C

claude-d3js-skill

Verified

by sickn33 · Updated Apr 16, 2026

claude-opus-4-6
8.8Kin9.1Kout
$0.434m 47s

This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.

d3javascriptdata-visualizationfrontendsvg

See It In Action

1 turns·claude
The project codebase is in your current working directory. Explore the files to understand the code before making changes. need a browser-ready d3 chart for this afternoon's ops review showing monthly incident counts by severity, with tooltips, legend toggles, and responsive resize

I'll explore the project structure first to understand what we're working with, then create a browser-ready D3 chart for your ops review.

Perfect! I can see the project structure. The baseline is already set up, but I need to complete the three TODOs:

  1. Add tooltips on bar hover
  2. Add legend toggle functionality
  3. Add responsive resize with ResizeObserver

Let me update the chart.js file to add all the missing interactive features:

Now update renderChart to filter by active severities and add tooltip interactions:

Now let me check the styles.css to ensure tooltip styling is in place:

I need to add the .visible class for the tooltip and the .swatch style, and update the legend button styling to support the active/filled state:

Let me verify the final state of both files:

Everything looks good. Here's what I wired up in chart.js and styles.css:

  • Tooltips — hover (or keyboard focus) any bar to see month, severity color swatch, and incident count. The tooltip follows the pointer and flips sides near the container edge.
  • Legend toggles — clicking a severity chip toggles it off/on (filled = active, outline = hidden). At least one severity always stays visible. The bars and y-axis rescale accordingly.
  • Responsive resize — a ResizeObserver on the chart container triggers a full redraw, so the chart adapts to any window/container size change.
  • Bonus — added subtle horizontal grid lines, rounded bar corners, and ARIA labels on each bar for accessibility.

To preview it:

python3 -m http.server 4173

Then open http://localhost:4173. Ready for the ops review.

Claude Sonnet 4.6

External Tools

ToolType
nodebinary
npmbinary

Permissions

ScopeDescription
filesystem:read
filesystem:write
process:spawn

SKILL.md

D3.js Visualisation

Overview

This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js. D3.js (Data-Driven Documents) excels at binding data to DOM elements and applying data-driven transformations to create custom, publication-quality visualisations with precise control over every visual element. The techniques work across any JavaScript environment, including vanilla JavaScript, React, Vue, Svelte, and other frameworks.

When to use d3.js

Use d3.js for:

  • Custom visualisations requiring unique visual encodings or layouts
  • Interactive explorations with complex pan, zoom, or brush behaviours
  • Network/graph visualisations (force-directed layouts, tree diagrams, hierarchies, chord diagrams)
  • Geographic visualisations with custom projections
  • Visualisations requiring smooth, choreographed transitions
  • Publication-quality graphics with fine-grained styling control
  • Novel chart types not available in standard libraries

Consider alternatives for:

  • 3D visualisations - use Three.js instead

Core workflow

1. Set up d3.js

Import d3 at the top of your script:

import * as d3 from 'd3';

Or use the CDN version (7.x):

<script src="https://d3js.org/d3.v7.min.js"></script>

All modules (scales, axes, shapes, transitions, etc.) are accessible through the d3 namespace.

2. Choose the integration pattern

Pattern A: Direct DOM manipulation (recommended for most cases) Use d3 to select DOM elements and manipulate them imperatively. This works in any JavaScript environment:

function drawChart(data) {
  if (!data || data.length === 0) return;

  const svg = d3.select('#chart'); // Select by ID, class, or DOM element

  // Clear previous content
  svg.selectAll("*").remove();

  // Set up dimensions
  const width = 800;
  const height = 400;
  const margin = { top: 20, right: 30, bottom: 40, left: 50 };

  // Create scales, axes, and draw visualisation
  // ... d3 code here ...
}

// Call when data changes
drawChart(myData);

Pattern B: Declarative rendering (for frameworks with templating) Use d3 for data calculations (scales, layouts) but render elements via your framework:

function getChartElements(data) {
  const xScale = d3.scaleLinear()
    .domain([0, d3.max(data, d => d.value)])
    .range([0, 400]);

  return data.map((d, i) => ({
    x: 50,
    y: i * 30,
    width: xScale(d.value),
    height: 25
  }));
}

// In React: {getChartElements(data).map((d, i) => <rect key={i} {...d} fill="steelblue" />)}
// In Vue: v-for directive over the returned array
// In vanilla JS: Create elements manually from the returned data

Use Pattern A for complex visualisations with transitions, interactions, or when leveraging d3's full capabilities. Use Pattern B for simpler visualisations or when your framework prefers declarative rendering.

