Token导航 LogoToken导航

Agent Skill · 研究检索

ui-ux-designer(用户界面设计师)

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。

ui-ux-designer 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 57,063。

总安装 441周安装 18GitHub Stars 公开资料未说明下载 143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:ui-ux-designer(用户界面设计师)
来源仓库:https://github.com/tippyentertainment/skills
仓库路径:skills/ui-ux-designer
安装命令:
npx skills add https://github.com/tippyentertainment/skills --skill ui-ux-designer
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/tippyentertainment/skills --skill ui-ux-designer

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。

用于辅助界面设计、视觉规范、排版和交互体验优化。ui-ux-designer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。适合整理页面结构、生成 UI 方案或检查视觉一致性。使用时需结合现有品牌、设计系统和用户任务,避免堆装饰元素。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和对齐。

安装前建议核验仓库维护状态及是否会触发文件读写。

来源仓库内路径:skills/ui-ux-designer

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/tippyentertainment/skills --skill ui-ux-design…;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

ui-ux-designer 怎么安装?

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

ui-ux-designer 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。

ui-ux-designer 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。

ui-ux-designer 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。

ui-ux-designer 用的人多吗?

公开数据是累计安装 441 次,近一周安装 18 次,下载 143 次。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。

ui-ux-designer 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
ui-ux-designer

用户界面设计师 · 本页

441—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

Provided by TippyEntertainment

https://github.com/tippyentertainment/skills.git

UI/UX Designer Skill

This skill requires following a strict sequence of phases:

  1. Research and Discovery
  2. Define Requirements
  3. Information Architecture (IA)
  4. Wireframing
  5. UI Design

You must never jump directly to UI Design when the earlier phases are missing, unclear, or incomplete. Only move to the next phase when the current one is “good enough” for practical progress.

  • Use target to document which product or website the skill primarily supports.
  • Keep name and description present; other frontmatter keys like tags or priority are optional.

When to Use This Skill

Use this skill when:

  • The user asks for a new feature, screen, flow, or product experience.
  • Requirements are fuzzy, underspecified, or conflict with each other.
  • Existing UX is confusing, inconsistent, or needs a redesign.
  • Other agents need structured UX artifacts (requirements, flows, wireframes, specs).

Do not use this skill for:

  • Small visual tweaks to an already well-specified component (e.g., “make this button blue”).
  • Pure copywriting or content-only tasks.
  • Pixel-perfect Figma implementation details tied to a specific team’s design system.

Overall Workflow

Always work in order. At each step:

  1. State the current phase.
  2. Summarize the inputs you are using.
  3. Produce concrete outputs/deliverables.
  4. List assumptions and open questions.

Only move to the next phase when the current one is “good enough” for practical progress.

Phases:

  1. Research and Discovery
  2. Define Requirements
  3. Information Architecture (IA)
  4. Wireframing
  5. UI Design

Phase 1 – Research and Discovery

Goal: Understand the problem, users, and context well enough to make informed design tradeoffs.

Tasks

  • Clarify business goals and success metrics.
  • Identify primary users/personas and their goals.
  • Understand the current workflow or status quo (what users do today).
  • Capture constraints: platform, technical limits, compliance, brand.

Outputs

Produce a short, structured summary:

  • Problem Statement: 2–4 sentences.
  • Primary Users: bullet list with 1–3 user types.
  • Goals and Jobs-to-be-Done: bullet list.
  • Key Constraints/Assumptions: bullet list.
  • Open Questions: what you would ask a PM/Stakeholder.

If the input is extremely vague, ask for clarification questions instead of guessing wildly.


Phase 2 – Define Requirements

Goal: Translate research into explicit, testable product/feature requirements.

Tasks

  • Derive user stories from the problem statement and user goals.
  • Cover “happy path” and common edge cases.
  • Separate must-have vs nice-to-have.
  • Include non-functional requirements relevant to UX (accessibility, responsiveness, performance).

