ui-ux-polish
starsforks
How to install ui-ux-polish?
dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/ui-ux-polish
$npx -y skills add Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill ui-ux-polishIterative UI/UX polishing workflow for web applications. The exact prompt and methodology for achieving Stripe-level visual polish through multiple passes.
SKILL.md
| 1 | # UI/UX Polish — Iterative Enhancement Workflow |
| 2 | |
| 3 | > **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. |
| 4 | > |
| 5 | > **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. |
| 6 | |
| 7 | --- |
| 8 | |
| 9 | ## The Workflow |
| 10 | |
| 11 | ### Overview |
| 12 | |
| 13 | 1. App already works and looks decent |
| 14 | 2. Run the polish prompt |
| 15 | 3. Agent makes incremental improvements |
| 16 | 4. Repeat many times (10+ iterations) |
| 17 | 5. Each pass adds small improvements that compound |
| 18 | |
| 19 | ### Why Multiple Passes Work |
| 20 | |
| 21 | - Each time, it tries to make some incremental improvement, even if it's minor |
| 22 | - These really add up after 10 iterations! |
| 23 | - Multiple agents can work on this simultaneously |
| 24 | - Cumulative effect is dramatic |
| 25 | |
| 26 | --- |
| 27 | |
| 28 | ## THE EXACT PROMPT — UI/UX Polish |
| 29 | |
| 30 | This prompt is used so frequently it's worth putting on a Stream Deck button: |
| 31 | |
| 32 | ``` |
| 33 | 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. |
| 34 | ``` |
| 35 | |
| 36 | --- |
| 37 | |
| 38 | ## Why This Prompt Works |
| 39 | |
| 40 | ### 1. Asks for Agreement |
| 41 | |
| 42 | The phrase "don't you agree?" engages the model's reasoning about whether improvements are possible, rather than just executing instructions. |
| 43 | |
| 44 | ### 2. Separates Desktop and Mobile |
| 45 | |
| 46 | ``` |
| 47 | "carefully consider desktop UI/UX and mobile UI/UX separately... |
| 48 | hyper-optimize for both separately to play to the specifics of each modality" |
| 49 | ``` |
| 50 | |
| 51 | This prevents the model from making compromises that work "okay" on both but great on neither. |
| 52 | |
| 53 | ### 3. Sets High Standards |
| 54 | |
| 55 | References: |
| 56 | - "world class" |
| 57 | - "best practices like those used by Stripe" |
| 58 | - "makes people gasp at how stunning and perfect it is" |
| 59 | |
| 60 | These anchors push the model toward higher quality than generic "make it better" instructions. |
| 61 | |
| 62 | ### 4. Uses Ultrathink |
| 63 | |
| 64 | Extended thinking allows the model to: |
| 65 | - Analyze the current state thoroughly |
| 66 | - Consider multiple improvement options |
| 67 | - Choose the highest-impact changes |
| 68 | - Think through edge cases |
| 69 | |
| 70 | --- |
| 71 | |
| 72 | ## Best Models for This Task |
| 73 | |
| 74 | | Model | Effectiveness | |
| 75 | |-------|---------------| |
| 76 | | **Claude Code + Opus 4.5** | Excellent | |
| 77 | | **Codex + GPT 5.2** (High/Extra-High reasoning) | Excellent | |
| 78 | | **Gemini CLI** | Good | |
| 79 | |
| 80 | --- |
| 81 | |
| 82 | ## Tech Stack Compatibility |
| 83 | |
| 84 | This prompt works with: |
| 85 | - Next.js 16 + React 19 + Tailwind 4 |
| 86 | - Any modern web framework |
| 87 | - Applications using Framer Motion or similar animation libraries |
| 88 | - Pretty much anything—it's generic enough to adapt |
| 89 | |
| 90 | --- |
| 91 | |
| 92 | ## Iteration Protocol |
| 93 | |
| 94 | ### Single Agent |
| 95 | |
| 96 | ``` |
| 97 | # First pass |
| 98 | [Run the UI/UX polish prompt] |
| 99 | |
| 100 | # Review changes |
| 101 | [Agent makes improvements] |
| 102 | |
| 103 | # Second pass |
| 104 | [Run the same prompt again] |
| 105 | |
| 106 | # Repeat 10+ times until changes become minimal |
| 107 | ``` |
| 108 | |
| 109 | ### Multiple Agents |
| 110 | |
| 111 | You can have more than one agent working on UI/UX polish simultaneously: |
| 112 | - They'll focus on different areas |
| 113 | - Use file reservations to avoid conflicts |
| 114 | - Compound improvements faster |
| 115 | |
| 116 | --- |
| 117 | |
| 118 | ## When to Use vs. When NOT to Use |
| 119 | |
| 120 | ### USE This Prompt When: |
| 121 | |
| 122 | - App works correctly |
| 123 | - Basic styling is in place |
| 124 | - You want to elevate from "decent" to "world-class" |
| 125 | - Ready for iterative refinement |
| 126 | - Want to optimize for both desktop and mobile |
| 127 | |
| 128 | ### DON'T Use This Prompt When: |
| 129 | |
| 130 | - App is broken or buggy (fix bugs first) |
| 131 | - Styling is fundamentally wrong (need complete overhaul) |
| 132 | - No basic design system in place |
| 133 | - Starting from scratch |
| 134 | |
| 135 | For complete overhauls, use a different approach focused on establishing a design system and component library first. |
| 136 | |
| 137 | --- |
| 138 | |
| 139 | ## What the Model Typically Improves |
| 140 | |
| 141 | ### Visual Polish |
| 142 | - Spacing and padding consistency |
| 143 | - Typography hierarchy |
| 144 | - Color contrast and accessibility |
| 145 | - Shadow and depth effects |
| 146 | - Border radius consistency |
| 147 | - Hover/focus states |
| 148 | |
| 149 | ### Interaction Design |
| 150 | - Button feedback |
| 151 | - Loading states |
| 152 | - Transitions and animations |
| 153 | - Error state handling |
| 154 | - Empty state design |
| 155 | |
| 156 | ### Mobile Optimization |
| 157 | - Touch target sizes |
| 158 | - Responsive breakpoints |
| 159 | - Mobile-specific navigation |
| 160 | - Gesture support |
| 161 | - Performance on mobile devices |
| 162 | |
| 163 | ### Desktop Optimization |
| 164 | - Keyboard navigation |
| 165 | - Hover states |
| 166 | - Multi-column layouts |
| 167 | - Sidebar navigation |
| 168 | - Power user shortcuts |
| 169 | |
| 170 | --- |
| 171 | |
| 172 | ## Tracking Progress |
| 173 | |
| 174 | After each iteration |
People who liked this also viewed
6 picksType
- web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".SkillsJul 2026
- lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 SkillsJul 2026
- design-taste-frontendTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop SkillsJul 2026
- ui-ux-pro-maxUI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presSkillsJul 2026
- caveman-helpQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".SkillsJul 2026
- codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-nSkillsJul 2026
