jupyter-live-kernel

Execute multi-line Python code against a live Jupyter kernel with persistent state.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/thisismynewfmail-ui/Monika-agent --skill jupyter-live-kernel-thisismynewfmail-ui
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: jupyter-live-kernel
Source: https://github.com/thisismynewfmail-ui/Monika-agent/tree/main/skills/data-science/jupyter-live-kernel
Command: npx skills add https://github.com/thisismynewfmail-ui/Monika-agent --skill jupyter-live-kernel-thisismynewfmail-ui

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a persistent, stateful Python execution environment so you can iteratively build, inspect, and refine code without losing variables or context between runs. This eliminates the friction of rerunning entire scripts for small experiments and supports rapid data exploration, debugging, and ML iteration.

Core Features & Use Cases

  • Stateful REPL: Execute multi-line Python snippets against a live Jupyter kernel where imports, variables, and objects persist across calls.
  • Kernel & Notebook Management: Discover running servers and notebooks, create sessions, inspect live variables, and edit notebook cells via the hamelnb CLI with structured JSON output.
  • Verification and Control: Restart kernels, run notebooks top-to-bottom for verification, and configure execution timeouts for long-running tasks.
  • Use Case: Iteratively explore a large DataFrame, run transformations step-by-step, preview intermediate variables, and finalize a reproducible notebook once analysis stabilizes.

Quick Start

Start a headless Jupyter server, create a scratch.ipynb session, and run iterative Python snippets with the hamelnb execute command to inspect live variables and refine code.

Frequently Asked Questions about jupyter-live-kernel

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

FAQPage Schema
How do I execute multi-line Python code and keep variables persistent across runs?

A stateful Python REPL connected to a live Jupyter kernel maintains persistent variables, imports, and objects across multiple multi-line code executions, enabling iterative data exploration without rerunning scripts.

How do I inspect live variables in a Jupyter kernel during interactive data exploration?

You can inspect live variables in a Jupyter kernel by executing Python snippets via the hamelnb CLI, which returns structured JSON output detailing the current state of variables for interactive data exploration.

Can I manage Jupyter notebook sessions and edit cells directly from the command line?

Yes, you can manage Jupyter notebook sessions and edit cells directly via the hamelnb CLI, which supports discovering running servers, creating sessions, and editing notebook cells with structured JSON output.

What is the best way to iteratively explore a large DataFrame without losing context?

Using a stateful Python REPL provides the best way to iteratively explore a large DataFrame, allowing you to run transformations step-by-step, preview intermediate variables, and finalize a reproducible notebook.

How do I handle long-running tasks and restart Jupyter kernels for machine learning experiments?

You can handle long-running tasks by configuring execution timeouts, and you can restart Jupyter kernels or run notebooks top-to-bottom for verification using the hamelnb CLI during machine learning experiments.

Does the stateful Jupyter kernel REPL support API prototyping and debugging workflows?

Yes, the stateful Jupyter kernel REPL supports API prototyping and debugging workflows by providing persistent kernel state and variable inspection, allowing iterative code execution and refinement.