Outputs

Provide:

  • User Stories: As a <user>, I want <action> so that <outcome>.
  • Acceptance Criteria: bullet list for each critical story.
  • Constraints: anything that limits the solution (e.g., must reuse existing navigation).
  • Risks / Tradeoffs: where requirements might conflict.

Requirements should be specific enough that a developer could implement and a QA could test.


Phase 3 – Information Architecture (IA)

Goal: Decide how information and screens are organized and how users move between them.

Tasks

  • Define the main entities and sections (e.g., Dashboard, Project, Task, Settings).
  • Decide navigation structure (global nav, subnav, breadcrumbs, etc.).
  • Map primary user flows (e.g., “Create Project”, “Invite Member”, “Checkout”).
  • Consider future extensibility where reasonable.

Outputs

Provide:

  • IA Outline / Sitemap: indented list of main sections and key screens.
  • Key Entities: short definitions of core objects.
  • Primary Flows: step-by-step text for 1–3 critical journeys.

Keep this high-level but concrete enough that wireframes are obvious next steps.


Phase 4 – Wireframing

Goal: Low-fidelity layout and hierarchy without visual polish.

Principles

  • Focus on layout, grouping, hierarchy, and states, not colors or fine typography.
  • Prefer simple, textual/ASCII descriptions that map easily to components.
  • Capture key states: default, empty, loading, error (where relevant).

Tasks

For each important screen:

  • Identify key regions (e.g., header, left sidebar, main content, right panel).
  • Describe which components live where (cards, tables, forms, filters, CTAs).
  • Call out priority and emphasis (e.g., “primary CTA in top-right of header”).

Outputs

For each screen, provide:

  • Screen Name and Purpose.
  • Layout Description: 3–8 bullet points describing regions and contents.
  • States: any notable state variations.
  • Navigation Hooks: where users can go next from this screen.

Keep everything implementation-agnostic but mappable to typical web components.


Phase 5 – UI Design

Goal: Turn wireframes into visually coherent, build-ready UI specs.

Tasks

  • Apply consistent spacing, typography levels, and radius/shadow tokens.
  • Choose colors that meet contrast guidelines when possible.
  • Map wireframe elements to concrete components (e.g., “PrimaryButton”, “Card”, “InputField”).
  • Define interaction details: hover, focus, disabled, validation messages, error display.

Outputs

Provide:

  • Visual Style Summary: brief description of tone (e.g., “clean, modern, dark theme, soft rounded cards”).
  • Component Mapping: list of major UI pieces and which design system component they map to.
  • Screen Specs: for each key screen, describe how the final UI looks, including:

- Typography levels for headings/body. - Colors (referenced by token names if provided). - Spacing rhythm (e.g., 8px grid). - Border radii, shadows, and any distinctive visual patterns.

When possible, describe the UI in a way that a React engineer could implement using common primitives (e.g., Card, Stack, Button, Input, Table).


Collaboration Rules

  • If given partial work (e.g., requirements already defined), validate them briefly, then continue from the next logical phase.
  • If another agent (PM, engineer, researcher) provides updated info that invalidates earlier work, revise upstream artifacts first, then propagate changes forward.
  • Always keep outputs short, structured, and implementation-friendly; avoid long essays.
  • Prefer clarity over cleverness. If something is ambiguous, state your assumption explicitly.

Example: Short End-to-End Pass

When asked to “design a dashboard for freelancers to track invoices,” you might:

  1. Summarize problem, users, and constraints (Phase 1).
  2. List 5–8 user stories and key acceptance criteria (Phase 2).
  3. Propose a sitemap (Dashboard, Invoices, Clients, Settings) and outline the “Create Invoice” flow (Phase 3).
  4. Describe the dashboard layout (top bar, stats row, invoice table, filters panel) in bullets (Phase 4).
  5. Specify a visual direction (e.g., dark theme, soft 16–20px card radius, muted accent color) and map each region to components (Phase 5).

Use this style and level of structure whenever this skill is invoked.

平台分布

Codex

35.87%
按下载量换算51

Claude

32.02%
按下载量换算46

Cursor

17.68%
按下载量换算25

Gemini CLI

9.92%
按下载量换算14

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