Token导航 LogoToken导航

Agent Skill · 前端设计

dashboard-design(仪表板设计)

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。

dashboard-design 是前端设计类 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,按安装量在前端设计类的 10,216 个 Skill 里排第 3,545。

总安装 1,270周安装 54GitHub Stars 3,667下载 445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:dashboard-design(仪表板设计)
来源仓库:https://github.com/mckinsey/vizro
仓库路径:skills/dashboard-design
安装命令:
npx skills add https://github.com/mckinsey/vizro --skill dashboard-design
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/mckinsey/vizro --skill dashboard-design

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

dashboard-design 提供结构化仪表板设计流程:需求理解 → 布局规划 → 可视化选型。每步依赖上一步输出,进度可通过勾选清单跟踪,确保设计完整性。强调用户任务导向,拒绝装饰性元素,优先保证信息传达效率。涉及真实页面改动时,应通过截图或预览检查文本溢出和对齐问题。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/dashboard-design

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/mckinsey/vizro --skill dashboard-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

dashboard-design 怎么安装?

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

dashboard-design 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。

dashboard-design 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。

dashboard-design 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。

dashboard-design 用的人多吗?

公开数据是累计安装 1,270 次,近一周安装 54 次,下载 445 次,GitHub 3,667 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。

dashboard-design 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。
  • 来源仓库有 3,667 星,维护活跃度相对可查。

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。
  • 需要处理前端设计类任务、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。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
dashboard-design

仪表板设计 · 本页

1,2703,667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

Designing Vizro Dashboards

Structured requirements → layout → visualization workflow.

Workflow execution

Run Steps 1–3 in order; each step depends on the prior. Track progress:

Dashboard Development Progress:
- [ ] Step 1: Understand Requirements (define end user, dashboard goals, document decisions)
- [ ] Step 2: Design Layout & Interactions (wireframes, filter placement)
- [ ] Step 3: Select Visualizations (chart types, KPIs; colors only if user asked)

Interaction style: When gathering requirements or making design decisions, ask focused questions and present 2–5 numbered options so the user can choose quickly. Prefer using your client’s built-in multiple-choice or question UI to keep the interaction lightweight and clickable; if that isn’t available, use the same numbered format in plain text

Do not skip steps. Handle partial context as follows:

  • User has data but no requirements → Start at Step 1
  • User has requirements but no data → Ask for data or suggest sample data
  • User has wireframes → Validate Step 1 decisions, then proceed from Step 2
  • User has visual designs/mockups → Validate Steps 1-2 decisions, then proceed from Step 3
  • User asks to "just build it" → Explain value of steps, offer to streamline but not skip, ask for data or suggest sample data

For simple dashboards (single page, less than 5 charts): Steps 1-3 can be abbreviated but not skipped entirely.


Spec Files: Documenting Decisions

IMPORTANT: Each step produces a spec file in the spec/ directory to document reasoning, enable collaboration, and allow resumption in future sessions. Create the spec/ directory at project start.


Step 1: Understand Requirements

Goal: Define WHAT information is presented and WHY it matters.

Key Questions to Discuss

  1. Users: Who are the end users of this dashboard? Per user type: What decisions do they need to make? What task/job do they need to accomplish?
  2. Goals: What is the current problem to solve? What is the goal of this dashboard?
  3. Data: What sources are available? What's the refresh frequency?
  4. Structure: How many pages or views? What's the logical grouping?

Design Principles

  • Limit KPIs: 5–9 primary metrics per page (7 ± 2 rule)
  • Clear hierarchy: Overview → Detail → Granular (max 3 levels)
  • Persona-based: Different users may need different views
  • Decision-focused: Every metric should inform a decision

REQUIRED OUTPUT: spec/1_information_architecture.yaml

Save this file BEFORE proceeding to Step 2:

# spec/1_information_architecture.yaml
dashboard:
  name: [Name]
  purpose: [One sentence goal]
pages:
  - name: [Page Name]
    purpose: [What question does this answer?]
    kpis: [List of 3-5 key metrics]
data_sources:
  - name: [Source Name]
    type: [csv/database/api]
decisions:
  - decision: [What was decided]
    reasoning: [Why this choice was made]

Validation Checklist

Before proceeding to Step 2:

  • Every page has a clear, distinct purpose
  • KPIs are measurable and actionable
  • Data sources are accessible
  • User has confirmed the structure

Detailed guidance: See information_architecture.md; Anti-patterns: See common_mistakes.md section "Step 1: Requirements Mistakes"


Step 2: Design Layout & Interactions

Goal: Define HOW users navigate and explore data.