3. Structure the visualisation code

Follow this standard structure in your drawing function:

function drawVisualization(data) {
  if (!data || data.length === 0) return;

  const svg = d3.select('#chart'); // Or pass a selector/element
  svg.selectAll("*").remove(); // Clear previous render

  // 1. Define dimensions
  const width = 800;
  const height = 400;
  const margin = { top: 20, right: 30, bottom: 40, left: 50 };
  const innerWidth = width - margin.left - margin.right;
  const innerHeight = height - margin.top - margin.bottom;

  // 2. Create main group with margins
  const g = svg.append("g")
    .attr("transform", `translate(${margin.left},${margin.top})`);

  // 3. Create scales
  const xScale = d3.scaleLinear()
    .domain([0, d3.max(data, d => d.x)])
    .range([0, innerWidth]);

  const yScale = d3.scaleLinear()
    .domain([0, d3.max(data, d => d.y)])
    .range([innerHeight, 0]); // Note: inverted for SVG coordinates

  // 4. Create and append axes
  const xAxis = d3.axisBottom(xScale);
  const yAxis = d3.axisLeft(yScale);

  g.append("g")
    .attr("transform", `translate(0,${innerHeight})`)
    .call(xAxis);

  g.append("g")
    .call(yAxis);

  // 5. Bind data and create visual elements
  g.selectAll("circle")
    .data(data)
    .join("circle")
    .attr("cx", d => xScale(d.x))
    .attr("cy", d => yScale(d.y))
    .attr("r", 5)
    .attr("fill", "steelblue");
}

// Call when data changes
drawVisualization(myData);

4. Implement responsive sizing

Make visualisations responsive to container size:

function setupResponsiveChart(containerId, data) {
  const container = document.getElementById(containerId);
  const svg = d3.select(`#${containerId}`).append('svg');

  function updateChart() {
    const { width, height } = container.getBoundingClientRect();
    svg.attr('width', width).attr('height', height);

    // Redraw visualisation with new dimensions
    drawChart(data, svg, width, height);
  }

  // Update on initial load
  updateChart();

  // Update on window resize
  window.addEventListener('resize', updateChart);

  // Return cleanup function
  return () => window.removeEventListener('resize', updateChart);
}

// Usage:
// const cleanup = setupResponsiveChart('chart-container', myData);
// cleanup(); // Call when component unmounts or element removed

Or use ResizeObserver for more direct container monitoring:

function setupResponsiveChartWithObserver(svgElement, data) {
  const observer = new ResizeObserver(() => {
    const { width, height } = svgElement.getBoundingClientRect();
    d3.select(svgElement)
      .attr('width', width)
      .attr('height', height);

    // Redraw visualisation
    drawChart(data, d3.select(svgElement), width, height);
  });

  observer.observe(svgElement.parentElement);
  return () => observer.disconnect();
}

Common visualisation patterns

Bar chart

function drawBarChart(data, svgElement) {
  if (!data || data.length === 0) return;

  const svg = d3.select(svgElement);
  svg.selectAll("*").remove();

  const width = 800;
  const height = 400;
  const margin = { top: 20, right: 30, bottom: 40, left: 50 };
  const innerWidth = width - margin.left - margin.right;
  const innerHeight = height - margin.top - margin.bottom;

  const g = svg.append("g")
    .attr("transform", `translate(${margin.left},${margin.top})`);

  const xScale = d3.scaleBand()
    .domain(data.map(d => d.category))
    .range([0, innerWidth])
    .padding(0.1);

  const yScale = d3.scaleLinear()
    .domain([0, d3.max(data, d => d.value)])
    .range([innerHeight, 0]);

  g.append("g")
    .attr("transform", `translate(0,${innerHeight})`)
    .call(d3.axisBottom(xScale));

  g.append("g")
    .call(d3.axisLeft(yScale));

  g.selectAll("rect")
    .data(data)
    .join("rect")
    .attr("x", d => xScale(d.category))
    .attr("y", d => yScale(d.value))
    .attr("width", xScale.bandwidth())
    .attr("height", d => innerHeight - yScale(d.value))
    .attr("fill", "steelblue");
}

