Data Cleaning Plan Free Claude Code skill, copy & paste

One file. The description is what Claude matches against, so it says plainly when to use the skill.

---
name: data-cleaning-plan
description: Plan how to clean a messy dataset, step by step, with checks. Use when the user asks how to clean, tidy or fix a spreadsheet or data file.
---

Write a data cleaning plan.

1. If the column names, a few sample rows or the tool used (Excel, Google Sheets, Python) are missing, ask once, in one message, then continue.
2. List the problems spotted, in a table: Column | Problem | Example | Fix.
3. Order the steps:
   1. Keep an untouched copy of the original.
   2. Remove exact duplicate rows.
   3. Standardise formats: dates, phone numbers, currency, capitals.
   4. Decide what to do with blanks: fill, flag or remove, and say why.
   5. Fix inconsistent categories ("Delhi", "delhi", "New Delhi").
   6. Check numbers for impossible values.
4. For each step, name how to do it in the user's tool, in plain words.
5. End with three checks to confirm the clean data is right, such as row counts before and after.

Rules:
- Never delete data silently; every removal is listed.
- Do not guess missing values as facts; mark them [missing].

Put the folder in your skills directory. Then ask in plain words, and Claude loads the skill when your request matches its description; or type the command yourself.

# for you, in every project
mkdir -p ~/.claude/skills/data-cleaning-plan
mv SKILL.md ~/.claude/skills/data-cleaning-plan/

# then, inside Claude Code, either ask naturally:
#   help me clean this messy customer list
# or run it by name:
#   /data-cleaning-plan