marimo-pair

Execute code and manage cells in running marimo notebook kernels via HTTP API.

3|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/legout/pi-config --skill marimo-pair-legout
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: marimo-pair
Source: https://github.com/legout/pi-config/tree/main/installed-skills/marimo-pair
Command: npx skills add https://github.com/legout/pi-config --skill marimo-pair-legout

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bash, curl, jq, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill bridges the gap between AI agents and interactive data science by allowing direct, programmatic control over running marimo notebooks, enabling real-time code execution and UI manipulation.

Core Features & Use Cases

  • Reactive Notebook Control: Programmatically create, edit, and execute cells within a live marimo kernel.
  • Dynamic UI Interaction: Manipulate anywidget state and reactive variables to build custom data visualizations and interactive dashboards.
  • Use Case: Use this skill to build a custom data analysis dashboard where the agent dynamically creates cells to process data and updates UI widgets to reflect the results in real-time.

Quick Start

Use the marimo-pair skill to discover the running notebook server and execute the code in the current session.

Frequently Asked Questions about marimo-pair

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I programmatically control a running marimo notebook kernel?

Programmatic control of a running marimo notebook is achieved by interfacing with its HTTP API and server registry using bash, curl, and jq to execute code and manage reactive cells.

Can an AI agent dynamically create and execute cells in a reactive Python notebook?

An AI agent can dynamically create, edit, and execute cells in a reactive Python notebook by interfacing with the active marimo kernel to construct real-time data dashboards.

Do I need bash and curl to interact with marimo reactive notebooks?

You need bash, curl, and jq to interface with the marimo HTTP API and server registry, enabling programmatic code execution and reactive variable management within active Python environments.

What is the best way to manipulate anywidget state in a live Python data science notebook?

Manipulating anywidget state in a live Python data science notebook involves programmatic interactions with the running marimo kernel to update UI widgets and reactive variables reflecting data processing results.

How does reactive notebook control facilitate automated data analysis and dashboard construction?

Reactive notebook control facilitates automated data analysis by enabling programmatic code execution and dynamic UI manipulation to build interactive dashboards within active Python environments.