Agent skill

Datavis

Create scientific plots and visualizations using matplotlib and seaborn

Apache-2.0Auto-check passedData & Analytics

Install Datavis

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill datavis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw datavis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/datavis .claude/skills/datavis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "datavis" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/datavis into .claude/skills/datavis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datavis", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/lamm-mit/scienceclaw/tree/main/skills/datavis

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill datavis -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw datavis --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/datavis .agents/skills/datavis && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "datavis" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/datavis into .agents/skills/datavis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datavis", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill datavis -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw datavis --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/datavis .cursor/skills/datavis && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "datavis" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/datavis into .cursor/skills/datavis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datavis", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/lamm-mit/scienceclaw.git --path skills/datavis

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill datavis -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw datavis --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/datavis .gemini/skills/datavis && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "datavis" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/datavis into .gemini/skills/datavis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datavis", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw datavis

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill datavis -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/datavis .github/skills/datavis && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "datavis" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/datavis into .github/skills/datavis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datavis", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill datavis -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw datavis --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/datavis .opencode/skills/datavis && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "datavis" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/datavis into .opencode/skills/datavis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datavis", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: datavis
GitHub stars: 244
Token cost: ~1.4k tokens
SKILL.md length: 426 words
Files: 5 (incl. scripts)
Skills in repo: 85
Repo updated: Aug 21, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Create scientific plots and visualizations using matplotlib and seaborn

Tasks that involve Data visualization
SKILL.md covers Overview, Usage, Plot Types and Common Options, plus 3 more sections
Runs Python scripts from its folder; calls python3

What it does

Datavis is an agent skill from lamm-mit/scienceclaw. Create scientific plots and visualizations using matplotlib and seaborn

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `scripts/demo.py` and `scripts/plot_data.py`).

It sits in Data & Analytics, covering Data visualization. It works with Matplotlib and Seaborn. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Data visualization

Example prompts

“/datavis”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit ab9aba1. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 4 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Datavis loads about 1.4k tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 426 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~20
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 426 words, ~1,422 tokens.

Download SKILL.mdSave it as .claude/skills/datavis/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.

name: datavis
description: Create scientific plots and visualizations using matplotlib and seaborn

Scientific Data Visualization

Create publication-quality scientific plots and visualizations using matplotlib and seaborn.

Overview

This skill provides data visualization capabilities for scientific data:

Line plots, scatter plots, bar charts
Heatmaps and clustermaps
Box plots and violin plots
Histograms and density plots
Sequence logos (for bioinformatics)
Multiple subplot layouts

Usage

Create a line plot from CSV:

bash

python3 {baseDir}/scripts/plot_data.py line --data data.csv --x time --y value --output plot.png

Create a scatter plot:

bash

python3 {baseDir}/scripts/plot_data.py scatter --data data.csv --x x_col --y y_col --hue group

Create a heatmap:

bash

python3 {baseDir}/scripts/plot_data.py heatmap --data matrix.csv --output heatmap.png

Create a bar chart:

bash

python3 {baseDir}/scripts/plot_data.py bar --data data.csv --x category --y value

Plot from JSON data:

bash

python3 {baseDir}/scripts/plot_data.py line --json '{"x": [1,2,3], "y": [4,5,6]}'

Plot Types

line

Line plot for continuous data.

Parameter	Description	Default
`--data`	CSV file path	-
`--json`	JSON data string	-
`--x`	X-axis column	Required
`--y`	Y-axis column(s), comma-separated	Required
`--hue`	Color grouping column	-
`--style`	Line style column	-
`--markers`	Add markers	False

scatter

Scatter plot for showing relationships.

Parameter	Description	Default
`--data`	CSV file path	-
`--x`	X-axis column	Required
`--y`	Y-axis column	Required
`--hue`	Color grouping column	-
`--size`	Size column	-
`--alpha`	Point transparency	0.7

bar

Bar chart for categorical data.

