redesign
Skill1 starsChanged 3 days agoMITView on GitHub
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- Integralist/agent-skillstheir own version, first seen Nov 14, 2026
- plugin87/ux-ui-agent-skillstheir own version, first seen Nov 10, 2026
- superset-sh/supersettheir own version, first seen Nov 2, 2026
- F0rger123/CLAUDE-DESIGN-GOD-MODEtheir own version, first seen Nov 1, 2026
- ParadevAI/Paradevtheir own version, first seen Nov 1, 2026
- LucasCooperBey/claude-skillsword for word, first seen Oct 20, 2026
Used with
Projects with it also use decide and polish.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dirienSkilldecide
Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.
Also in 3 projects that use this
HK-hubSkillpolish
Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
Also in 3 projects that use this
Other versions13 projects use a version of this.
Word for word · 1
- LucasCooperBey/claude-skills★ 1100% same
Edited · 0
None found.
Wrote their own version · 12
- ParadevAI/Paradev★ 16ksame name
- superset-sh/superset★ 16ksame name
- plugin87/ux-ui-agent-skills★ 3.2ksame name
- educlopez/ui-craft★ 441same name
- Integralist/agent-skills★ 29same name
- arjunkshah/design-skill★ 21same name
- ItamarZand88/design-skills★ 8same name
- VoxTechnologies/transmute-framework★ 5same name
- vagkaratzas/skills★ 4same name
- Darcos-Loft/fluid★ 3same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository53 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/deep-recon/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adversarial-researchSkill
- algorithmic-artSkill
- api-integrationSkill
- breakdownSkill
- c4-architectSkill
- canvas-designSkill
- coding-agentsSkill
- compound-engineeringSkill
- context-budgetSkill
- counterfactualSkill
- critiqueSkill
- d3js-visualizationSkill
- data-analyst-agentSkill
- database-migrationsSkill
- deep-reconSkill
- design-tasteSkill
- e2b-sandboxSkill
- ecosystem-auditSkill
- executing-plansSkill
- frontend-designSkill
- fullstack-agentSkill
- grillSkill
- kickoffSkill
- mcp-builderSkill
- model-migrationSkill
- naming-the-machineSkill
- full-output-enforcementSkill
- package-researchSkill
- pdf-generationSkill
- pp2pSkill
- pp3pSkill
- prompt-engineerSkill
- prompt-groundingSkill
- requesting-code-reviewSkill
- reverse-engineer-to-learnSkill
- review-changesSkill
- scratchpadSkill
- shipSkill
- slack-gif-creatorSkill
- sprint-architectSkill
- techdebtSkill
- test-and-fixSkill
- threat-modelSkill
- verification-before-completionSkill
- visual-verdictSkill
- webapp-testingSkill
- web-asset-generatorSkill
- whatdidimissSkill
- wiki-writeSkill
- writing-plansSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 12 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Only Regular/Bold weights → Introduce Medium (500) and SemiBold (600)
- Distinctive: line 40
No max-width container → Add ~1200-1440px with auto margins
- Distinctive: line 41
No overlap or depth → Negative margins for layering
- Distinctive: line 46
No hover states → Add background shift, slight scale, or translate
- Very specific: line 47
No active/pressed feedback → scale(0.98) or translateY(1px)
- Distinctive: line 50
No loading states → Skeleton loaders matching layout shape
- Distinctive: line 51
No empty states → Composed "getting started" view
- Distinctive: line 52
No error states → Clear, inline error messages
- Distinctive: line 69
No legal links (privacy policy, terms)
- Distinctive: line 74
No cookie consent (if required by jurisdiction)
- Distinctive: line 89
Do not break existing functionality.
- Distinctive: line 90
Before importing new libraries, check dependency file first.
- Distinctive: line 91
Keep changes reviewable and focused.
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Redesign Skill
How This Works
- Scan — Read the codebase. Identify the framework, styling method, and current design patterns.
