spreadsheet hidden problem finder

The problem

Data quality issues in spreadsheets often stay hidden until they break a production pipeline or skew a report. Manually hunting for whitespace, mixed casing, and statistical outliers across thousands of rows is slow and error-prone.

What it does

• Identifies missing values, duplicate rows, and type mismatches across .xlsx, .csv, and .tsv files.
• Detects statistical outliers using IQR and flags inconsistent categorical data.
• Generates an annotated .xlsx workbook with problem cells highlighted in red/amber and detailed explanatory comments.
• Produces a Markdown audit report summarizing sheet counts, findings by check type, and data limitations.
• Maintains original data integrity by never modifying the source file in place.

Frameworks & tools

Python, pandas, openpyxl, and xlrd.

Why this beats prompting it yourself

A simple LLM prompt cannot visually highlight specific cells in a downloadable Excel file or reliably run statistical outlier detection on large datasets. This skill uses deterministic Python scripts to ensure 100% accuracy in finding errors that LLMs frequently hallucinate or overlook.

Use cases

• Audit messy CSV exports before importing them into a database.
• Scan financial models for broken formulas and spreadsheet error values.
• Validate large datasets against specific regex rules or allowed-value lists.
• Find duplicate records and referential integrity gaps in multi-sheet workbooks.

Known limitations

Does not recalculate formulas; audits only cached values. Annotated output for CSV/TSV files is converted to XLSX to support cell comments and styling.