/build-dashboard - Build Interactive Dashboards

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Build a self-contained interactive HTML dashboard with charts, filters, tables, and professional styling. Opens directly in a browser -- no server or dependencies required.

Usage

/build-dashboard <description of dashboard> [data source]

Workflow

1. Understand the Dashboard Requirements

Determine:

• Purpose: Executive overview, operational monitoring, deep-dive analysis, team reporting
• Audience: Who will use this dashboard?
• Key metrics: What numbers matter most?
• Dimensions: What should users be able to filter or slice by?
• Data source: Live query, pasted data, CSV file, or sample data

2. Gather the Data

If data warehouse is connected:

1. Query the necessary data
2. Embed the results as JSON within the HTML file

If data is pasted or uploaded:

1. Parse and clean the data
2. Embed as JSON in the dashboard

If working from a description without data:

1. Create a realistic sample dataset matching the described schema
2. Note in the dashboard that it uses sample data
3. Provide instructions for swapping in real data

3. Design the Dashboard Layout

Follow a standard dashboard layout pattern:

┌──────────────────────────────────────────────────┐
│  Dashboard Title                    [Filters ▼]  │
├────────────┬────────────┬────────────┬───────────┤
│  KPI Card  │  KPI Card  │  KPI Card  │ KPI Card  │
├────────────┴────────────┼────────────┴───────────┤
│                         │                        │
│    Primary Chart        │   Secondary Chart      │
│    (largest area)       │                        │
│                         │                        │
├─────────────────────────┴────────────────────────┤
│                                                  │
│    Detail Table (sortable, scrollable)           │
│                                                  │
└──────────────────────────────────────────────────┘

Adapt the layout to the content:

• 2-4 KPI cards at the top for headline numbers
• 1-3 charts in the middle section for trends and breakdowns
• Optional detail table at the bottom for drill-down data
• Filters in the header or sidebar depending on complexity

4. Build the HTML Dashboard

Generate a single self-contained HTML file using the base template below. The file includes:

Structure (HTML):

• Semantic HTML5 layout
• Responsive grid using CSS Grid or Flexbox
• Filter controls (dropdowns, date pickers, toggles)
• KPI cards with values and labels
• Chart containers
• Data table with sortable headers

Styling (CSS):

• Professional color scheme (clean whites, grays, with accent colors for data)
• Card-based layout with subtle shadows
• Consistent typography (system fonts for fast loading)
• Responsive design that works on different screen sizes
• Print-friendly styles

Interactivity (JavaScript):

• Chart.js for interactive charts (included via CDN)
• Filter dropdowns that update all charts and tables simultaneously
• Sortable table columns
• Hover tooltips on charts
• Number formatting (commas, currency, percentages)

Data (embedded JSON):

• All data embedded directly in the HTML as JavaScript variables
• No external data fetches required
• Dashboard works completely offline

5. Implement Chart Types

Use Chart.js for all charts. Common dashboard chart patterns:

• Line chart: Time series trends
• Bar chart: Category comparisons
• Doughnut chart: Composition (when <6 categories)
• Stacked bar: Composition over time
• Mixed (bar + line): Volume with rate overlay

Use the Chart.js integration patterns below for each chart type.

6. Add Interactivity

Use the filter and interactivity implementation patterns below for dropdown filters, date range filters, combined filter logic, sortable tables, and chart updates.

7. Save and Open

1. Save the dashboard as an HTML file with a descriptive name (e.g., sales_dashboard.html)
2. Open it in the user's default browser
3. Confirm it renders correctly
4. Provide instructions for updating data or customizing

Base Template

Every dashboard follows this structure:

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Dashboard Title</title>
    <script src="https://cdn.jsdelivr.net/npm/[email protected]" integrity="sha384-jb8JQMbMoBUzgWatfe6COACi2ljcDdZQ2OxczGA3bGNeWe+6DChMTBJemed7ZnvJ" crossorigin="anonymous"></script>
    <script src="https://cdn.jsdelivr.net/npm/[email protected]" integrity="sha384-cVMg8E3QFwTvGCDuK+ET4PD341jF3W8nO1auiXfuZNQkzbUUiBGLsIQUE+b1mxws" crossorigin="anonymous"></script>
    <style>
        /* Dashboard styles go here */
    </style>
</head>
<body>
    <div class="dashboard-container">
        <header class="dashboard-header">
            <h1>Dashboard Title</h1>
            <div class="filters">
                <!-- Filter controls -->
            </div>
        </header>

        <section class="kpi-row">
            <!-- KPI cards -->
        </section>

        <section class="chart-row">
            <!-- Chart containers -->
        </section>

        <section class="table-section">
            <!-- Data table -->
        </section>

        <footer class="dashboard-footer">
            <span>Data as of: <span id="data-date"></span></span>
        </footer>
    </div>

    <script>
        // Embedded data
        const DATA = [];

        // Dashboard logic
        class Dashboard {
            constructor(data) {
                this.rawData = data;
                this.filteredData = data;
                this.charts = {};
                this.init();
            }

            init() {
                this.setupFilters();
                this.renderKPIs();
                this.renderCharts();
                this.renderTable();
            }

            applyFilters() {
                // Filter logic
                this.
how to use build-dashboard
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use build-dashboard on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add build-dashboard
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/anthropics/knowledge-work-plugins --skill build-dashboardcopy
The skills CLI fetches build-dashboard from GitHub repository anthropics/knowledge-work-plugins and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/build-dashboard
Reload or restart Cursor to activate build-dashboard. Access the skill through slash commands (e.g., /build-dashboard) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?