Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Seaborn Statistical Visualization

A reference skill that makes Claude write modern, correct seaborn 0.13 code for distributions, relationships and categorical comparisons from pandas DataFrames.

Data & AnalyticsIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Gives Claude an up-to-date playbook for producing publication-quality statistical graphics with seaborn 0.13.2.

  • Plot-type selection guide: scatter/line, box/violin/strip, hist/KDE/ECDF, heatmap/clustermap, pair/joint plots
  • Captures 0.12/0.13 API changes: ci → errorbar, scale → density_norm, palette requiring hue, native_scale=True
  • Long-form (tidy) vs wide-form data guidance with a melt() example
  • Bundled references/ docs for FacetGrid/PairGrid/JointGrid, palettes and theming, troubleshooting, and the objects interface
  • Guidance on when the declarative seaborn.objects API is worth it versus the stable function API

Who it's for

  • Analysts and researchers who plot in Python regularly
  • Anyone tired of verbose matplotlib boilerplate
  • Users hitting deprecation warnings from older seaborn syntax
  • People assembling multi-panel figures for papers or reports

Examples

  1. "Compare tip distributions by weekday with violin plots" → code using violinplot(density_norm=...)
  2. "Load my experiment CSV and plot mean with an SD band over time per condition" → lineplot(errorbar='sd') with faceting
  3. "Export a correlation heatmap and clustermap as a 300dpi PDF" → heatmap/clustermap plus savefig(dpi=300, bbox_inches='tight')

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/seaborn folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/seaborn/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/seaborn ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy the whole seaborn folder (references included): cp -r scientific-agent-skills/skills/seaborn ~/.claude/skills/
  5. Install the Python dependency: uv pip install "seaborn==0.13.2" (use "seaborn[stats]==0.13.2" for regression/clustering examples)
  6. Restart Claude Code and ask something like "plot this dataset's distribution with seaborn" to trigger the skill.
  7. Note that sns.load_dataset() fetches sample data from the internet — for private or offline work, load local files with pandas instead.
View source on GitHub ↗License: MIT