be improved and polished to be slicker, more visually appealing, and more premium feeling and just ultra high quality, like Stripe-level apps.
```
---
## Tips
1. **Don't skip iterations** — Even when changes seem small, keep going
2. **Review changes** — Make sure the model isn't breaking things
3. **Test on real devices** — Desktop browser != mobile experience
4. **Consider accessibility** — WCAG compliance matters
5. **Keep performance in mind** — Pretty but slow is bad UX
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.