skills.rest
KarlinskyS
KarlinskySCOMMUNITY
Explore all skills by this author →
GitHub

jupyter-live-kernel

Execute Python code in a live Jupyter kernel with persistent state.

Updated Apr 10, 2026
Search Tags:#python#repl#kernel#jupyter#stateful#data-science
One-click install
npx skills add https://github.com/KarlinskyS/hermesSkills --skill jupyter-live-kernel-karlinskys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jupyter-live-kernel
Source: https://github.com/KarlinskyS/hermesSkills/tree/main/data-science/jupyter-live-kernel
Command: npx skills add https://github.com/KarlinskyS/hermesSkills --skill jupyter-live-kernel-karlinskys

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires uv, jupyterlab, hamelnb, and includes scripts (resource) components.

What problem does it solve?

Provides a stateful, iterative Python execution environment by connecting to a live Jupyter kernel, eliminating the need for separate notebook files or one‑shot execution tools.

Core Features & Use Cases

  • Stateful REPL: Variables and imports persist across calls.
  • Execute arbitrary code in any notebook kernel.
  • Inspect and edit notebook cells programmatically.
  • Perfect for data‑science exploration, machine‑learning experimentation, and API testing where code persistence matters.

Quick Start

Use the jupyter-live-kernel skill to run a Python snippet in a live Jupyter kernel and return its output.

Frequently Asked Questions about jupyter-live-kernel

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

FAQPage Schema
How do I run Python code statefully across multiple steps without creating notebook files?▼

You can run Python code statefully by connecting to a live Jupyter kernel, which allows variables and imports to persist across multiple calls. This eliminates the need for separate notebook files or one-shot execution tools.

What's the best way to execute iterative machine-learning experiments with persistent variables?▼

Executing iterative machine-learning experiments is best handled through a stateful Python REPL connected to a live Jupyter kernel, allowing code and variables to persist across iterative computation steps.

Do I need a JupyterLab server and uv installed to use a stateful Python REPL?▼

Yes, you need an active JupyterLab server with uv installed and the hamelnb script accessible to use this stateful Python REPL. These dependencies are required to connect to the live Jupyter kernel.

Can I inspect and edit notebook cells programmatically while running data-science exploration?▼

Yes, you can inspect and edit notebook cells programmatically during data-science exploration. The live Jupyter kernel connection supports executing arbitrary code and manipulating cells without needing separate notebook files.

Why use a live Jupyter kernel instead of one-shot execution tools for API testing?▼

A live Jupyter kernel is used for API testing because it provides stateful execution where variables and imports persist across calls. One-shot execution tools lack this persistence, requiring redundant code re-execution for iterative testing.

Related Skills

Explore More Data & Analytics Skills→
i9wa4i9wa4
11

jupyter-notebook

Execute Jupyter notebooks on local Python kernels and Databricks clusters.

Community
Advanced
samlaggzsamlaggz

jupyter-live-kernel

Launch a stateful Python REPL with a live Jupyter kernel.

Community
Advanced
juliuss1907juliuss1907

jupyter-live-kernel

Execute stateful Python code blocks with a live Jupyter kernel.

Community
Intermediate
automatedigitalautomatedigital
1

jupyter-live-kernel

Execute iterative Python code against a live Jupyter kernel with persistent variables.

Official
Intermediate