How do I install the Seaborn skill?

Run npx skillmds@latest add ai4protein/seaborn in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Seaborn safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Seaborn?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Seaborn free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Unknown.

Who published Seaborn?

ai4protein (@ai4protein) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Seaborn by ai4protein — Agent Skill

Name: Seaborn
Author: ai4protein

Seaborn

Seaborn statistical plots for exploratory analysis via agent_generated_code. Use for quick relational/distribution/categorical charts. Do NOT use for submission-grade Nature figures (nature_figure) or low-level artists control (matplotlib).

ai4protein 3110d47 5 files · 82.9 KB Updated Sep 17, 2026

File contents

Seaborn Statistical Visualization

Overview

High-level statistical viz on top of matplotlib. In VenusFactory, plots run through agent_generated_code / python_repl. Publication figures must load nature_figure first.

VenusFactory execution

No seaborn_* @tool. Optional helpers: src/tools/visualize/matplotlib/plot_template.py, style_configurator.py.
Deep API: read_skill("seaborn", relative_path="references/function_reference.md") or references/legacy_guide.md.

When to use / NOT

Use seaborn	Prefer instead
EDA bar/box/violin/heatmap	—
Publication multi-panel Nature style	`nature_figure`
Pixel-perfect artists / custom projections	`matplotlib`

Quick start

import seaborn as sns
import matplotlib.pyplot as plt
sns.set_theme(style="whitegrid")
ax = sns.barplot(data=df, x="mutation", y="score")
fig = ax.get_figure()
fig.savefig(out_png, dpi=300, bbox_inches="tight")

Plot selection (index)

Relational: scatterplot, lineplot, relplot
Distribution: histplot, kdeplot, ecdfplot
Categorical: boxplot, violinplot, barplot, stripplot
Matrix: heatmap, clustermap
Objects API: seaborn.objects — see references/objects_interface.md if present / legacy guide

Common mistakes

Skipping nature_figure for manuscript figures
Not saving PNG under session output_dir at dpi≥300
Passing wide data without melting for categorical plots

References (progressive disclosure)

Trust order: SKILL.md (hub tools & envelopes) → topic refs → references/legacy_guide.md (archived; may be outdated).

read_skill(skill_id="seaborn", relative_path="references/legacy_guide.md")

Load legacy only after the hub workflow in this file is insufficient.

---name: seaborndescription: Seaborn statistical plots for exploratory analysis via agent_generated_code. Use for quick relational/distribution/categorical charts. Do NOT use for submission-grade Nature figures (nature_figure) or low-level artists control (matplotlib).license: Unknown---# Seaborn Statistical Visualization## OverviewHigh-level statistical viz on top of matplotlib. In VenusFactory, plots run through **`agent_generated_code`** / `python_repl`. Publication figures must load **`nature_figure`** first.## VenusFactory execution- No `seaborn_*` `@tool`. Optional helpers: `src/tools/visualize/matplotlib/plot_template.py`, `style_configurator.py`.- Deep API: `read_skill("seaborn", relative_path="references/function_reference.md")` or `references/legacy_guide.md`.## When to use / NOT| Use seaborn | Prefer instead ||-------------|----------------|| EDA bar/box/violin/heatmap | — || Publication multi-panel Nature style | `nature_figure` || Pixel-perfect artists / custom projections | `matplotlib` |## Quick start```pythonimport seaborn as snsimport matplotlib.pyplot as pltsns.set_theme(style="whitegrid")ax = sns.barplot(data=df, x="mutation", y="score")fig = ax.get_figure()fig.savefig(out_png, dpi=300, bbox_inches="tight")```## Plot selection (index)- Relational: `scatterplot`, `lineplot`, `relplot`- Distribution: `histplot`, `kdeplot`, `ecdfplot`- Categorical: `boxplot`, `violinplot`, `barplot`, `stripplot`- Matrix: `heatmap`, `clustermap`- Objects API: `seaborn.objects` — see `references/objects_interface.md` if present / legacy guide## Common mistakes- Skipping `nature_figure` for manuscript figures- Not saving PNG under session `output_dir` at dpi≥300- Passing wide data without melting for categorical plots## References (progressive disclosure)**Trust order:** `SKILL.md` (hub tools & envelopes) → topic refs → `references/legacy_guide.md` (archived; may be outdated).```textread_skill(skill_id="seaborn", relative_path="references/legacy_guide.md")```Load legacy only after the hub workflow in this file is insufficient.

Frequently asked questions