Token导航 LogoToken导航

Agent Skill · 研究检索

extract(提取)

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。

extract 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,权限为需要联网;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 25GitHub Stars 14下载 198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:extract(提取)
来源仓库:https://github.com/aladicf/better-web-ui
仓库路径:skills/extract
安装命令:
npx skills add https://github.com/aladicf/better-web-ui --skill extract
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 extract

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。

extract 识别可复用的模式、组件和设计令牌,整合进系统以减少未来决策负担。适用于 Codex、Claude、Cursor、Gemini CLI 中需要建立或完善设计系统的项目。避免捕获所有代码值,而是构建约束性体系以保持界面一致性并防止 token 泛滥。

需先加载 frontend-design 上下文,并参考设计系统对齐指南判断归属层级。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/extract

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 extract;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

extract 怎么安装?

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

extract 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。

extract 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

extract 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。

extract 用的人多吗?

公开数据是累计安装 612 次,近一周安装 25 次,下载 198 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。

extract 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。

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。

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
extract

提取 · 本页

61214需要联网未明确通过

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

Identify reusable patterns, components, and design tokens, then extract and consolidate them into the design system for systematic reuse.

The goal is not to capture every value in the codebase. The goal is to create constrained systems that reduce future design decisions and keep the interface coherent.

Consult the design-system alignment reference for tokens vs components vs patterns, drift, and how to avoid turning inconsistency into token sprawl.

MANDATORY PREPARATION

Users start this workflow with /extract. 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.

Discover

Analyze the target area to identify extraction opportunities:

  1. Find the design system: Locate your design system, component library, or shared UI directory (grep for "design system", "ui", "components", etc.). Understand its structure: CRITICAL: If no design system exists, ask before creating one. Understand the preferred location and structure first.

- Component organization and naming conventions - Design token structure (if any) - Documentation patterns - Import/export conventions

  1. Identify patterns: Look for:

- Repeated components: Similar UI patterns used multiple times (buttons, cards, inputs, etc.) - Hard-coded values: Colors, spacing, typography, shadows that should be tokens - Inconsistent variations: Multiple implementations of the same concept (3 different button styles) - Reusable patterns: Layout patterns, composition patterns, interaction patterns worth systematizing

  • Missing systems: Places where the team is clearly re-solving spacing, type, color, radius, or elevation repeatedly
  1. Assess value: Not everything should be extracted. Consider:

- Is this used 3+ times, or likely to be reused? - Would systematizing this improve consistency? - Is this a general pattern or context-specific? - What's the maintenance cost vs benefit?

Plan Extraction

Create a systematic extraction plan:

  • Components to extract: Which UI elements become reusable components?
  • Tokens to create: Which hard-coded values become design tokens?
  • System boundaries: Which token sets should stay intentionally small so they guide decisions instead of documenting chaos?
  • Variants to support: What variations does each component need?
  • Naming conventions: Component names, token names, prop names that match existing patterns
  • Migration path: How to refactor existing uses to consume the new shared versions

IMPORTANT: Design systems grow incrementally. Extract what's clearly reusable now, not everything that might someday be reusable.

Extraction when a component library already exists

If the project already uses a library such as shadcn/ui, prefer extracting:

  • local wrappers
  • reusable compositions
  • documented patterns

Do not replace upstream primitives with redundant local copies unless the project truly needs a stable customized abstraction.

A good extraction often sits one layer above the library primitive: not another generic Button, but a product-specific action bar, filter panel, settings section, or empty-state pattern that uses the existing primitives consistently.

Extract & Enrich

Build improved, reusable versions:

  • Components: Create well-designed components with:

- Clear props API with sensible defaults - Proper variants for different use cases - Accessibility built in (ARIA, keyboard navigation, focus management) - Documentation and usage examples

  • Design tokens: Create tokens with:

- Clear naming (primitive vs semantic) - Proper hierarchy and organization - Documentation of when to use each token - Constrained scales for spacing, typography, color, radius, and elevation where applicable

Prefer systems like:

  • Spacing: A small scale with meaningful jumps, not every number between 4 and 64
  • Typography: A hand-crafted set of sizes and weights for UI roles
  • Color: Defined ramps instead of ad-hoc lighten/darken variations
  • Elevation: A few shadows with semantic meaning, not endless custom box-shadows
  • Patterns: Document patterns with:

- When to use this pattern - Code examples - Variations and combinations

NEVER:

  • Extract one-off, context-specific implementations without generalization
  • Create components so generic they're useless
  • Extract without considering existing design system conventions
  • Skip proper TypeScript types or prop documentation
  • Create tokens for every single value (tokens should have semantic meaning)
  • Turn inconsistency into a token catalog instead of simplifying it into a system

Migrate

Replace existing uses with the new shared versions:

  • Find all instances: Search for the patterns you've extracted
  • Replace systematically: Update each use to consume the shared version
  • Test thoroughly: Ensure visual and functional parity
  • Delete dead code: Remove the old implementations

Document

Update design system documentation:

  • Add new components to the component library
  • Document token usage and values
  • Add examples and guidelines
  • Update any Storybook or component catalog

Remember: A good design system is a living system. Extract patterns as they emerge, enrich them thoughtfully, and maintain them consistently.

平台分布

Codex

32.46%
按下载量换算64

Claude

31.44%
按下载量换算62

Cursor

17.79%
按下载量换算35

Gemini CLI

9.64%
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

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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