jupyter-live-kernel

A stateful Python REPL maintains variables and context across executions, letting you iteratively build data transformations. This skill connects to a live Jupyter kernel for incremental exploration without resetting state between commands.

Persisting variable state across Python executions requires a live Jupyter kernel. This skill manages a dedicated kernel session to run code and inspect variables, dataframes, and results incrementally across multiple steps.

Yes, a running Jupyter server is required. This skill uses a dedicated kernel management script to start, execute code, inspect variables, and edit notebooks through the live Jupyter kernel.

Yes, you can inspect dataframes and variables. The skill interacts with a live Jupyter kernel to run code and inspect variables, dataframes, and results directly from the agent during exploratory coding.

A stateful Jupyter kernel retains context across executions while a standard REPL resets state. This approach is designed for data science exploration, ML experiments, and API testing where state must persist across steps.

Your kernel loses context because it is not configured for stateful execution. This skill provides a live Jupyter kernel connection designed to persist state across iterative data transformations and exploratory coding.