// Usage:
// drawBarChart(myData, document.getElementById('chart'));

Line chart

const line = d3.line()
  .x(d => xScale(d.date))
  .y(d => yScale(d.value))
  .curve(d3.curveMonotoneX); // Smooth curve

g.append("path")
  .datum(data)
  .attr("fill", "none")
  .attr("stroke", "steelblue")
  .attr("stroke-width", 2)
  .attr("d", line);

Scatter plot

g.selectAll("circle")
  .data(data)
  .join("circle")
  .attr("cx", d => xScale(d.x))
  .attr("cy", d => yScale(d.y))
  .attr("r", d => sizeScale(d.size)) // Optional: size encoding
  .attr("fill", d => colourScale(d.category)) // Optional: colour encoding
  .attr("opacity", 0.7);

Chord diagram

A chord diagram shows relationships between entities in a circular layout, with ribbons representing flows between them:

function drawChordDiagram(data) {
  // data format: array of objects with source, target, and value
  // Example: [{ source: 'A', target: 'B', value: 10 }, ...]

  if (!data || data.length === 0) return;

  const svg = d3.select('#chart');
  svg.selectAll("*").remove();

  const width = 600;
  const height = 600;
  const innerRadius = Math.min(width, height) * 0.3;
  const outerRadius = innerRadius + 30;

  // Create matrix from data
  const nodes = Array.from(new Set(data.flatMap(d => [d.source, d.target])));
  const matrix = Array.from({ length: nodes.length }, () => Array(nodes.length).fill(0));

  data.forEach(d => {
    const i = nodes.indexOf(d.source);
    const j = nodes.indexOf(d.target);
    matrix[i][j] += d.value;
    matrix[j][i] += d.value;
  });

  // Create chord layout
  const chord = d3.chord()
    .padAngle(0.05)
    .sortSubgroups(d3.descending);

  const arc = d3.arc()
    .innerRadius(innerRadius)
    .outerRadius(outerRadius);

  const ribbon = d3.ribbon()
    .source(d => d.source)
    .target(d => d.target);

  const colourScale = d3.scaleOrdinal(d3.schemeCategory10)
    .domain(nodes);

  const g = svg.append("g")
    .attr("transform", `translate(${width / 2},${height / 2})`);

  const chords = chord(matrix);

  // Draw ribbons
  g.append("g")
    .attr("fill-opacity", 0.67)
    .selectAll("path")
    .data(chords)
    .join("path")
    .attr("d", ribbon)
    .attr("fill", d => colourScale(nodes[d.source.index]))
    .attr("stroke", d => d3.rgb(colourScale(nodes[d.source.index])).darker());

  // Draw groups (arcs)
  const group = g.append("g")
    .selectAll("g")
    .data(chords.groups)
    .join("g");

  group.append("path")
    .attr("d", arc)
    .attr("fill", d => colourScale(nodes[d.index]))
    .attr("stroke", d => d3.rgb(colourScale(nodes[d.index])).darker());

  // Add labels
  group.append("text")
    .each(d => { d.angle = (d.startAngle + d.endAngle) / 2; })
    .attr("dy", "0.31em")
    .attr("transform", d => `rotate(${(d.angle * 180 / Math.PI) - 90})translate(${outerRadius + 30})${d.angle > Math.PI ? "rotate(180)" : ""}`)
    .attr("text-anchor", d => d.angle > Math.PI ? "end" : null)
    .text((d, i) => nodes[i])
    .style("font-size", "12px");
}

Heatmap

A heatmap uses colour to encode values in a two-dimensional grid, useful for showing patterns across categories:

function drawHeatmap(data) {
  // data format: array of objects with row, column, and value
  // Example: [{ row: 'A', column: 'X', value: 10 }, ...]

  if (!data || data.length === 0) return;

  const svg = d3.select('#chart');
  svg.selectAll("*").remove();

  const width = 800;
  const height = 600;
  const margin = { top: 100, right: 30, bottom: 30, left: 100 };
  const innerWidth = width - margin.left - margin.right;
  const innerHeight = height - margin.top - margin.bottom;

