product-data-cleanup

# /product-data-cleanup — Product Data Normalizer Takes a messy FF&E schedule and normalizes everything: casing, dimensions, units, language, materials vocabulary, currency formatting, and duplicates. Outputs a clean, consistent, spec-ready schedule. Operates on the **master Google Sheet** — the same 33-column schema used by all product skills. Also works on standalone CSV files and pasted tables. ## Input The user provides a schedule in one of these ways: 1. **Master Google Sheet** — the shared product library. Provide spreadsheet ID or URL. 2. **File path** — a `.csv`, `.tsv`, `.xlsx` export, or `.md` file 3. **Pasted table** — markdown or tab-separated data in the message If the input format is unclear, ask. ## Cleanup Rules ### 1. Casing | Field | Rule | Example | |-------|------|---------| | Product Name | Title Case | `eames lounge chair` → `Eames Lounge Chair` | | Brand | Title Case, preserve known abbreviations | `HERMAN MILLER` → `Herman Miller`, `HAY` → `HAY` | | Collection | Title Case | `cosm` → `Cosm` | | Category | Title Case, singular | `chairs` → `Chair`, `TABLES` → `Table` | | Materials | Sentence case, lowercase after first word | `MOLDED PLYWOOD, FULL GRAIN LEATHER` → `Molded plywood, full grain leather` | | Colors/Finishes | Title Case per item | `walnut/black leather` → `Walnut / Black Leather` | **Known brand abbreviations to preserve**: HAY, USM, B&B, DWR, CB2, HBF, OFS, SitOnIt, 3form, ICF ### 2. Category Normalization Map free-text categor...