skills.rest
jakubbartnik
jakubbartnikCOMMUNITY
Explore all skills by this author →
GitHub

jupyter-live-kernel

Execute stateful Python code through a live Jupyter kernel with persistent variables.

Updated Aug 19, 2026
Search Tags:#python#data science#repl#exploration#kernel#jupyter#notebook
One-click install
npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill jupyter-live-kernel-jakubbartnik
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jupyter-live-kernel
Source: https://github.com/jakubbartnik/honey-barrel-finale/tree/main/honey-barrel-finale/workspace/hermes/skills/data-science/jupyter-live-kernel
Command: npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill jupyter-live-kernel-jakubbartnik

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? One-shot code execution loses all state between runs, forcing you to re-import libraries, reload data, and rebuild objects every time. This Skill provides a persistent Python REPL backed by a live Jupyter kernel, so variables, imports, and DataFrames survive across executions for true iterative exploration. ## Core Features & Use Cases - Stateful Code Execution: Run Python code against a live kernel where variables, imports, and objects persist across calls. - Variable Inspection: List and preview live kernel variables to inspect DataFrames, models, and intermediate results without re-running code. - Notebook Cell Editing: View, insert, replace, and delete notebook cells, plus restart-and-run-all verification for clean top-to-bottom execution. - Use Case: While exploring a new dataset, load it into a pandas DataFrame once, then iteratively filter, plot, and transform it across many executions, inspecting intermediate variables as you go. ## Quick Start Start a Jupyter kernel session and run my Python exploration code step by step, keeping the DataFrame in memory between each step.

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 with persistent state between executions?▼

Use a live Jupyter kernel as a stateful REPL: start a JupyterLab server, create a kernel session via the REST API, then send code with the execute command. Variables, imports, and objects persist across all subsequent executions.

When should I use a Jupyter kernel instead of one-shot code execution?▼

Use a live kernel for iterative exploration, data science, and tasks where state must persist across steps. Use one-shot execution for stateless scripts, and a terminal for shell commands, builds, and package installs.

How do I inspect variables in a running Jupyter kernel?▼

Use the variables command with the notebook path to list all live variables, or pass a variable name to preview its value. This works for DataFrames, models, and any object held in kernel memory.

Why does the first Jupyter kernel execution time out?▼

The kernel needs time to initialize after the server starts, so the first execution may hit the 30-second default timeout. Retry the execution, or pass a longer timeout such as --timeout 120 for heavy computation.

Can I install packages for the Jupyter kernel environment?▼

The kernel uses JupyterLab's Python environment, so packages must be installed into that environment before use. Install them into the JupyterLab tool environment first, then import them in your executed code.

Related Skills

Explore More Data & Analytics Skills→
kaminocorpkaminocorp
1

jupyter-live-kernel

Execute stateful Python code against a live Jupyter kernel via hamelnb CLI.

Official
Intermediate
zongtingweizongtingwei
25

reporting-and-figure-export

Package analysis outputs into reproducible reports and publication-ready figure exports.

Community
Advanced
lengoctuong2005lengoctuong2005
5

weights-and-biases

Automate logging and tracking of machine learning experiments with wandb.

Community
Advanced
NousResearchNousResearch
227.8k

claude-code

Delegate coding tasks to the Claude Code CLI agent for features, refactoring, and PR reviews.

Official
Intermediate