  // Get unique rows and columns
  const rows = Array.from(new Set(data.map(d => d.row)));
  const columns = Array.from(new Set(data.map(d => d.column)));

  const g = svg.append("g")
    .attr("transform", `translate(${margin.left},${margin.top})`);

  // Create scales
  const xScale = d3.scaleBand()
    .domain(columns)
    .range([0, innerWidth])
    .padding(0.01);

  const yScale = d3.scaleBand()
    .domain(rows)
    .range([0, innerHeight])
    .padding(0.01);

  // Colour scale for values
  const colourScale = d3.scaleSequential(d3.interpolateYlOrRd)
    .domain([0, d3.max(data, d => d.value)]);

  // Draw rectangles
  g.selectAll("rect")
    .data(data)
    .join("rect")
    .attr("x", d => xScale(d.column))
    .attr("y", d => yScale(d.row))
    .attr("width", xScale.bandwidth())
    .attr("height", yScale.bandwidth())
    .attr("fill", d => colourScale(d.value));

  // Add x-axis labels
  svg.append("g")
    .attr("transform", `translate(${margin.left},${margin.top})`)
    .selectAll("text")
    .data(columns)
    .join("text")
    .attr("x", d => xScale(d) + xScale.bandwidth() / 2)
    .attr("y", -10)
    .attr("text-anchor", "middle")
    .text(d => d)
    .style("font-size", "12px");

  // Add y-axis labels
  svg.append("g")
    .attr("transform", `translate(${margin.left},${margin.top})`)
    .selectAll("text")
    .data(rows)
    .join("text")
    .attr("x", -10)
    .attr("y", d => yScale(d) + yScale.bandwidth() / 2)
    .attr("dy", "0.35em")
    .attr("text-anchor", "end")
    .text(d => d)
    .style("font-size", "12px");

  // Add colour legend
  const legendWidth = 20;
  const legendHeight = 200;
  const legend = svg.append("g")
    .attr("transform", `translate(${width - 60},${margin.top})`);

  const legendScale = d3.scaleLinear()
    .domain(colourScale.domain())
    .range([legendHeight, 0]);

  const legendAxis = d3.axisRight(legendScale)
    .ticks(5);

  // Draw colour gradient in legend
  for (let i = 0; i < legendHeight; i++) {
    legend.append("rect")
      .attr("y", i)
      .attr("width", legendWidth)
      .attr("height", 1)
      .attr("fill", colourScale(legendScale.invert(i)));
  }

  legend.append("g")
    .attr("transform", `translate(${legendWidth},0)`)
    .call(legendAxis);
}

Pie chart

const pie = d3.pie()
  .value(d => d.value)
  .sort(null);

const arc = d3.arc()
  .innerRadius(0)
  .outerRadius(Math.min(width, height) / 2 - 20);

const colourScale = d3.scaleOrdinal(d3.schemeCategory10);

const g = svg.append("g")
  .attr("transform", `translate(${width / 2},${height / 2})`);

g.selectAll("path")
  .data(pie(data))
  .join("path")
  .attr("d", arc)
  .attr("fill", (d, i) => colourScale(i))
  .attr("stroke", "white")
  .attr("stroke-width", 2);

Force-directed network

const simulation = d3.forceSimulation(nodes)
  .force("link", d3.forceLink(links).id(d => d.id).distance(100))
  .force("charge", d3.forceManyBody().strength(-300))
  .force("center", d3.forceCenter(width / 2, height / 2));

const link = g.selectAll("line")
  .data(links)
  .join("line")
  .attr("stroke", "#999")
  .attr("stroke-width", 1);

const node = g.selectAll("circle")
  .data(nodes)
  .join("circle")
  .attr("r", 8)
  .attr("fill", "steelblue")
  .call(d3.drag()
    .on("start", dragstarted)
    .on("drag", dragged)
    .on("end", dragended));

simulation.on("tick", () => {
  link
    .attr("x1", d => d.source.x)
    .attr("y1", d => d.source.y)
    .attr("x2", d => d.target.x)
    .attr("y2", d => d.target.y);
  
  node
    .attr("cx", d => d.x)
    .attr("cy", d => d.y);
});

function dragstarted(event) {
  if (!event.active) simulation.alphaTarget(0.3).restart();
  event.subject.fx = event.subject.x;
  event.subject.fy = event.subject.y;
}

function dragged(event) {
  event.subject.fx = event.x;
  event.subject.fy = event.y;
}

function dragended(event) {
  if (!event.active) simulation.alphaTarget(0);
  event.subject.fx = null;
  event.subject.fy = null;
}

