skill CX Codex

matplotlib · k-dense-ai — Claude Code skill: scientific plots and export

Q: How do I install the matplotlib skill in Claude Code?

Run `npx skills add K-Dense-AI/scientific-agent-skills --skill matplotlib -a claude-code`. The skill lands at `~/.claude/skills/matplotlib/SKILL.md`.

A skill that guides the agent through Matplotlib: building scientific plots, tuning axes and legends, and exporting figures to PNG, PDF or SVG.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add K-Dense-AI/scientific-agent-skills --skill matplotlib -a claude-code

Open on GitHub

What matplotlib does

The skill tells the agent how to work with Matplotlib — which interface to pick, how to lay out several axes in one figure, how to label axes and legends. It ships examples for line charts, scatter plots, histograms, heatmaps, contours and box plots, plus scripts the agent can run through Bash.

You need Python 3.11+ and Matplotlib 3.11.2. The examples also pull in NumPy and SciPy, some use pandas, and Jupyter widgets need ipympl. Installing packages requires network access; drawing locally needs no credentials.

File output runs without a GUI. For batch scripts set MPLBACKEND=Agg, or select Agg before importing pyplot. Interactive windows need an installed GUI toolkit such as PySide6 (QtAgg) or a working Tk (TkAgg), and plt.ioff() will not drop the GUI thread requirement. Migrating older code? Check the 3.11 API changes: box plots now take tick_labels and orientation, and colormaps come from mpl.colormaps[name].

What it helps with

plot a line chart or scatter plot from an array
assemble a multi-panel figure from several axes
tune colors, labels and legends for a journal
save a figure as PNG, PDF or SVG for publication
draw a heatmap or contour plot from a matrix

Example prompts for the agent

Plot sin(x) and cos(x) on one figure and save it to plot.png with dpi=300
Build a 2 by 2 grid of four different charts and label the axes
Draw a heatmap from this matrix and add a colorbar

How to install matplotlib

1Skills CLI (Vercel)

npx skills add K-Dense-AI/scientific-agent-skills --skill matplotlib -a claude-code

2Manually: put the files in place

~/.claude/skills/matplotlib/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/matplotlib/

1Skills CLI (Vercel)

npx skills add K-Dense-AI/scientific-agent-skills --skill matplotlib -a codex

2Manually: put the files in place

.agents/skills/matplotlib/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add K-Dense-AI/scientific-agent-skills --skill matplotlib -a cursor

2Manually: put the files in place

.cursor/skills/matplotlib/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install K-Dense-AI/scientific-agent-skills matplotlib

2Manually: put the files in place

.github/skills/matplotlib/SKILL.md

1Skills CLI (Vercel)

npx skills add K-Dense-AI/scientific-agent-skills --skill matplotlib -a gemini-cli

2Platform CLI

gemini skills install https://github.com/K-Dense-AI/scientific-agent-skills --path skills/matplotlib

Manually: put the files in place

.devin/skills/matplotlib/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add K-Dense-AI/scientific-agent-skills --skill matplotlib -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about matplotlib

How do I install the matplotlib skill in Claude Code?

Run npx skills add K-Dense-AI/scientific-agent-skills --skill matplotlib -a claude-code. The skill lands at ~/.claude/skills/matplotlib/SKILL.md.

What does the matplotlib skill do?

It helps the agent create and customize scientific plots: choose between the pyplot and object-oriented interfaces, build multi-panel figures, and export them to PNG, PDF or SVG.

What does the skill require?

Python 3.11+ and Matplotlib 3.11.2. The examples also use NumPy and SciPy, some need pandas, and Jupyter widgets require ipympl.

Similar skills

Everything for Science and research →

matplotlib by other authors comes first.

matplotlib tondevrel A skill that tells your agent how to build matplotlib figures: line and scatter plots, heatmaps, multi-panel layouts. Useful when the data sits in NumPy or Pandas and the output goes into a paper or report. CX Codex +1 374installs matplotlib davila7 A Claude skill for matplotlib: line plots, scatter, bar, histograms, heatmaps and 3D figures, exported to PNG, PDF or SVG. 257installs anysearch anysearch-ai This skill gives an agent web search, domain-specific queries, parallel batch search, and page extraction. Use it when a task needs current information or a claim needs checking. CX Codex +1 38,500installs academic-paper Imbad0202 This skill runs a 12-agent academic pipeline across 11 modes. It guides projects from literature searches and outlines to citation audits and rebuttal reviews. CX Codex +1 10,800installs nature-figure Yuan1z0825 A skill that builds, revises and audits scientific figures for manuscripts in Python or R. Useful when plots go to submission, not to a report. CX Codex +1 18,800installs academic-paper-reviewer Imbad0202 This skill reviews an academic paper through five role-based perspectives. Use it for peer review, revision checks, or a focused methodology assessment. CX Codex +1 9,800installs nature-polishing Yuan1z0825 A skill that polishes, translates and tightens existing academic prose. Facts, terminology and evidence boundaries stay intact. CX Codex +1 17,500installs nature-citation Yuan1z skill, refactored into static/dynamic layers Finds Nature and CNS-family papers for manuscript claims, maps claims to sources, and prepares a reference-manager export. Use it when the journal scope matters. CX Codex +1 15,600installs

From the same set159

scientific-schematics Creates PNG drafts of scientific diagrams and runs a separate quality review. Use it for neural network architectures, flowcharts, system diagrams, and biological pathways. CX Codex +1 2,200installs scikit-learn A skill for Python machine learning tasks: classification, regression, clustering, preprocessing, and building ML pipelines with scikit-learn 1.9.1. CX Codex +1 2,200installs scientific-slides Builds presentation decks for academic conferences, seminars, and thesis defenses. Supports PowerPoint and LaTeX Beamer with structured layouts, timing guidance, and visual consistency. CX Codex +1 2,200installs peer-review A review skill for scientific manuscripts: checks authorization, picks a reporting guideline, maps claims to evidence and drafts a working assessment. CX Codex +1 2,200installs citation-management Searches OpenAlex, PubMed, and Google Scholar, extracts publication metadata, and builds valid BibTeX references. Helpful when preparing bibliographies for academic manuscripts. CX Codex +1 2,200installs paper-lookup Search scholarly papers, preprints, citations, and open-access full text through 18 APIs. Use it for DOI, PMID, arXiv ID, author, or topic lookups. CX Codex +1 2,300installs database-lookup Queries 80 documented public database APIs with explicit filters, pagination, and provenance. It is useful when scientific or financial facts require reproducible citations. CX Codex +1 2,100installs seaborn A skill that gets your coding agent building seaborn plots from pandas DataFrames: distributions, regressions, pairplots and heatmaps, written against the current API. CX Codex +1 2,100installs