Parameter	Description	Default
`--data`	CSV file path	-
`--x`	Category column	Required
`--y`	Value column	Required
`--hue`	Color grouping column	-
`--horizontal`	Horizontal bars	False
`--error`	Error bar column	-

heatmap

Heatmap for matrix data.

Parameter	Description	Default
`--data`	CSV file path	Required
`--cmap`	Color map	viridis
`--annotate`	Show values	False
`--cluster`	Cluster rows/columns	False

box

Box plot for distributions.

Parameter	Description	Default
`--data`	CSV file path	-
`--x`	Grouping column	-
`--y`	Value column	Required
`--hue`	Color grouping column	-

violin

Violin plot for distributions.

Parameter	Description	Default
`--data`	CSV file path	-
`--x`	Grouping column	-
`--y`	Value column	Required
`--hue`	Color grouping column	-
`--split`	Split violins by hue	False

Show full SKILL.md (174 more words)Show less

histogram

Histogram for distributions.

Parameter	Description	Default
`--data`	CSV file path	-
`--x`	Value column	Required
`--bins`	Number of bins	auto
`--kde`	Add KDE line	False
`--hue`	Color grouping column	-

Common Options

Option	Description	Default
`--output`	Output file path	plot.png
`--format`	Output format: png, svg, pdf	png
`--title`	Plot title	-
`--xlabel`	X-axis label	column name
`--ylabel`	Y-axis label	column name
`--figsize`	Figure size (width,height)	10,6
`--style`	Seaborn style	whitegrid
`--palette`	Color palette	deep
`--dpi`	Output resolution	150
`--legend`	Legend position	auto
`--logx`	Log scale X-axis	False
`--logy`	Log scale Y-axis	False

Examples

Multi-line plot with legend:

bash

python3 {baseDir}/scripts/plot_data.py line --data timeseries.csv --x date --y "temp,humidity" --title "Weather Data" --output weather.png

Scatter plot with regression line:

bash

python3 {baseDir}/scripts/plot_data.py scatter --data experiment.csv --x dose --y response --hue treatment --title "Dose Response" --output dose_response.png

Clustered heatmap:

bash

python3 {baseDir}/scripts/plot_data.py heatmap --data expression.csv --cluster --cmap RdBu_r --title "Gene Expression" --output heatmap.svg --format svg

Box plot with multiple groups:

bash

python3 {baseDir}/scripts/plot_data.py box --data measurements.csv --x condition --y value --hue treatment --title "Treatment Effects"

Histogram with KDE:

bash

python3 {baseDir}/scripts/plot_data.py histogram --data samples.csv --x measurement --bins 30 --kde --title "Distribution"

Publication-quality figure:

bash

python3 {baseDir}/scripts/plot_data.py scatter --data results.csv --x x --y y --figsize 8,6 --dpi 300 --format svg --style white --output figure1.svg

Color Palettes

deep: Default seaborn palette
muted: Muted colors
bright: Bright colors
pastel: Pastel colors
dark: Dark colors
colorblind: Colorblind-friendly
viridis: Perceptually uniform
plasma: Perceptually uniform
RdBu: Red-Blue diverging
coolwarm: Cool-Warm diverging

Notes

Data can be provided as CSV files or JSON strings
SVG output is recommended for publications
Use --dpi 300 for high-resolution figures
Column names with spaces should be quoted

Files

SKILL.md and 4 other files (scripts) in skills/datavis of lamm-mit/scienceclaw.

