What is ui-ux-polish?

A workflow for repeatedly reviewing and improving a web application's visual design, usability, accessibility, and responsive layout.

It is for auditing and polishing web interfaces on desktop and mobile, including spacing, typography, contrast, interaction states, and dark mode.

It turns broad requests to make an interface look or work better into focused changes that can be checked for regressions.

ui-ux-polish — Skill for Claude Code by JuanMarchetto/agent-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add JuanMarchetto/agent-skills --skill ui-ux-polish

Clone the repo

git clone --depth 1 https://github.com/JuanMarchetto/agent-skills

Made for: Claude Code.

Or install ui-ux-polish, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/ui-ux-polish/github.svg)](https://agentmods.dev/skills/juanmarchetto/agent-skills/ui-ux-polish)

Your own site

<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/ui-ux-polish"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/ui-ux-polish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/ui-ux-polish"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/ui-ux-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 700 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00065	$0.00700
Opus 5.5	$0.00026	$0.00280
Sonnet 5.5	$0.00013	$0.00140
Haiku 4.5	$0.00006	$0.00070

Measured 2mo ago against content hash db31c409616f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui-ux-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ui-ux-polish/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI/UX Polish

Iterative polishing workflow that systematically improves web application interfaces toward production quality.

Workflow

Step 1: Audit Current State

Read the application's main pages/components. For each, note:

Spacing inconsistencies (not on 8px grid)
Typography issues (too many sizes/weights, poor hierarchy)
Color contrast violations (check against WCAG 4.5:1 for text)
Missing states (hover, focus, loading, error, empty)
Mobile vs desktop issues

Step 2: Prioritize Improvements

Rank findings by impact:

Accessibility violations (contrast, touch targets) — fix first
Spacing/alignment inconsistencies — high visual impact
Missing interaction states — hover, focus, pressed
Typography hierarchy — size and weight cleanup
Animation/transition smoothness
Dark mode consistency

Step 3: Apply Changes

For each improvement:

Make the specific code change
Explain what changed and why
Consider both desktop and mobile separately

Step 4: Verify

After each round, check:

No regressions introduced
Changes work on both desktop and mobile
Accessibility maintained or improved

Step 5: Iterate

Repeat Steps 1-4. Each pass finds smaller issues. Stop when changes become minimal (typically 3-5 passes for significant improvement).

Quality Targets

All text: 4.5:1 contrast ratio minimum
All spacing: divisible by 4 or 8
All interactive elements: visible focus state
All buttons: 44px minimum touch target on mobile
Typography: max 3 font sizes, 2 weights
Animations: 200-300ms duration, ease-out curve

Example Output

Pass 1 (12 changes):
- Fixed 4 contrast violations in sidebar text
- Aligned card padding to 8px grid (was 13px -> 16px)
- Added hover states to 3 buttons missing them
- Increased mobile CTA touch target from 36px to 48px

Pass 2 (7 changes):
- Reduced font sizes from 6 to 3 (unified scale)
- Added loading skeleton to data table
- Smoothed page transition (added 200ms ease-out)

Pass 3 (3 changes):
- Fine-tuned shadow consistency across cards
- Added focus-visible outlines for keyboard nav
- Aligned icon sizes to consistent 20px

Quality Score: 8.5/10 (up from 5.5/10)

Read the full file on GitHub · 82 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 82 lines · 65 tokens per session scan A db31c409616f

Subscribe to this mod's changes

ui-ux-polish is a skill published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 65 tokens to every session and 700 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

CSS and styling Claude Code Design and UX Evaluation Frontend ai-agents ai-tools automation browser-automation

ui-ux-polish next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ui-ux-polishJuanMarchetto/agent-skills	Skill	5	7mo ago	MIT	A	65	Claude Code
omh-visual-qarlaope/oh-my-hermes	Skill	5.4k	today	MIT	A	70	Claude Code, Codex
design-craftWrongStack/WrongStack	Skill	409	yesterday	MIT	A	98	Claude Code
design-critiqueWrongStack/WrongStack	Skill	409	yesterday	MIT	A	95	Claude Code, Codex
color-palette-generatorAlpacaLabsLLC/skills-for-architects	Skill	408	yesterday	MIT	A	41	Claude Code
frontend-compositionjuspay/xyne-spaces	Skill	826	yesterday	Apache-2.0	A	26	Claude Code, Codex
motion-interactionjuspay/xyne-spaces	Skill	826	yesterday	Apache-2.0	A	28	Claude Code, Codex