Token导航 LogoToken导航

Agent Skill · 研究检索

normalize(normalize 文档)

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。

normalize 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 50,488。

总安装 612周安装 26GitHub Stars 14下载 214核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:normalize(normalize 文档)
来源仓库:https://github.com/aladicf/better-web-ui
仓库路径:skills/normalize
安装命令:
npx skills add https://github.com/aladicf/better-web-ui --skill normalize
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/aladicf/better-web-ui --skill normalize

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

normalize 将偏离标准的设计还原为系统一致的语言,涵盖间距、色彩、交互等维度。适用于 Codex、Claude、Cursor、Gemini CLI 中需要统一多模块或多团队产出风格的场景。不仅是视觉清理,更是恢复组件对设计系统规则的遵守,避免局部特例破坏整体。

需先加载 frontend-design 上下文,并参考交互设计与系统对齐指南判断处理级别。安装前建议确认权限范围和维护状态,注意是否会触发联网、命令执行或文件读写。

来源仓库内路径:skills/normalize

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/aladicf/better-web-ui --skill normalize;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

normalize 怎么安装?

在终端执行 npx skills add https://github.com/aladicf/better-web-ui --skill normalize。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

normalize 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

normalize 需要什么权限?

权限级别是只读。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。

normalize 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

normalize 用的人多吗?

公开数据是累计安装 612 次,近一周安装 26 次,下载 214 次,GitHub 14 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

normalize 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
normalize

normalize 文档 · 本页

61214只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Analyze and redesign the feature to perfectly match our design system standards, aesthetics, and established patterns.

Normalization is not just visual cleanup. It is restoring the feature to the system so spacing, type, color, interaction, and hierarchy all speak the same language again.

Consult the design-system alignment reference for tokens vs components vs patterns, drift, and when to normalize locally versus escalate to system work. Consult the interaction design reference when normalization includes restoring familiar patterns, improving target sizing, or removing bespoke interaction behavior from standard controls. Consult the legacy modernization reference when the feature lives inside a legacy system, mixed old/new flow, or partial migration where low-risk upgrade strategy matters as much as visual alignment.

MANDATORY PREPARATION

Users start this workflow with /normalize. Once this skill is active, load $frontend-design — it contains design principles, anti-patterns, and the Context Gathering Protocol. Follow that protocol before proceeding — if no design context exists yet, you MUST load $setup first.


Plan

Before making changes, deeply understand the context:

  1. Discover the design system: Search for design system documentation, UI guidelines, component libraries, or style guides (grep for "design system", "ui guide", "style guide", etc.). Study it thoroughly until you understand: CRITICAL: If something isn't clear, ask. Don't guess at design system principles.

- Core design principles and aesthetic direction - Target audience and personas - Component patterns and conventions - Design tokens (colors, typography, spacing)

  1. Analyze the current feature: Assess what works and what doesn't:

- Where does it deviate from design system patterns? - Which inconsistencies are cosmetic vs. functional? - What's the root cause—missing tokens, one-off implementations, or conceptual misalignment? - If the feature is legacy or hybrid, which workflows and dependencies would make a "simple redesign" risky? - Which pain points can be improved safely now without breaking institutional workflow knowledge?

  1. Create a normalization plan: Define specific changes that will align the feature with the design system: IMPORTANT: Great design is effective design. Prioritize UX consistency and usability over visual polish alone. Think through the best possible experience for your use case and personas first. When the surface is legacy, normalization often means making the current experience safer, clearer, and more consistent while a larger migration is still in progress. Do not mistake every legacy problem for a mandate to rewrite the workflow wholesale.

- Which components can be replaced with design system equivalents? - Which styles need to use design tokens instead of hard-coded values? - How can UX patterns match established user flows? - Where have standard interactions drifted away from familiar product conventions without a compelling reason? - Which areas feel off because hierarchy is weak, actions are flattened, or spacing is arbitrary rather than systematic?

Execute

Systematically address all inconsistencies across these dimensions:

  • Typography: Use design system fonts, sizes, weights, and line heights. Replace hard-coded values with typographic tokens or classes.
  • Color & Theme: Apply design system color tokens. Remove one-off color choices that break the palette.
  • Spacing & Layout: Use spacing tokens (margins, padding, gaps). Align with grid systems and layout patterns used elsewhere.
  • Hierarchy: Restore primary, secondary, and tertiary emphasis. A normalized feature should make it obvious what matters first.
  • Components: Replace custom implementations with design system components. Ensure props and variants match established patterns.
  • Motion & Interaction: Match animation timing, easing, and interaction patterns to other features.
  • Conventional UX patterns: Realign forms, tables, filters, dialogs, menus, tabs, and settings to recognizable platform/category conventions unless the custom behavior clearly improves the workflow.
  • Responsive Behavior: Ensure breakpoints and responsive patterns align with design system standards.
  • Accessibility: Verify contrast ratios, focus states, ARIA labels match design system requirements.
  • Target sizing & placement: Restore generous hit areas, whole-row labels where appropriate, and action placement that reduces precision work for common tasks.
  • Progressive Disclosure: Match information hierarchy and complexity management to established patterns.

NEVER:

  • Create new one-off components when design system equivalents exist
  • Hard-code values that should use design tokens
  • Introduce new patterns that diverge from the design system
  • Compromise accessibility for visual consistency
  • Normalize by making everything visually similar while leaving hierarchy unclear

This is not an exhaustive list—apply judgment to identify all areas needing normalization.

Clean Up

After normalization, ensure code quality:

  • Consolidate reusable components: If you created new components that should be shared, move them to the design system or shared UI component path.
  • Remove orphaned code: Delete unused implementations, styles, or files made obsolete by normalization.
  • Verify quality: Lint, type-check, and test according to repository guidelines. Ensure normalization didn't introduce regressions.
  • Ensure DRYness: Look for duplication introduced during refactoring and consolidate.

Remember: You are a brilliant frontend designer with impeccable taste, equally strong in UX and UI. Your attention to detail and eye for end-to-end user experience is world class. Execute with precision and thoroughness.

平台分布

Codex

38.53%
按下载量换算82

Claude

26.97%
按下载量换算58

Cursor

19%
按下载量换算41

Gemini CLI

9.1%
按下载量换算19

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills