Verified:GitHub

marimo-pair

Execute and mutate marimo notebook cells programmatically for interactive AI pair programming.

3|Updated May 11, 2026

Search Tags:#agent skills #reactive programming #marimo #artifact creation #python notebooks #cell editing #HTTP kernel execution

Ready to run

npx skills add https://github.com/JeromyJSmith/lattice-platform --skill marimo-pair-jeromyjsmith

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: marimo-pair
Source: https://github.com/JeromyJSmith/lattice-platform/tree/main/.agents/skills/marimo-pair
Command: npx skills add https://github.com/JeromyJSmith/lattice-platform --skill marimo-pair-jeromyjsmith

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

It removes the friction of building and iterating on reactive Python notebooks by letting an AI work directly inside a running marimo kernel to create/edit cells and produce an artifact the user can trust.

Core Features & Use Cases

Run, inspect, and mutate a live notebook: read cell code, create/edit/delete cells, and run cells so results appear immediately in the user’s browser.
Control via deterministic helper scripts: discover active marimo sessions and execute code through provided Bash scripts without requiring marimo to be installed locally.
Guide notebook structure and safety: follow guard rails for marimo’s code API (async context, use ctx.* for mutations) to avoid silent UI inconsistencies and clobbered edits.

Quick Start

Tell the assistant to work in your currently running marimo session by executing the minimal code needed to locate the target cells and then creating the appropriate cells to implement your change.

Frequently Asked Questions about marimo-pair

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

FAQPage Schema

How do I use AI pair programming inside a running marimo notebook?▼

AI pair programming in a running marimo notebook works by programmatically executing and mutating cells through an HTTP kernel, allowing the assistant to safely read, edit, and run code so reactive graph changes appear live in your browser.

How do I create and mutate notebook cells programmatically without breaking the reactive graph?▼

To create and mutate notebook cells programmatically without breaking the reactive graph, you must follow guard rails for marimo's code API, using async context and ctx.* for mutations to avoid silent UI inconsistencies and clobbered edits.

Do I need marimo installed locally to execute code through an HTTP kernel?▼

You do not need marimo installed locally to execute code through an HTTP kernel, because the workflow uses provided Bash scripts to discover active marimo sessions and execute code deterministically without requiring a local installation.

What is the best way to debug and refactor Python notebooks with reactive programming?▼

The best way to debug and refactor Python notebooks with reactive programming is to let an AI work directly inside the running kernel, targeting exploration and refactoring workflows while ensuring reactive graph changes reflect live in the browser.

Why does editing marimo cells programmatically cause silent UI inconsistencies?▼

Editing marimo cells programmatically causes silent UI inconsistencies when you bypass the async context and code_mode guard rails, which are required to ensure kernel-safe cell mutations and prevent clobbered edits in the reactive graph.