- Diagnose — Run through the audit below. List every generic pattern, weak point, and missing state.
- Fix — Apply targeted upgrades working with the existing stack. Do not rewrite from scratch.
Design Audit
Typography
- Browser default fonts or Inter everywhere → Replace with
Geist,Outfit,Cabinet Grotesk,Satoshi - Headlines lack presence → Increase size, tighten letter-spacing, reduce line-height
- Body text too wide → Limit to ~65 characters, increase line-height
- Only Regular/Bold weights → Introduce Medium (500) and SemiBold (600)
- Numbers in proportional font → Use monospace or
font-variant-numeric: tabular-nums - Orphaned words → Fix with
text-wrap: balanceortext-wrap: pretty
Color and Surfaces
- Pure
#000000background → Off-black (#0a0a0a,#121212) - Oversaturated accents → Keep saturation < 80%
- More than one accent color → Pick one, remove the rest
- Mixing warm and cool grays → Stick to one gray family
- Purple/blue "AI gradient" aesthetic → Most common AI fingerprint, replace
- Generic
box-shadow→ Tint shadows to match background hue - Flat design with zero texture → Add subtle noise, grain, or micro-patterns
- Random dark sections in a light page → Keep consistent background tone
- Empty flat sections → Add background imagery, patterns, or ambient gradients
Layout
- Everything centered and symmetrical → Break with offset margins, mixed aspect ratios
- Three equal card columns → 2-column zig-zag, asymmetric grid, or masonry
height: 100vh→min-height: 100dvh(iOS Safari fix)- Complex flexbox math → CSS Grid
- No max-width container → Add ~1200-1440px with auto margins
- No overlap or depth → Negative margins for layering
- Buttons not bottom-aligned in card groups → Pin to bottom
- Mathematical alignment that looks optically wrong → 1-2px optical adjustments
Interactivity and States
- No hover states → Add background shift, slight scale, or translate
- No active/pressed feedback →
scale(0.98)ortranslateY(1px) - Instant transitions → 200-300ms smooth transitions
- Missing focus ring → Visible focus indicators (accessibility requirement)
- No loading states → Skeleton loaders matching layout shape
- No empty states → Composed "getting started" view
- No error states → Clear, inline error messages
- Animations using
top/left/width/height→transformandopacityonly
Content
- Generic names ("John Doe") → Diverse, realistic names
- Fake round numbers (
99.99%) → Organic data (47.2%) - AI copywriting cliches → "Elevate", "Seamless", "Unleash" all banned
- Lorem Ipsum → Real draft copy always
- Same avatar for multiple users → Unique assets per person
Component Patterns
- Generic card look → Remove border OR use only background OR use only spacing
- 3-card carousel testimonials → Masonry wall, embedded social, single rotating quote
- Modals for everything → Inline editing, slide-over panels, expandable sections
- Footer link farm → Simplify to main paths + legal links
Strategic Omissions (What AI Forgets)
- No legal links (privacy policy, terms)
- No "back" navigation
- No custom 404 page
- No form validation
- No "skip to content" link
- No cookie consent (if required by jurisdiction)
Fix Priority (maximum impact, minimum risk)
- Font swap — biggest instant improvement
- Color palette cleanup — remove clashing colors
- Hover and active states — makes interface feel alive
- Layout and spacing — proper grid, max-width, consistent padding
- Replace generic components — swap cliche patterns
- Add loading, empty, error states — makes it feel finished
- Polish typography scale — the premium final touch
Rules
- Work with the existing tech stack. Do not migrate frameworks.
- Do not break existing functionality. Test after every change.
- Before importing new libraries, check dependency file first.
- Keep changes reviewable and focused. Small improvements over big rewrites.
Source
Adapted from https://github.com/Leonxlnx/taste-skill (MIT, Copyright (c) 2026 Leonxlnx). Changed for this repo by Lucas Cooper-Bey in 2026: partly rewritten, keeping the "Scan, Diagnose, Fix" opening.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

