Data Visualization

This handles all your matplotlib and seaborn charting in Claude's headless GPU environment. It automatically configures the Agg backend so plots actually render, sets publication quality defaults at 300 DPI, and includes a colorblind safe palette out of the box. The skill doc gives you copy paste templates for the usual suspects: bar charts, line plots, scatter plots with both continuous and categorical coloring, heatmaps, histograms with KDE overlays, and box plots. The multi panel layout option is clutch for analysis summaries where you want everything in one image. One thing to remember is you must call read_file on every saved PNG or the user won't see it inline. Solid if you're tired of fighting matplotlib configuration every time.

skills.sh installs: 272
GitHub stars: 31.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add langchain-ai/deepagents --skill data-visualization --agent claude-code

Installs into .claude/skills of the current project.

Files

Data Visualization Skill

Create publication-quality analytical charts using matplotlib and seaborn in a headless GPU sandbox. Charts are saved as PNG files to /workspace/ for retrieval.

When to Use This Skill

Use this skill when:

Visualizing results from cuDF analysis or cuML models
Creating charts (bar, line, scatter, heatmap, histogram, box plot)
Building multi-panel analysis summaries
The user asks for visual output, plots, graphs, or charts
Presenting statistical findings with figures

Initialization (REQUIRED)

MUST call matplotlib.use('Agg') BEFORE importing pyplot. This enables headless rendering.

import matplotlib
matplotlib.use('Agg')  # Headless backend — MUST be before pyplot import
import matplotlib.pyplot as plt
import numpy as np

# Publication-quality defaults
plt.rcParams.update({
    'figure.dpi': 100,
    'savefig.dpi': 300,
    'font.size': 11,
    'axes.labelsize': 12,
    'axes.titlesize': 14,
    'xtick.labelsize': 10,
    'ytick.labelsize': 10,
    'legend.fontsize': 10,
    'figure.constrained_layout.use': True,
})

SKILL.md on GitHub