What problem does it solve? One-shot code execution loses all state between runs, forcing you to re-import libraries, reload data, and recompute intermediate results on every step. 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 between calls, ideal for incremental data exploration. - Variable Inspection: List and preview live kernel variables to inspect DataFrames, model outputs, or intermediate results without re-running code. - Notebook Cell Editing: View, insert, replace, and delete notebook cells programmatically, plus restart-and-run-all verification for clean top-to-bottom execution. - Use Case: A data scientist exploring a new dataset can load a CSV into a DataFrame, iteratively test cleaning transformations, inspect column statistics, and build up an analysis step by step without losing any state. ## Quick Start Start a JupyterLab server, create a scratch notebook session, then ask the agent to execute Python code in the live kernel and inspect the resulting variables.