Vizro Navigation Architecture

Tier 1: Global Navigation
├── Multi-page sidebar (automatic in Vizro)
└── Page selection

Tier 2: Page-level Controls
└── Filters/Parameters in left collapsible sidebar

Tier 3: Component-level
├── Container-specific filters/parameters
├── Cross-filter, cross-highlight interactions
└── Export actions

Layout Strategy

Load the designing-vizro-layouts skill for grid system, component sizing, filter placement, and selector rules. Use the wireframe templates when building ASCII wireframes for user approval.

REQUIRED OUTPUT: spec/2_interaction_ux.yaml

Save this file BEFORE proceeding to Step 3:

# spec/2_interaction_ux.yaml
pages:
  - name: [Must match Step 1]
    layout_type: grid  # or flex
    grid_columns: 12
    grid_pattern: [[0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3]] # Component placement

    containers:
      - name: [Container Name]
        has_own_filters: true/false
    filter_placement:
      page_level: [columns with selector types]
      container_level: [columns with selector types]
wireframe: |
  [ASCII wireframe for ALL pages and tab views]
decisions:
  - decision: [What was decided]
    reasoning: [Why this choice was made]

Validation Checklist

Before proceeding to Step 3:

  • Layout follows Vizro constraints
  • Filter placement is intentional and documented
  • User has been presented ASCII wireframes for every page and approved them

Anti-patterns: See common_mistakes.md section "Step 2: Layout Mistakes"


Step 3: Select Visualizations

Goal: Choose appropriate chart types and establish visual consistency.

Chart Types, Colors & KPIs

Load the selecting-vizro-charts skill for chart selection, color strategy, anti-patterns, and KPI card rules. Key design decisions:

  • Match chart type to data question (bar for comparison, line for trends, pie only for 2–5 slices)
  • Colors: Do NOT include color_decisions in the spec. Vizro assigns palettes automatically. Only include if the user explicitly requested custom colors in their message.
  • Use built-in kpi_card / kpi_card_reference; never rebuild as custom charts

REQUIRED OUTPUT: spec/3_visual_design.yaml

Save this file BEFORE proceeding to implementation (dashboard-build skill).

# spec/3_visual_design.yaml
visualizations:
  - name: [Chart Name]
    type: [bar/line/scatter/etc]
    needs_custom_implementation: true/false
    reason: [if custom: has_reference_line/needs_data_processing/etc]

# DO NOT include color_decisions unless the user explicitly asked for custom colors in their message.

kpi_cards:
  - name: [KPI Name]
    value_column: [column]
    format: [e.g., '${value:,.0f}']
    has_reference: true/false

decisions:
  - decision: [What was decided]
    reasoning: [Why this choice was made]

Validation Checklist

Before proceeding to implementation (dashboard-build skill):

  • Chart types match data types (no pie charts for time series)
  • No anti-patterns used
  • Custom chart needs are identified
  • color_decisions is absent unless the user explicitly requested custom colors

Anti-patterns: See common_mistakes.md section "Step 3: Visualization Mistakes"

Reference Files

ReferenceWhen to Load
information_architecture.mdStep 1: Deep dive on requirements
designing-vizro-layouts skillStep 2: Grid system, component sizing, filters
wireframe_templates.mdStep 2: Wireframe templates and interaction labels
selecting-vizro-charts skillStep 3: Chart types, anti-patterns
common_mistakes.mdAll steps: Anti-patterns to avoid

平台分布

Codex

32.73%
按下载量换算146

Claude

29.7%
按下载量换算132

Cursor

19.81%
按下载量换算88

Gemini CLI

8.86%
按下载量换算39

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