Skill

Official

Pass

Audit score 90

create-viz

anthropics/knowledge-work-plugins

Create publication-quality visualizations from data with Python—charts, plots, and interactive graphics optimized for reports and presentations.

Source View on skills.sh

What is create-viz?

Generate professional data visualizations from query results, DataFrames, or pasted data using matplotlib, seaborn, or plotly. Use this skill when you need to turn raw data into a clear chart for exploration, reporting, or presentation—the skill recommends appropriate chart types and applies design best practices automatically.

Converts data sources (queries, CSVs, pasted data) into pandas DataFrames and generates charts
Recommends optimal chart types based on data relationships (trends, comparisons, distributions, correlations, etc.)
Creates static publication-quality charts with matplotlib/seaborn or interactive charts with plotly
Applies design best practices: colorblind-friendly palettes, clear titles, proper axis formatting, and removed chart junk
Saves charts as high-resolution PNG files with descriptive names
Supports multiple chart types: line, bar, scatter, histogram, heatmap, stacked area, Sankey, choropleth, and more

How to install create-viz

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill create-viz

Claude Code

Cursor

Windsurf

Cline

How to use create-viz

1.Provide your data source: a database query, CSV/Excel file, pasted data, or reference existing data from the conversation
2.Optionally specify a chart type; if not provided, the skill will recommend one based on your data
3.Add any additional instructions (e.g., 'interactive', 'presentation', specific color scheme, or multiple charts)
4.The skill generates Python code, creates the visualization, saves it as a PNG, and displays the result
5.Review the generated code and request variations if needed (different chart type, grouping, or time range)

Use cases

Good for

Turn monthly sales query results into a line chart showing revenue trends over the last 12 months
Create a horizontal bar chart ranking products by NPS score from pasted survey data
Generate a heatmap of order volume by day-of-week and hour from a database query
Build an interactive plotly chart with hover tooltips and zoom for a dashboard component
Create a 2×2 grid of comparison charts for a presentation to executives

Who it's for

Data analysts and business intelligence professionals creating reports
Product managers preparing presentation decks with data visualizations
Engineers and researchers visualizing analysis results
Anyone needing to convert raw data into clear, professional charts

create-viz FAQ

What if I don't know which chart type to use?

Describe your data and question, and the skill will recommend the best chart type. For example, trends over time → line chart, comparisons across categories → bar chart, part-to-whole → stacked bar or area chart.

Can I create interactive charts?

Yes. Mention 'interactive' in your request and the skill will use plotly instead of matplotlib, adding hover tooltips, zoom, and filtering capabilities.

How do I customize the appearance?

The skill generates Python code you can modify. You can adjust colors, fonts, sizes, labels, and layout by editing the code before re-running it.

What data formats are supported?

Query results from connected data warehouses, CSV/Excel files, pasted data, and DataFrames from previous analyses in the conversation.

Can I create multiple charts at once?

Yes. Request a grid of charts (e.g., '2×2 grid') or multiple visualizations of the same data with different chart types.

Full instructions (SKILL.md)

Source of truth, from anthropics/knowledge-work-plugins.

name: create-viz description: Create publication-quality visualizations with Python. Use when turning query results or a DataFrame into a chart, selecting the right chart type for a trend or comparison, generating a plot for a report or presentation, or needing an interactive chart with hover and zoom. argument-hint: "<data source> [chart type]"

/create-viz - Create Visualizations

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

Create publication-quality data visualizations using Python. Generates charts from data with best practices for clarity, accuracy, and design.

Usage

/create-viz <data source> [chart type] [additional instructions]

Workflow

1. Understand the Request

Determine:

Data source: Query results, pasted data, CSV/Excel file, or data to be queried
Chart type: Explicitly requested or needs to be recommended
Purpose: Exploration, presentation, report, dashboard component
Audience: Technical team, executives, external stakeholders

2. Get the Data

If data warehouse is connected and data needs querying:

Write and execute the query
Load results into a pandas DataFrame

If data is pasted or uploaded:

Parse the data into a pandas DataFrame
Clean and prepare as needed (type conversions, null handling)

If data is from a previous analysis in the conversation:

Reference the existing data

3. Select Chart Type

If the user didn't specify a chart type, recommend one based on the data and question:

Data Relationship	Recommended Chart
Trend over time	Line chart
Comparison across categories	Bar chart (horizontal if many categories)
Part-to-whole composition	Stacked bar or area chart (avoid pie charts unless <6 categories)
Distribution of values	Histogram or box plot
Correlation between two variables	Scatter plot
Two-variable comparison over time	Dual-axis line or grouped bar
Geographic data	Choropleth map
Ranking	Horizontal bar chart
Flow or process	Sankey diagram
Matrix of relationships	Heatmap

Explain the recommendation briefly if the user didn't specify.

4. Generate the Visualization

Write Python code using one of these libraries based on the need:

matplotlib + seaborn: Best for static, publication-quality charts. Default choice.
plotly: Best for interactive charts or when the user requests interactivity.

Code requirements:

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd

# Set professional style
plt.style.use('seaborn-v0_8-whitegrid')
sns.set_palette("husl")

# Create figure with appropriate size
fig, ax = plt.subplots(figsize=(10, 6))

# [chart-specific code]

# Always include:
ax.set_title('Clear, Descriptive Title', fontsize=14, fontweight='bold')
ax.set_xlabel('X-Axis Label', fontsize=11)
ax.set_ylabel('Y-Axis Label', fontsize=11)

# Format numbers appropriately
# - Percentages: '45.2%' not '0.452'
# - Currency: '$1.2M' not '1200000'
# - Large numbers: '2.3K' or '1.5M' not '2300' or '1500000'

# Remove chart junk
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

plt.tight_layout()
plt.savefig('chart_name.png', dpi=150, bbox_inches='tight')
plt.show()

5. Apply Design Best Practices

Color:

Use a consistent, colorblind-friendly palette
Use color meaningfully (not decoratively)
Highlight the key data point or trend with a contrasting color
Grey out less important reference data

Typography:

Descriptive title that states the insight, not just the metric (e.g., "Revenue grew 23% YoY" not "Revenue by Month")
Readable axis labels (not rotated 90 degrees if avoidable)
Data labels on key points when they add clarity

Layout:

Appropriate whitespace and margins
Legend placement that doesn't obscure data
Sorted categories by value (not alphabetically) unless there's a natural order

Accuracy:

Y-axis starts at zero for bar charts
No misleading axis breaks without clear notation
Consistent scales when comparing panels
Appropriate precision (don't show 10 decimal places)

6. Save and Present

Save the chart as a PNG file with descriptive name
Display the chart to the user
Provide the code used so they can modify it
Suggest variations (different chart type, different grouping, zoomed time range)

Examples

/create-viz Show monthly revenue for the last 12 months as a line chart with the trend highlighted

/create-viz Here's our NPS data by product: [pastes data]. Create a horizontal bar chart ranking products by score.

/create-viz Query the orders table and create a heatmap of order volume by day-of-week and hour

Tips

If you want interactive charts (hover, zoom, filter), mention "interactive" and Claude will use plotly
Specify "presentation" if you need larger fonts and higher contrast
You can request multiple charts at once (e.g., "create a 2x2 grid of charts showing...")
Charts are saved to your current directory as PNG files