AutoGineer
Generated banner for Clean Data Xls
Generated logo for Clean Data Xls

Clean Data Xls

AnthropicOfficialPublished by Anthropic

  • Skill
  • Workflow
  • Documents and content
  • Apache-2.0
  • No issues found
Download ZIP

From the author

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".
— the description by Anthropic

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured approach to cleaning spreadsheet data by identifying and resolving common inconsistencies such as whitespace, casing errors, mixed data types, and formatting issues. It emphasizes transparency by preferring the use of helper columns with formulas for transformations, ensuring that data processing remains auditable. The workflow includes profiling the data, proposing specific fixes, and confirming destructive operations with the user before execution.

What it does

  • Profiles spreadsheet columns to detect data types and identify outliers.
  • Identifies common data issues like inconsistent casing, whitespace, and mixed date formats.
  • Generates a summary table of detected issues and proposed fixes for user review.
  • Applies transformations using helper columns to maintain an audit trail.
  • Handles destructive operations like deduplication with explicit user confirmation.
  • Provides a before-and-after summary report of all changes made.

When to use it

  • When preparing raw spreadsheet data for analysis or reporting.
  • When dealing with inconsistent data entries from multiple sources.
  • When you need to standardize formats like dates or currency across a large dataset.
  • When you need to identify and remove duplicate records in a sheet.
  • When you need to fix encoding issues or non-printing characters in your data.

Advantages

  • Maintains data integrity by using non-destructive helper columns.
  • Provides transparency through a pre-execution summary of proposed changes.
  • Reduces manual effort in cleaning large or complex datasets.
  • Ensures user control by requiring confirmation for destructive actions.
  • Standardizes data formats for better compatibility with analysis tools.

Usage examples

“Clean this data”
The agent profiles the active sheet, identifies inconsistencies like whitespace and casing, and presents a summary table of proposed fixes.
“Dedupe my spreadsheet”
The agent scans for exact and near-duplicate rows, shows a sample of the duplicates found, and asks for confirmation before removing them.
“Standardize this column”
The agent analyzes the selected column for mixed date formats or number-as-text issues and creates a helper column with standardized values.
“This data is messy”
The agent performs a full audit of the active sheet, flagging mixed types, errors, and formatting inconsistencies for the user to review.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/anthropics/clean-data-xls/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip clean-data-xls.zip -d .agents/skills

Documentation by Anthropic

Clean Data

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

Environment

  • If running inside Excel (Office Add-in / Office JS): Use Office JS directly (Excel.run(async (context) => {...})). Read via range.values, write helper-column formulas via range.formulas = [["=TRIM(A2)"]]. The in-place vs helper-column decision still applies.

  • If operating on a standalone .xlsx file: Use Python/openpyxl.

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
IssueWhat to look for
Whitespaceleading/trailing spaces, double spaces
Casinginconsistent casing in categorical columns (usa / USA / Usa)
Number-as-textnumeric values stored as text; stray $, ,, % in number cells
Datesmixed formats in the same column (3/8/26, 2026-03-08, March 8 2026)
Duplicatesexact-duplicate rows and near-duplicates (case/whitespace differences)
Blanksempty cells in otherwise-populated columns
Mixed typesa column that's 98% numbers but has 3 text entries
Encodingmojibake (é, ’), non-printing characters
Errors#REF!, #N/A, #VALUE!, #DIV/0!
Step 3: Propose fixes

Show a summary table before changing anything:

ColumnIssueCountProposed 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

Files

Requirements and compatibility

Written for: Claude Code, Claude apps

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Anthropic
Publisher
Anthropic (Official)
Source
anthropics/financial-services · plugins/vertical-plugins/financial-analysis/skills/clean-data-xls · commit 6056506
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Anthropic.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download clean-data-xls.zip