# SKILL: CSV Cleanup Agent Skill

## Purpose
Clean messy CSV data by detecting header issues, encoding problems, duplicates, malformed rows, category drift, and risky transformations.

## When to Use
Use this when the user needs to: Clean messy CSV data by detecting header issues, encoding problems, duplicates, malformed rows, category drift, and risky transformations. It is designed for repeatable agent or automation work, not one-off fluffy prompting.

## Inputs Required
- CSV file or pasted sample
- Target schema
- Required columns
- Deduplication rules
- Output format

## Workflow
1. Inspect headers and sample rows before transforming
2. Report schema mismatches and malformed rows
3. Define safe transformations
4. Preserve raw values where uncertain
5. Return clean output plus change log

## Output Format
Cleaned CSV plan, transformation log, validation checks, and export-ready data structure.

## Quality Rules
- Ground every claim in supplied inputs or clearly mark it as an assumption.
- Prefer specific fields, examples, and decision points over generic advice.
- Include a test command and pass criteria so the skill can be evaluated.
- Keep the output usable by a human first and automation-ready second.

## Guardrails
- Do not send emails, publish posts, contact leads, change calendars, spend money, delete data, or alter production systems without explicit human approval.
- Do not invent facts, private details, legal claims, prices, or external data.
- For web or profile research, use current sources and separate evidence from inference.
- For connected tools, use the minimum permission needed and log the action taken.

## Test Command
Run this skill on a simple example for CSV Cleanup Agent Skill and return the expected output structure plus any missing inputs.