What problem does it solve? Data analysis tasks often require multi-step queries, iterative exploration, and visualizations that are hard to manage in one-off scripts. This Skill provides structured rules for building, executing, and validating Jupyter notebooks, especially when querying BigQuery, so analyses are reproducible, readable, and error-free. ## Core Features & Use Cases - Conditional Execution Workflow: Enforces a generate-cell, execute-cell, validate-output loop when an execution tool is available, or full-notebook generation with user-run verification when it is not. - BigQuery Integration Rules: Mandates the %%bqsql BigFrames magic for SQL queries, forbids the Python BigQuery client library, and requires BigFrames (not pandas or scikit-learn) for data manipulation and ML. - Notebook Structure & Storytelling: Defines a layout of markdown headers, small logical cells, visualizations, and a final summary with Q&A, key findings, and next steps. - Use Case: A user asks to explore crime trends in a BigQuery dataset. The Skill guides kernel selection, library checks, step-by-step %%bqsql queries, plotting with proper figure sizing, and a grounded summary of findings. ## Quick Start Ask the assistant to analyze a BigQuery table in a Jupyter notebook and visualize the key trends it finds.
