data-analyst

To analyze CSV data for performance drops, the Skill frames the business question, profiles data quality for nulls and gaps, then generates annotated CTE-structured SQL queries. It produces a structured findings report with Situation, Finding, Evidence, Implication, and Recommendation.

Yes, you can run funnel and cohort analysis on spreadsheet-like inputs. The Skill applies SQL-first insight generation alongside statistical and visual reasoning to execute these workflows, selecting appropriate chart types and explicitly qualifying uncertainty in the final report.

Data quality audits for A/B testing involve profiling nulls, duplicates, date gaps, and referential integrity. The Skill runs pre-analysis framing and profiling checks to prevent incorrect conclusions, ensuring your dataset is clean before generating statistical reasoning and annotated SQL.

This data analysis approach works with CSV, JSON, and spreadsheet-like inputs. It diagnoses performance changes across these formats by generating annotated SQL or code, applying trend, cohort, funnel, and A/B test analysis while reporting findings with a confidence signal.

Turning raw metrics into dashboard insights requires selecting appropriate chart types based on the analysis type. The Skill translates raw data into structured findings, applying dashboarding best practices and reporting results with uncertainty qualification to ensure decisions are trustworthy.

Automated SQL for trend analysis requires clean data to avoid misleading results. The Skill mitigates this by running pre-analysis profiling checks for unexpected values and join issues, but it explicitly qualifies uncertainty and provides a confidence signal to prevent overreliance on flawed inputs.