sn-da-excel-workflow

Excel data-analysis multi-step orchestrator. Covers: (1) reading multi-sheet Excel files and counting rows, (2) large-file detection (≥10k rows → automatic Parquet optimization), (3) data cleaning (missing-value handling, text normalization, removal of invalid characters), (4) conditional filtering and category extraction, (5) cross-sheet statistical aggregation, (6) export to Excel/CSV and provide download links. Implements the full flow from data reading to report generation, orchestrating capability sub-skills step by step. **Proactively use this skill in any of the following situations; do not respond with just a few lines of pandas code**: ① The user uses trigger terms: Excel analysis / spreadsheet analysis / data analysis / data cleaning / data statistics / data filtering / data visualization / data export / summary statistics / pivot table / grouped statistics / cross analysis / trend analysis / comparative analysis / outlier detection / deduplication / missing value handling / Excel report / generate report / analyze Excel / data analysis / data cleaning / pivot table; ② The user uploads or specifies a .xlsx / .xls / .csv file and requests analysis, cleaning, statistics, or visualization; ③ The task involves any of: reading multiple sheets, conditional filtering, category aggregation, or chart generation; ④ The user requests exporting a formatted Excel report or a download link. Not for: pure text processing unrelated to tabular data, image analysis (use sn-da-image-caption), or simple single-formula Q&A.