Adding interactivity

Tooltips

// Create tooltip div (outside SVG)
const tooltip = d3.select("body").append("div")
  .attr("class", "tooltip")
  .style("position", "absolute")
  .style("visibility", "hidden")
  .style("background-color", "white")
  .style("border", "1px solid #ddd")
  .style("padding", "10px")
  .style("border-radius", "4px")
  .style("pointer-events", "none");

// Add to elements
circles
  .on("mouseover", function(event, d) {
    d3.select(this).attr("opacity", 1);
    tooltip
      .style("visibility", "visible")
      .html(`<strong>${d.label}</strong><br/>Value: ${d.value}`);
  })
  .on("mousemove", function(event) {
    tooltip
      .style("top", (event.pageY - 10) + "px")
      .style("left", (event.pageX + 10) + "px");
  })
  .on("mouseout", function() {
    d3.select(this).attr("opacity", 0.7);
    tooltip.style("visibility", "hidden");
  });

Zoom and pan

const zoom = d3.zoom()
  .scaleExtent([0.5, 10])
  .on("zoom", (event) => {
    g.attr("transform", event.transform);
  });

svg.call(zoom);

Click interactions

circles
  .on("click", function(event, d) {
    // Handle click (dispatch event, update app state, etc.)
    console.log("Clicked:", d);

    // Visual feedback
    d3.selectAll("circle").attr("fill", "steelblue");
    d3.select(this).attr("fill", "orange");

    // Optional: dispatch custom event for your framework/app to listen to
    // window.dispatchEvent(new CustomEvent('chartClick', { detail: d }));
  });

Transitions and animations

Add smooth transitions to visual changes:

// Basic transition
circles
  .transition()
  .duration(750)
  .attr("r", 10);

// Chained transitions
circles
  .transition()
  .duration(500)
  .attr("fill", "orange")
  .transition()
  .duration(500)
  .attr("r", 15);

// Staggered transitions
circles
  .transition()
  .delay((d, i) => i * 50)
  .duration(500)
  .attr("cy", d => yScale(d.value));

// Custom easing
circles
  .transition()
  .duration(1000)
  .ease(d3.easeBounceOut)
  .attr("r", 10);

Scales reference

Quantitative scales

// Linear scale
const xScale = d3.scaleLinear()
  .domain([0, 100])
  .range([0, 500]);

// Log scale (for exponential data)
const logScale = d3.scaleLog()
  .domain([1, 1000])
  .range([0, 500]);

// Power scale
const powScale = d3.scalePow()
  .exponent(2)
  .domain([0, 100])
  .range([0, 500]);

// Time scale
const timeScale = d3.scaleTime()
  .domain([new Date(2020, 0, 1), new Date(2024, 0, 1)])
  .range([0, 500]);

Ordinal scales

// Band scale (for bar charts)
const bandScale = d3.scaleBand()
  .domain(['A', 'B', 'C', 'D'])
  .range([0, 400])
  .padding(0.1);

// Point scale (for line/scatter categories)
const pointScale = d3.scalePoint()
  .domain(['A', 'B', 'C', 'D'])
  .range([0, 400]);

// Ordinal scale (for colours)
const colourScale = d3.scaleOrdinal(d3.schemeCategory10);

Sequential scales

// Sequential colour scale
const colourScale = d3.scaleSequential(d3.interpolateBlues)
  .domain([0, 100]);

// Diverging colour scale
const divScale = d3.scaleDiverging(d3.interpolateRdBu)
  .domain([-10, 0, 10]);

Best practices

Data preparation

Always validate and prepare data before visualisation:

// Filter invalid values
const cleanData = data.filter(d => d.value != null && !isNaN(d.value));

// Sort data if order matters
const sortedData = [...data].sort((a, b) => b.value - a.value);

