ui-polish
Skill1 starsChanged 15 days agoMITView on GitHub
Use when a UI works but looks generic or rough — fast visual design, layout, typography, states and accessibility fixes that make a demo look professional.
18 other projects use a version of this.
Adopted by
Most recently taken up by
- agentes-chat/agentes-chattheir own version, first seen Nov 15, 2026
- Markssuave/Markssuave-Agent-skillstheir own version, first seen Nov 8, 2026
- trina-app/trina-axtheir own version, first seen Nov 8, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- cindyeme/ui-polishtheir own version, first seen Nov 1, 2026
- aictrl-dev/skillstheir own version, first seen Oct 22, 2026
Used with
Projects with it also use design.
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.
Microsoft AzureSkilldesign
Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.
Also in 3 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- agentes-chat/agentes-chat★ 1.5ksame name
- trina-app/trina-ax★ 117same name
- felvieira/claude-skills-fv★ 28same name
- icons8/agent-skills★ 12same name
- The-Utopia-Studio/skills★ 6same name
- aictrl-dev/skills★ 4same name
- AhmedMerza/agent-skills★ 2same name
- AhmedMerza/claude-skills★ 2same name
- cindyeme/ui-polish★ 2same name
- jukrap/ai-agent-playbook★ 2same name
8 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 repository58 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/vercel-composition-patterns/AGENTS.mdAGENTS.md
- .agents/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- .claude/skills/vercel-composition-patterns/AGENTS.mdAGENTS.md
- .claude/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ai-in-the-productSkill
- backend-apiSkill
- database-quickSkill
- data-ml-quickstartSkill
- debug-fastSkill
- demo-and-pitchSkill
- deploy-fastSkill
- deploy-to-vercelSkill
- docker-build-strategiesSkill
- docker-compose-patternsSkill
- docker-destructive-guardrailsSkill
- docker-project-foundationsSkill
- find-skillsSkill
- frontend-nextjs-vercelSkill
- git-githubSkill
- kickoffSkill
- pitch-deckSkill
- rapid-prototypeSkill
- repo-polishSkill
- security-basicsSkill
- smoke-testingSkill
- team-syncSkill
- vercel-composition-patternsSkill
- vercel-react-best-practicesSkill
- verification-before-doneSkill
- ai-in-the-productSkill
- backend-apiSkill
- database-quickSkill
- data-ml-quickstartSkill
- debug-fastSkill
- demo-and-pitchSkill
- deploy-fastSkill
- deploy-to-vercelSkill
- docker-build-strategiesSkill
- docker-compose-patternsSkill
- docker-destructive-guardrailsSkill
- docker-project-foundationsSkill
- find-skillsSkill
- frontend-nextjs-vercelSkill
- git-githubSkill
- kickoffSkill
- pitch-deckSkill
- rapid-prototypeSkill
- repo-polishSkill
- security-basicsSkill
- smoke-testingSkill
- team-syncSkill
- ui-polishSkill
- vercel-composition-patternsSkill
- vercel-react-best-practicesSkill
- verification-before-doneSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Responsive: check at 375 px and 1280 px.
“Common” is measured: kept by at least 6 in 10 of the 15 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
UI polish (demo-grade in 30 minutes)
- Pick a direction in one line (e.g. "calm, clinical, lots of whitespace" or "bold, dark, data-dense") and apply it everywhere. Avoid default-template look.
- Tokens, not magic numbers: define colors, radius, spacing scale, font sizes once (Tailwind theme / CSS variables). One accent color + neutrals.
- Typography: one font pair max; clear hierarchy (title ≥ 2× body); line length 50–75 chars; body ≥ 16 px.
- Layout: consistent spacing (4/8 px scale), align to a grid, generous whitespace, one primary action per screen.
- States for everything: loading (skeleton/spinner), empty (explain + CTA), error (human message + retry), success. Disabled while pending.
- Feedback: hover/focus/active styles, subtle transitions (150–200 ms).
cursor: pointeron clickable things. - Accessibility basics: contrast ≥ 4.5:1, visible focus ring, labels on inputs,
alttext, semantic elements (button, not clickablediv), keyboard reachable. - Responsive: check at 375 px and 1280 px; judges may look on a phone.
- Real content: realistic data, no lorem ipsum, no "Test 123" in screenshots.
- Check it: open the page, look at it. Take a screenshot at both sizes.
Upstream references: Vercel Web Interface Guidelines, Anthropic frontend-design skill (github.com/anthropics/skills) — vet before installing.
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.

