What problem does it solve? Data analysis tasks often require multi-step queries, iterative exploration, and visualizations, but without clear guidance notebooks end up with failed cells, wrong libraries, or inefficient BigQuery access patterns. This Skill enforces a structured, validated notebook workflow for data analysis on Google Cloud. ## Core Features & Use Cases - Conditional Execution Flow: Adapts behavior based on tool availability, using an incremental generate-execute-validate loop when cell execution is possible, or generating a complete notebook for user execution otherwise. - BigQuery Integration via BigFrames: Enforces use of %%bqsql magics instead of the Python BigQuery client, with mandatory dataframe export and BigFrames-based manipulation and ML. - Notebook Structure & Visualization Rules: Defines a story-like layout with markdown sections, plotting rules, data cleaning constraints, and a standardized final summary. - Use Case: A user asks to explore user retention trends in a BigQuery table. The Skill guides querying with %%bqsql, validating each cell's output, plotting trends with distinct colors, and ending with a grounded summary of key findings. ## Quick Start Create a Jupyter notebook that analyzes sales trends from my BigQuery table and visualizes the key findings.