// Parse dates
const parsedData = data.map(d => ({
  ...d,
  date: d3.timeParse("%Y-%m-%d")(d.date)
}));

Performance optimisation

For large datasets (>1000 elements):

// Use canvas instead of SVG for many elements
// Use quadtree for collision detection
// Simplify paths with d3.line().curve(d3.curveStep)
// Implement virtual scrolling for large lists
// Use requestAnimationFrame for custom animations

Accessibility

Make visualisations accessible:

// Add ARIA labels
svg.attr("role", "img")
   .attr("aria-label", "Bar chart showing quarterly revenue");

// Add title and description
svg.append("title").text("Quarterly Revenue 2024");
svg.append("desc").text("Bar chart showing revenue growth across four quarters");

// Ensure sufficient colour contrast
// Provide keyboard navigation for interactive elements
// Include data table alternative

Styling

Use consistent, professional styling:

// Define colour palettes upfront
const colours = {
  primary: '#4A90E2',
  secondary: '#7B68EE',
  background: '#F5F7FA',
  text: '#333333',
  gridLines: '#E0E0E0'
};

// Apply consistent typography
svg.selectAll("text")
  .style("font-family", "Inter, sans-serif")
  .style("font-size", "12px");

// Use subtle grid lines
g.selectAll(".tick line")
  .attr("stroke", colours.gridLines)
  .attr("stroke-dasharray", "2,2");

Common issues and solutions

Issue: Axes not appearing

  • Ensure scales have valid domains (check for NaN values)
  • Verify axis is appended to correct group
  • Check transform translations are correct

Issue: Transitions not working

  • Call .transition() before attribute changes
  • Ensure elements have unique keys for proper data binding
  • Check that useEffect dependencies include all changing data

Issue: Responsive sizing not working

  • Use ResizeObserver or window resize listener
  • Update dimensions in state to trigger re-render
  • Ensure SVG has width/height attributes or viewBox

Issue: Performance problems

  • Limit number of DOM elements (consider canvas for >1000 items)
  • Debounce resize handlers
  • Use .join() instead of separate enter/update/exit selections
  • Avoid unnecessary re-renders by checking dependencies

Resources

references/

Contains detailed reference materials:

  • d3-patterns.md - Comprehensive collection of visualisation patterns and code examples
  • scale-reference.md - Complete guide to d3 scales with examples
  • colour-schemes.md - D3 colour schemes and palette recommendations

assets/

Contains boilerplate templates:

  • chart-template.js - Starter template for basic chart
  • interactive-template.js - Template with tooltips, zoom, and interactions
  • sample-data.json - Example datasets for testing

These templates work with vanilla JavaScript, React, Vue, Svelte, or any other JavaScript environment. Adapt them as needed for your specific framework.

To use these resources, read the relevant files when detailed guidance is needed for specific visualisation types or patterns.

FAQ

What does claude-d3js-skill do?

This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.

When should I use claude-d3js-skill?

Use it when you need a repeatable workflow that produces code diff.

What does claude-d3js-skill output?

In the evaluated run it produced code diff.

How do I install or invoke claude-d3js-skill?

Ask the agent to use this skill when the task matches its documented workflow.

Which agents does claude-d3js-skill support?

Agent support is inferred from the source, but not explicitly declared.

What tools, channels, or permissions does claude-d3js-skill need?

It uses node, npm; channels commonly include diff; permissions include filesystem:read, filesystem:write, process:spawn.

Is claude-d3js-skill safe to install?

Static analysis marked this skill as medium risk; review side effects and permissions before enabling it.

How is claude-d3js-skill different from an MCP or plugin?

A skill packages instructions and workflow conventions; tools, MCP servers, and plugins are dependencies the skill may call during execution.

Does claude-d3js-skill outperform not using a skill?

About claude-d3js-skill

When to use claude-d3js-skill

When you need custom charts or diagrams that standard charting libraries cannot express well. When implementing interactive SVG-based visualizations with zooming, brushing, transitions, or custom layouts. When adding D3.js visualizations to a web app built with vanilla JavaScript or a frontend framework.

When claude-d3js-skill is not the right choice

When you only need simple off-the-shelf charts from a higher-level charting library. When the task is primarily 3D visualization rather than 2D interactive graphics.

What it produces

Produces code diff.