Skip to main content
skill CX Codex

python-visuals — Claude Code skill for Power BI matplotlib charts

This skill guides an agent through adding Python visuals to PBIR Power BI reports and writing the matplotlib or seaborn scripts behind them.

GPL-3.0 ★ 1,104 updated 2026-10-28

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add data-goblin/power-bi-agentic-development
/plugin install custom-visuals@power-bi-agentic-development
Open on GitHub

What python-visuals does

The skill covers the full build cycle for a Python visual: the agent adds it to a report page with pbir add visual pythonVisual, writes a matplotlib or seaborn script, injects it with pbir visuals python --script-file, and checks the binding through pbir validate. Editing the report JSON by hand is off limits; every change goes through the pbir CLI.

A Python visual renders as a static PNG with no interactivity, and the script must end with plt.show() or nothing appears. Data arrives pre-loaded in a dataset variable that the script should not recreate. Power BI Service only runs a fixed set of packages — matplotlib, seaborn, numpy, pandas, scipy, scikit-learn, statsmodels, pillow — and blocks plotly, bokeh and altair because outbound networking is disabled there; Desktop has no such package restriction.

Before handing a finished script back to the user, the skill dispatches a separate python-reviewer subagent to check it. It also spells out when a Python visual is the wrong tool: Deneb covers cross-filtering and interactive charts, while small inline marks are better served by SVG measures that skip the row cap and timeout entirely.

What it helps with

  • add a Python visual to a PBIR report page
  • write a matplotlib or seaborn script for Power BI
  • review a Python visual script before it goes into a report
  • decide between a Python visual, Deneb, or an SVG measure
  • inject a finished script into a visual through pbir

Example prompts for the agent

  • Add a Python visual showing sales by date as a bar chart
  • Write a seaborn script for the PythonChart visual and inject it with pbir
  • Check whether this Python visual script will fit the Power BI Service timeout

How to install python-visuals

1Plugin marketplace

/plugin marketplace add data-goblin/power-bi-agentic-development
/plugin install custom-visuals@power-bi-agentic-development

This installs the whole custom-visuals plugin with all its skills

2Skills CLI (Vercel)

npx skills add data-goblin/power-bi-agentic-development --skill python-visuals -a claude-code

3Manually: put the files in place

~/.claude/skills/python-visuals/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/python-visuals/

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

Questions about python-visuals

How do I install python-visuals in Claude Code?

Run /plugin marketplace add data-goblin/power-bi-agentic-development, then /plugin install custom-visuals@power-bi-agentic-development.

What does the python-visuals skill do?

It walks an agent through building Python visuals in PBIR reports: adding the visual through pbir, writing a matplotlib or seaborn script, injecting it, and validating the binding.

Which libraries work in Power BI Service Python visuals?

Service supports matplotlib, seaborn, numpy, pandas, scipy, scikit-learn, statsmodels and pillow, but blocks plotly, bokeh and altair since networking is disabled there.

Similar skills

All skills for Data and databases →

From the same set59

The whole set →
executing-spark executing-spark is a Claude Code skill that runs Python or PySpark on Fabric Spark through Livy without creating a notebook. It supports temporary transformations and lakehouse table queries. CX Codex +1 ★ 1,104repo stars modifying-theme-json modifying-theme-json manages Power BI report themes via the pbir CLI: creates themes, changes palette and fonts, promotes visual formatting into the theme, clears local overrides. CX Codex +1 ★ 1,104repo stars creating-good-dashboards creating-good-dashboards enforces visual clarity and comment protocols when building or styling Claude dashboards, applying principles from Edward Tufte, Stephen Few, and Ben Shneiderman. CX Codex +1 ★ 1,104repo stars te2-cli The te2-cli skill helps Claude Code work with Tabular Editor 2 from the command line, from running scripts to checking and deploying models. Use it when automating Power BI model tasks. CX Codex +1 ★ 1,104repo stars power-query Drafts, inspects, and verifies Power Query M expressions in semantic model partitions while protecting query folding. CX Codex +1 ★ 1,104repo stars r-visuals r-visuals is a Claude Code skill for creating R visuals, including ggplot2 statistical charts, in PBIR reports. CX Codex +1 ★ 1,104repo stars help-me-get-started help-me-get-started walks Power BI people new to coding agents through setup, explaining terms in plain language along the way. CX Codex +1 ★ 1,104repo stars semantic-model semantic-model guides tabular data modeling for Power BI and Analysis Services from the terminal across design, refresh, and review tasks. CX Codex +1 ★ 1,104repo stars

Project sponsors

Companies that keep this analytics open