Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Seaborn Statistical Visualization

Gives Claude a complete, code-first seaborn reference for turning pandas DataFrames into publication-ready statistical plots.

Data & AnalyticsIntermediate★ 357⑂ 34AI score 9/10Last updated: Aug 29, 2026

What it does

  • Equips Claude with accurate seaborn recipes so it can write working plotting code for your DataFrame on the first try.
  • Coverage: distributions (histplot, kdeplot, ecdfplot), categorical (box, violin, bar, swarm), relational (scatter, line with automatic aggregation and CIs), regression (regplot, residplot), matrix (heatmap, clustermap), faceting (relplot, catplot, displot) and exploratory grids (pairplot, jointplot).
  • Explains figure-level vs axes-level functions, long-form vs wide-form data, plus a key-parameter table (hue, style, estimator, errorbar, bw_adjust, multiple).
  • Includes a publication-figure workflow (panel labels, despine, 300 dpi PDF/PNG export) and a troubleshooting table for clipped legends, overlapping ticks, KDE bandwidth, and wide-form hue errors.

Who it's for

  • Data analysts and researchers doing exploratory analysis in Python.
  • Grad students preparing statistical figures for papers and reports.
  • Developers comfortable with matplotlib who keep looking up seaborn arguments.

Examples

  1. "Plot a correlation heatmap of the numeric columns in this CSV with significance stars" → generates scipy p-value computation plus annotated heatmap.
  2. "Build a 3-panel paper figure: body-mass boxplot by species, regression scatter, bill-length violin" → set_theme(context="paper") code saving both PDF and PNG.
  3. "I get a ValueError using hue on my wide-format spreadsheet" → converts with df.melt() and rewrites the plot call.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/jaechang-hits/SciAgent-Skills/HEAD/legacy/seaborn-statistical-visualization/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

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 legacy/seaborn-statistical-visualization folder from the GitHub repo jaechang-hits/SciAgent-Skills into my ~/.claude/skills/seaborn-statistical-visualization/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/jaechang-hits/SciAgent-Skills.git && cp -r SciAgent-Skills/legacy/seaborn-statistical-visualization ~/.claude/skills/

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

  1. Open a terminal (Terminal on macOS, Git Bash or WSL on Windows).
  2. Create the skills folder if needed: mkdir -p ~/.claude/skills
  3. Clone the repository: git clone https://github.com/jaechang-hits/SciAgent-Skills.git
  4. Copy just this skill: cp -r SciAgent-Skills/legacy/seaborn-statistical-visualization ~/.claude/skills/
  5. Install the Python dependencies: pip install seaborn matplotlib pandas scipy
  6. Restart Claude Code and try a prompt like "use seaborn to plot distributions by group for this dataset".
View source on GitHub ↗License: NOASSERTION