---
name: clean-data-xls
description: Clean up messy spreadsheet data — trim whitespace, fix inconsistent casing, convert numbers-stored-as-text, standardize dates, remove duplicates, and flag mixed-type columns. Use when data is messy, inconsistent, or needs prep before analysis. Triggers on "clean this data", "clean up this sheet", "normalize this data", "fix formatting", "dedupe", "standardize this column", "this data is messy".
---

# Clean Data

## India

This skill operates on **Indian markets**. Load **`india-market-conventions`**
before building anything, and **`india-market-data`** for sources. Two rules cause
most Indian errors:

- **Fiscal year is April–March.** `FY2025` = year ending **31 Mar 2025**; `Q1 FY26` =
  Apr–Jun 2025. Label periods `Q3 FY26 (Oct–Dec 25)`, never a bare calendar year.
  Never annualise a quarter without stating the fiscal offset.
- **Units are lakh (10⁵) and crore (10⁷).** Never use the Excel format
  `#,##0,," Cr"` — each trailing comma divides by 1,000, so that format displays
  **lakh under a crore label: a 100× error**. Divide by `10000000` in a live
  formula and label the column `Total Revenue (₹ Cr)`.

What has no Indian equivalent is listed in `NOT-ADAPTABLE.md`. Name the gap —
never substitute a proxy and present it as the real thing.

Clean messy data in the active sheet or a specified range.

## Environment

- Operate on the .xlsx with the `officecli` CLI. Read with `officecli get <file> <path>` or `officecli view <file> text`; write helper-column formulas with `--prop formula="TRIM(A2)"`. The in-place vs helper-column decision still applies.
- Load **`xlsx-author`** for the build loop and **`officecli-xlsx`** for the element vocabulary.

## Workflow

### Step 1: Scope

- If a range is given (e.g. `A1:F200`), use it
- Otherwise use the full used range of the active sheet
- Profile each column: detect its dominant type (text / number / date) and identify outliers

### Step 2: Detect issues

| Issue | What to look for |
|---|---|
| Whitespace | leading/trailing spaces, double spaces |
| Casing | inconsistent casing in categorical columns (`usa` / `USA` / `Usa`) |
| Number-as-text | numeric values stored as text; stray `$`, `,`, `%` in number cells |
| Dates | mixed formats in the same column (`3/8/26`, `2026-03-08`, `March 8 2026`) |
| Duplicates | exact-duplicate rows and near-duplicates (case/whitespace differences) |
| Blanks | empty cells in otherwise-populated columns |
| Mixed types | a column that's 98% numbers but has 3 text entries |
| Encoding | mojibake (`é`, `’`), non-printing characters |
| Errors | `#REF!`, `#N/A`, `#VALUE!`, `#DIV/0!` |

### Step 3: Propose fixes

Show a summary table before changing anything:

| Column | Issue | Count | Proposed Fix |
|---|---|---|---|

### Step 4: Apply

- **Prefer formulas over hardcoded cleaned values** — where the cleaned output can be expressed as a formula (e.g. `=TRIM(A2)`, `=VALUE(SUBSTITUTE(B2,"$",""))`, `=UPPER(C2)`, `=DATEVALUE(D2)`), write the formula in an adjacent helper column rather than computing the result in Python and overwriting the original. This keeps the transformation transparent and auditable.
- Only overwrite in place with computed values when the user explicitly asks for it, or when no sensible formula equivalent exists (e.g. encoding/mojibake repair)
- For destructive operations (removing duplicates, filling blanks, overwriting originals), confirm with the user first
- After each category of fix (whitespace → casing → number conversion → dates → dedup), show the user a sample of what changed and get confirmation before moving to the next category
- Report a before/after summary of what changed