Skip to content
Get packs

Data Cleaning Specialist

Deduplicate and standardise messy tables into a clean Excel workbook with a full change log

Source Download skill
Repository
genspark-ai/genoffice
Stars
11,537
Licence
Apache-2.0
Files
1 file

What it does

When installed, the agent works as a data-cleaning specialist for messy spreadsheets or exported tables. It first checks the data for problems such as blanks, mixed date formats, stray spaces and duplicates, then proposes cleaning rules and asks you to confirm them before anything is deleted. The result is a new Excel workbook with the original data untouched, a standardised table, a log of every change, and a list of suspected duplicates for you to review.

Great for

  • Analysts or operations staff who receive exports from several systems and need one consistent table
  • Anyone merging inconsistently formatted spreadsheets into a single standard layout
  • People who need an auditable record of exactly which values were changed or removed

Skip it if

  • Tables containing sensitive personal data such as ID numbers, phone numbers or emails, where the output file should be handled carefully because it is distributed as a spreadsheet; the skill itself only format-checks these fields
  • Situations where you need fully automatic deletion without review, since the skill is designed to ask for confirmation before any deletion runs
  • Very large datasets, since the workflow relies on the agent's spreadsheet tools and step-by-step confirmation

Try asking

  • “Clean this customer list and remove duplicates”
  • “Merge these inconsistently formatted tables into one standard table”
  • “Check this sales export for blanks, mixed date formats and extra spaces, then propose cleaning rules”
Step-by-step guide: how to use Data Cleaning SpecialistInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    data-cleaning.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip data-cleaning.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip data-cleaning.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Tell the agent the downstream use (system import, analysis or mailing) up front, since that determines the standard format.
  • Review the proposed rules carefully before confirming, especially the dedupe key and which record to keep on conflict.
  • Check the Suspected duplicates sheet and the list of row numbers needing human judgement before using the cleaned table.

What's inside

  • SKILL.md

Redistributed unmodified from genspark-ai/genoffice under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.