SKILL.md
scripts/__pycache__/demo.cpython-313.pyc
scripts/__pycache__/plot_data.cpython-313.pyc
scripts/demo.py
scripts/plot_data.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Datavis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Datavis compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Datavis this skilllamm-mit/scienceclaw	244	—	~1.4k	Automated safety check: Pass	Apache-2.0	1 mo ago
MatplotlibzLanqing/codex-claude-academic-skills	4.6k	18 repos	~2.9k	Automated safety check: Pass	MIT	4 mo ago
Scientific Visualizationmims-harvard/OptimusKG	146	19 repos	~6.3k	Automated safety check: Pass	MIT	17 days ago
SeabornzLanqing/codex-claude-academic-skills	4.6k	16 repos	~4.9k	Automated safety check: Pass	BSD-3-Clause	4 mo ago
Scientific VisualizationOleafly/Oleafly	206	1 repos	~3.4k	Automated safety check: Notes	MIT	today
Ieee Figure TableCloudWave818/ieee-skills	355	—	~1k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Matplotlib
zLanqing/codex-claude-academic-skills
Low-level plotting library for full customization. An agent skill from zLanqing/codex-claude-academic-skills.
4.6k GitHub starsUsed in 18 repos~2.9k tokens
Data & AnalyticsAuto-check passed
Scientific Visualization
mims-harvard/OptimusKG
Create publication figures with matplotlib/seaborn/plotly. An agent skill from mims-harvard/OptimusKG.
146 GitHub starsUsed in 19 repos~6.3k tokens
Data & AnalyticsAuto-check passed
Seaborn
zLanqing/codex-claude-academic-skills
Statistical visualization with pandas integration. An agent skill from zLanqing/codex-claude-academic-skills.
4.6k GitHub starsUsed in 16 repos~4.9k tokens
Data & AnalyticsAuto-check passed
Scientific Visualization
Oleafly/Oleafly
Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly.
206 GitHub starsUsed in 1 repo~3.4k tokens
Data & AnalyticsAuto-check: notes
Ieee Figure Table
CloudWave818/ieee-skills
Audit, redesign, generate, and improve IEEE manuscript figures, tables, captions, result presentation, plotting scripts, visual polish, hybrid Python/R plus vector-editor workflows…
355 GitHub stars~1k tokensUpdated 1 mo ago
Data & AnalyticsAuto-check passed
Nature Figure
Citrus-bit/Anaxa
Submission-grade Nature/high-impact journal figure workflow for Python or R.
120 GitHub starsUsed in 2 repos~2.7k tokens
Data & AnalyticsAuto-check passed

Questions about Datavis

What does Datavis do?

Create scientific plots and visualizations using matplotlib and seaborn. Datavis is an agent skill from lamm-mit/scienceclaw.

When should I use Datavis?

Datavis fits situations like: tasks that involve Data visualization.

How do I install Datavis in Claude Code?

Run `npx skills add lamm-mit/scienceclaw --skill datavis -a claude-code`. Or copy the skill folder (skills/datavis in lamm-mit/scienceclaw) into .claude/skills/datavis in your project. Claude Code loads it when a task matches its description.

How do I install Datavis in Codex?

Run `npx skills add lamm-mit/scienceclaw --skill datavis -a codex`. Or copy the skill folder (skills/datavis in lamm-mit/scienceclaw) into .agents/skills/datavis in your project. Codex loads it when a task matches its description.

Can I use Datavis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lamm-mit/scienceclaw --skill datavis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/datavis, .gemini/skills/datavis, .github/skills/datavis and .opencode/skills/datavis in your project.

What does Datavis need to run?

Going by SKILL.md and its folder, Datavis needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Datavis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Datavis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Datavis use?

Datavis is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Datavis use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Datavis?

Skills that share tags, products or a category with Datavis: Matplotlib (zLanqing/codex-claude-academic-skills, 4.6k stars), Scientific Visualization (mims-harvard/OptimusKG, 146 stars), Seaborn (zLanqing/codex-claude-academic-skills, 4.6k stars) and Scientific Visualization (Oleafly/Oleafly, 206 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Datavis?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 21, 2026.

Source: lamm-mit/scienceclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Datavis

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Scientific Data Visualization

Overview

Usage

Create a line plot from CSV:

Create a scatter plot:

Create a heatmap:

Create a bar chart:

Plot from JSON data:

Plot Types

line

scatter

bar

heatmap

box

violin

histogram

Common Options

Examples

Multi-line plot with legend:

Scatter plot with regression line:

Clustered heatmap:

Box plot with multiple groups:

Histogram with KDE:

Publication-quality figure:

Color Palettes

Notes

Files

Compare with similar skills

Similar skills

More from lamm-mit/scienceclaw

Related

Questions about Datavis