Skip to content
Get packs

Matplotlib Plotting

Lets the agent create, style, and export Python Matplotlib plots (PNG, PDF, SVG) for scientific work.

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
7 files

What it does

Once installed, the agent follows this skill's guidance for building charts in Matplotlib, Python's standard plotting library. It knows how to build line, scatter, bar, histogram, heatmap, contour, box and 3D plots, arrange multi-panel figures, customise colours and fonts, and save publication-ready image files. It also ships ready-made Python scripts and style presets that it can run to generate example plots or custom style sheets.

Great for

  • Researchers or students who need precise, publication-quality figures from Python data
  • Developers who want an agent to write and debug Matplotlib code with correct modern API usage
  • Anyone migrating older Matplotlib code to version 3.11 conventions

Skip it if

  • Quick statistical charts or interactive dashboards; the skill itself points to seaborn or plotly for those
  • Running the bundled scripts on machines where you have not reviewed the code first, since the agent will execute Python files on your computer

Try asking

  • “Make a two-panel figure of my experiment results with error bars and export it as a 300 dpi PDF”
  • “Create a heatmap of this correlation matrix with a labelled colourbar and save it as SVG”
  • “Apply a publication style preset to my existing plotting script and check the output”
  • “Convert this old boxplot code to the current Matplotlib 3.11 API”
Step-by-step guide: how to use Matplotlib PlottingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 7 original files, the MIT licence and an attribution note.

    matplotlib.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip matplotlib.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip matplotlib.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Review scripts/plot_template.py and scripts/style_configurator.py before letting the agent run them, and run them in a virtual environment.
  • Specify the output format and dpi you need (for example PDF at 300 dpi) so the agent picks the right savefig settings.
  • For multi-panel journal figures with strict styling, the skill recommends a separate scientific-visualization skill instead.

What's inside

  • references/api_reference.md
  • references/common_issues.md
  • references/plot_types.md
  • references/styling_guide.md
  • scripts/plot_template.py
  • scripts/style_configurator.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.