UI Polish Pass Agent Skill

Conducts comprehensive pre-release quality audits across accessibility, visual hierarchy, interaction states, and AI design tropes.

Context cost
1.1k tokensestimated from the bundle, loaded when it triggers
Bundle
2 files · 4.5 kBtext throughout, nothing executable
Licence
MIT. See LICENSE.txt for full terms.the author’s own terms
Last change
—v1.0.0
Servers it uses
Noneruns standalone

What it does

在设计向客户、团队或利益相关者展示或发布前执行最终质量门禁,综合检查无障碍、AI 模板味、视觉层级与节奏、交互状态,并对发现去重和分级。用户提出“最终润色”“发布前检查”“Polish Pass”“能不能交付”时使用;结构仍在大改或内容严重缺失时应先完成设计,不要过早抛光。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

accessibilitydesign
Filed under

Design & Media

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md3.4 kB · preview
--- name: polish-pass license: MIT. See LICENSE.txt for full terms. metadata: author: Onevium version: "1.0.0" ---
10# 最终润色门禁
11
12这是四类专项审查的总入口。重点是发现会阻碍交付的问题,并让用户知道什么已验证、什么仍需决策,而不是产生最长的问题清单。
13
14## 1. 确认是否适合进入润色
15
16读取最终交付物和相关样式,确认媒介、使用场景、品牌和用户约束。若布局仍破损、主要区块缺失或占位内容仍在重写,说明现在抛光的浪费,并先完成结构。
17
18确认操作模式:只要求审查时不要修改;明确要求“修好并交付”时再实施修复。
19
20## 2. 执行四个维度
21
22可直接应用以下量表;运行环境支持并且并行不会增加风险时,也可以分别加载同库中的专项 Skill,再统一汇总。
23
241. **无障碍**:对比度、颜色信号、语义、标签、键盘、焦点、动效、表单和点击目标。
252. **AI 模板味**:无依据渐变、装饰 emoji、默认卡片、临时插画、静默默认字体、散乱 token 和不合场景的暖色编辑风。
263. **层级与节奏**:主要与次要信息、5 秒扫描、间距和字号尺度、重复一致性、策略性变化、调色板和对齐。
274. **交互状态**:适用的 default、hover、active、disabled、focus、loading,以及过渡、成功、失败和当前状态反馈。
28
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md89 words
Files2
LicenceMIT. See LICENSE.txt for full terms.
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈70
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,055
on trigger
The instruction body and 1 supporting file, read only when the skill fires.
0.56%
of a 200k window
Ten skills this size would take about 6% of the window before you open a file.
050k100k150k200k context window

1.1k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Small enough to keep loaded permanently without thinking about it.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

2 files, 4.5 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md3.4 kB
  • LICENSE.txt1.1 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 2 files you can review in full before installing. The licence the author declares covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# UI Polish Pass · 1.1k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/ui-polish-pass/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/ui-polish-pass" ] && { [ ! -e .claude/skills/ui-polish-pass ] || { mv .claude/skills/ui-polish-pass "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/ui-polish-pass" .claude/skills/ && echo "Installed .claude/skills/ui-polish-pass"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add onevium/ui-polish-pass

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/ui-polish-pass/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/ui-polish-pass/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/ui-polish-pass" ] && { [ ! -e ~/.claude/skills/ui-polish-pass ] || { mv ~/.claude/skills/ui-polish-pass "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/ui-polish-pass" ~/.claude/skills/ && echo "Installed ~/.claude/skills/ui-polish-pass" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/ui-polish-pass/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as polish-pass in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, ui-polish-pass.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0.0
Publishedno release date on file
PriceFree
Referenceonevium/ui-polish-pass

Versions

v1.0.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill