Skip to main content
skill CX Codex

data-cleaning — Claude Code skill: what it does, how to install

data-cleaning audits a messy spreadsheet, agrees cleaning rules with you, then returns an Excel workbook with the clean table, a row-by-row log and the duplicates it would not merge on its own.

Apache-2.0 ★ 12,746 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add genspark-ai/genoffice --skill data-cleaning -a claude-code
Open on GitHub

What data-cleaning does

The skill opens with an audit of the sheet: what each field means, how many cells are blank per column, text sitting in a number column, date formats that disagree. It lists what it found. Then it asks where the table is going, because a system import and a one-off analysis want different shapes, and the answer sets the target format.

Rules come next, one per kind of problem: what happens to blank cells, which columns identify a duplicate and which record survives a conflict, how dates and numbers get formatted, which lookup table resolves aliases. You confirm the rules before any cleaning runs. Nothing is deleted or merged without your explicit yes.

Cleaning happens in a fresh table; the original stays untouched. You get an Excel workbook with five sheets: raw data, the cleaned result, the rules, a change log and the suspected duplicates. The reply carries row counts and the row numbers that need a human decision. Mixed units are not guessed at — if a column holds both metres and kilometres, the skill asks which basis to use and writes the factor into the rules sheet.

What it helps with

  • merge exports from several systems into one standard table
  • drop duplicates on a confirmed key
  • normalise dates and numbers across sources
  • account for every row that was deleted
  • flag records that need a human decision

Example prompts for the agent

  • Clean customers_export.xlsx: dedupe on phone number and convert the dates to ISO.
  • Merge these two tables into one standard sheet and keep the change log.
  • Run a health check on this sheet and show me the cleaning rules before you touch anything.

How to install data-cleaning

1Skills CLI (Vercel)

npx skills add genspark-ai/genoffice --skill data-cleaning -a claude-code

2Manually: put the files in place

~/.claude/skills/data-cleaning/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/data-cleaning/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about data-cleaning

How do I install data-cleaning in Claude Code?

Run npx skills add genspark-ai/genoffice --skill data-cleaning -a claude-code. The skill file lands at ~/.claude/skills/data-cleaning/SKILL.md.

What does data-cleaning do?

It inspects the table, agrees cleaning rules with you, then deduplicates and standardises the data in a separate table. The deliverable is an Excel workbook with the result and a log of every changed row.

Can it delete rows on its own?

No. Every rule is sent for confirmation first, and any deletion or merge needs your approval. Records that look alike but have different keys go to the suspected duplicates sheet for you to decide.

Source text

SKILL.md · Apache-2.0
---
name: data-cleaning
description: Define cleaning rules, then deduplicate and standardise dirty data into a clean table with a line-by-line cleaning log, delivered as an Excel workbook
category: data
scenarios: Data cleaning | Deduplication and standardisation | Table merging
quickPrompts: Clean this customer list and remove duplicates | Merge these inconsistently formatted tables into one standard table
metadata:
  version: 1.0.0
---

You are a data-cleaning specialist. The user gives you dirty data (system exports, multi-source merged tables, manually keyed sheets); you deliver a cleaned standard table and a cleaning log that explains every change.

## Workflow

1. Health check first: field meanings, row count, blank rate per column, mixed types (text inside number columns, several date formats), obvious duplicates, inconsistent units and codes, leading / trailing spaces and full-width versus half-width characters. List the findings.
2. Ask about the downstream use (system import / analysis / mailing); the use decides the standard format. When the target system has a field specification, follow it.
3. Set the rules and confirm them: one rule per problem class -- blanks (delete / fill default / keep and flag), dedupe key (which column combination counts as the same record, and which to keep on conflict: newest / most complete / first), date and number formats, text normalisation (case, full/half width, trimming, alias unification such as "Beijing City" and "Beijing"), code mapping tables. Send the rules to the user for confirmation first; anything involving deletion must be confirmed before it runs.
4. Run the cleaning: leave the original data untouched and process by the rules in a new table. Use formulas where possible (TRIM / CLEAN / DATEVALUE / VLOOKUP mappings) so the work can be checked; every modified or deleted record goes into the log.
5. Build the workbook as an Excel workbook with the spreadsheet tools available here. Title it "<Dataset> Cleaning Result".
6. After delivering, summarise: original rows -> deleted / merged / modified counts -> final rows, and list the row numbers that still cannot be decided automatically and need a human look.

## Workbook structure

- Sheet "Raw data": the user's original table as supplied.
- Sheet "Cleaned": the standardised result; unified header names, one type per column, ISO dates, number columns right-aligned.
- Sheet "Cleaning rules": # / Field / Problem / Rule / Rows affected.
- Sheet "Cleaning log": Original row / Field / Old value / New value / Rule # / Action (modify / delete / merge).
- Sheet "Suspected duplicates": the groups judged to be duplicates with the kept record marked, for the user to review.
- When merging several tables, Cleaned keeps a source-table column for traceability.

## Rules

- Never delete data silently; every deletion and merge must trace back to the original row through the log.
- Deduplicate only on confirmed keys; records with similar names but different keys go to Suspected duplicates for the user to decide, never merged on your own.
- National ID numbers, phone numbers and e-mail addresses are only format-checked and standardised, never inferred or completed; for tables with personal data, remind the user to mind the distribution.
- With inconsistent numeric units, ask for the basis before converting and never assume a unit; conversion factors go into the rules sheet.
- When merging tables, align field names and types first; fields with the same name but different meanings across tables are renamed.
- Place or company names that look misspelt are changed only when a mapping table supports it; otherwise mark "suspected" and leave them.

## Output

One Excel workbook (Raw data / Cleaned / Cleaning rules / Cleaning log / Suspected duplicates, five sheets). The reply holds only the row-count summary and the list needing human judgement.

© genspark-ai · Apache-2.0 · genspark-ai/genoffice

Similar skills

All skills for Data and databases →

From the same set65

The whole set →
study-plan study-plan builds a weekly and daily learning schedule from a goal and available time, then delivers it as an Excel workbook. Useful for exam prep and skill learning. CX Codex +1 ★ 12,746repo stars product-launch product-launch turns notes about a new product or feature into a launch plan: timeline, channel checklist, press release and FAQ, delivered as a Word document. CX Codex +1 ★ 12,746repo stars executive-deck executive-deck is a Claude Code skill that builds executive presentations with a conclusion in each slide title. It activates for management updates, board decks, business reviews, and documents turned into slides. CX Codex +1 ★ 12,746repo stars performance-review The performance-review skill turns period goals and results into an evidence-based self-assessment or manager review in a Word document. Use it for goal retrospectives. CX Codex +1 ★ 12,746repo stars onboarding-plan onboarding-plan generates structured 30/60/90-day onboarding spreadsheets with milestones, resources, and manager checkpoints in Excel. CX Codex +1 ★ 12,746repo stars sales-forecast sales-forecast turns historical sales data into an Excel forecast with scenarios and sensitivity analysis. Use it to examine seasonality or plan sales for a chosen horizon. CX Codex +1 ★ 12,746repo stars survey-analyst survey-analyst turns a raw survey export into a cleaned Excel workbook and a Word findings report, cross-tabs and charts included. CX Codex +1 ★ 12,746repo stars swot-strategy swot-strategy conducts SWOT and PEST reviews for a company or product, benchmarks competitors, and compiles an actionable Word document with prioritized initiatives. CX Codex +1 ★ 12,746repo stars

Project sponsors

Companies that keep this analytics open