skills.rest
luckybbjason1
luckybbjason1COMMUNITY
Explore all skills by this author →
GitHub

jupyter-live-kernel

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

Updated Sep 9, 2026
Search Tags:#python#data science#repl#kernel#jupyter#notebook#iterative execution
One-click install
npx skills add https://github.com/luckybbjason1/trading --skill jupyter-live-kernel-luckybbjason1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jupyter-live-kernel
Source: https://github.com/luckybbjason1/trading/tree/main/.hermes/skills/data-science/jupyter-live-kernel
Command: npx skills add https://github.com/luckybbjason1/trading --skill jupyter-live-kernel-luckybbjason1

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jupyterlab, uv.

What problem does it solve? One-shot code execution loses all state between runs, forcing you to re-import libraries, reload data, and redefine variables on every attempt. This Skill provides a persistent Python REPL backed by a live Jupyter kernel, so variables, imports, and objects survive across executions for true iterative exploration. ## Core Features & Use Cases - Stateful Code Execution: Run Python code against a live kernel where variables, DataFrames, and imports persist across calls. - Variable Inspection: List and preview live kernel variables to inspect 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 dataset, load a CSV into a pandas DataFrame, inspect its shape, try several cleaning transformations, and preview the result at each step without ever reloading the file. ## Quick Start Start a JupyterLab server and use the jupyter-live-kernel skill to run Python code in a persistent scratch notebook so I can explore my data iteratively.

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 Jupyter REST API, then send code with the execute command. Variables, imports, and objects persist across every subsequent execution.

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

Use a live kernel for iterative exploration, data science, and ML work where you build state incrementally. Use one-shot execution for standalone scripts that need no carried-over variables, and a terminal for shell commands, installs, and git.

What are the prerequisites for running a live Jupyter kernel?▼

You need uv installed, JupyterLab installed via uv tool install jupyterlab, and a running Jupyter server. A kernel session must also be started through the Jupyter REST API before code can execute.

Why does the first Jupyter kernel execution time out?▼

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

Can I install extra Python packages for the Jupyter kernel?▼

The kernel uses JupyterLab's Python environment, so packages must be installed into that environment. Install additional packages into the JupyterLab tool environment before importing them in executed code.

Related Skills

Explore More Data & Analytics Skills→
zengbaochengzengbaocheng

jupyter-live-kernel

Start a stateful Jupyter kernel session for iterative Python exploration.

Community
Advanced
agentic-inagentic-in
577

Jupyter Live Kernel

Run interactive Jupyter notebook sessions with live kernel management.

Official
Intermediate
biomaps-infrabiomaps-infra

lib-seaborn

Generate statistical visualizations from data using the seaborn library in Python.

Official
Intermediate
everCokeeverCoke

colab-cli

Automate Colab runtime control and Jupyter integration from the command line.

Community
Advanced