Data Analysis Toolkit

Sample rows give both models concrete data to work with instead of guessing. The plain English explanation step ensures you understand the output.

Providing the schema in XML tags lets Claude reference exact column names. The 'state your assumptions' instruction prevents silent misinterpretation of ambiguous questions.

Providing the full schema and relationships eliminates guesswork. Asking for comments and assumption flags makes the output reviewable and trustworthy before running against production.

SQL query builder with optimization tips, performance analysis, and edge case handling.

Requiring before/after logging and a summary report turns a cleaning script into an auditable process. Flagging rows for manual review prevents silent data loss.

A/B test design and analysis with sample size calculations, implementation checklist, and results templates.

Listing confounders and asking for assumption checks prevents the common mistake of running a test on data that violates its assumptions. The plain-English interpretation ensures you understand the results.

Starting from the insight rather than the chart type ensures the visualization serves the story. Asking for common mistakes prevents the most frequent data viz errors.

Data visualization advisor with chart selection, design specs, code generation, and storytelling framing.

Requiring a 'so what' for each finding transforms a data dump into actionable insight. The ban on vague language forces specificity that executives can act on.