Token导航 LogoToken导航TokenDH.com
前端设计只读github未标认证来源可访问许可证需确认审计通过

ui-design-iterationUI 设计迭代

Agent Skill

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

总安装

353

周安装

15

GitHub Stars

5

下载量

124
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ui-design-iteration(UI 设计迭代)
来源仓库:https://github.com/ozten/skills
仓库路径:skills/ui-design-iteration
安装命令:
npx skills add https://github.com/ozten/skills --skill ui-design-iteration
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/ozten/skills --skill ui-design-iteration

简介

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。

  • 适合根据产品场景整理页面结构、生成 UI 方案或检查视觉一致性。
  • 使用时需结合品牌和设计系统,避免堆砌装饰元素;涉及页面改动应通过截图或浏览器预览检查表现。
  • 安装方式:通过 npx skills add 命令从指定 GitHub 仓库添加。
  • 注意:需确认宿主环境支持 Codex、Claude、Cursor 或 Gemini CLI。

SKILL.md

UI Design Iteration

Transform functional-but-flat interfaces into scannable, actionable, accessible designs.

Core Principles

1. Align labels with user intent

  • Page titles and nav labels should reflect the user's job, not internal terminology
  • Group navigation by intent (Create, Review, Analyze, Manage)
  • Ensure naming consistency across title, nav, tabs, and empty states

2. Make primary actions unmistakable

  • One primary CTA per screen with consistent placement
  • Provide contextual "next step" affordances near where attention already is
  • Secondary actions visible but subordinate; tertiary actions in overflow menus

3. Improve scannability through hierarchy

  • Strengthen typographic hierarchy: title → section headers → row primary → metadata
  • Consistent row heights, spacing, and alignment
  • Use whitespace and dividers to encode structure, not decoration

4. Make state explicit everywhere

  • Represent modes with tabs/segmented controls
  • Selection needs multiple cues: indicator + weight + background (not color alone)
  • Summarize active automation/filters where relevant

5. Systematize the visual design

  • Standardize spacing, typography, and color via tokens
  • Use accent color for priority and state, not decoration
  • Build reusable components rather than one-off styles

Iteration Playbook

A. Reframe the page

Define the job statement: "User comes here to ____."

  • Update page title and nav selection to reflect that job
  • Remove ambiguous or overlapping labels

B. Establish action hierarchy

Identify primary (most common), secondary (common but not main path), and tertiary (rare, collapse to overflow) actions.

  • Only one primary button style per screen
  • Place contextual next-step affordance near the data surface

C. Chunk dense controls

Replace walls of toggles/fields with:

  • Group headers + short descriptions
  • Progressive disclosure for advanced settings
  • Aligned labels and descriptions for quick scanning

D. Increase scan speed for data surfaces

  • Consistent columns and alignment
  • Primary value bold, metadata muted
  • Row actions right-aligned with overflow
  • Truncation that preserves meaning (with tooltip/detail access)

E. Clarify modes and location

  • Top-level modes via tabs/segmented control
  • Active filters shown as chips with clear remove affordance
  • Context line under headers showing scope when needed

Quick References

Accessibility requirements: See CHECKLIST.md Reusable component patterns: See COMPONENTS.md

Output Format

When completing an iteration, produce:

  1. Design intent — 1-2 sentences on what job is supported and what changed
  2. Key UX changes — Bulleted, mapped to the principles above
  3. Component updates — What was created or standardized
  4. A11y verification — Contrast, focus, labels, targets, truncation
  5. Known risks — Only if materially impacting usability

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.33%
按下载量换算45

Claude

30.06%
按下载量换算37

Cursor

17.41%
按下载量换算22

Gemini CLI

8.91%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills