Csv Cleaner

CSV Cleaner

Two-phase workflow: diagnose first, clean second. Never start fixing before knowing what is broken.

Phase 1: Diagnose

Run scripts/diagnose.py on the input file:

python scripts/diagnose.py 

The script reports:

• Encoding (utf-8, latin-1, utf-16, etc.)
• Delimiter (comma, tab, semicolon)
• Quote character and escape behavior
• Header row detection (present, absent, or duplicate)
• Row count
• Column count consistency across rows
• Type inference per column (integer, float, date, string, mixed)
• Null distribution per column
• Duplicate row count

Read the output carefully before doing anything else. The diagnosis tells you which fixes apply.

Phase 2: Clean

Apply fixes in this order:

1. Fix encoding: re-read with detected encoding, write as utf-8.
2. Normalize line endings to \n.
3. Strip BOM and zero-width characters.
4. Fix headers: lowercase, snake_case, replace spaces with underscores, ensure uniqueness.
5. Trim whitespace from every cell.
6. Coerce types where the column is type-consistent.
7. Standardize null representations: empty string, "NA", "null", "n/a" all become empty.
8. Deduplicate exact rows.
9. Validate column count consistency. Flag rows that do not match the header.

Do not silently change data. If a fix alters values, report the count.

Output

Save the cleaned file as -cleaned.csv in the same directory. Always utf-8, always comma-delimited, always with a header row.

Then emit a summary:

````

Diagnosis

Fixes applied

• :
• :

Manual review needed

````

When to refuse

If the file appears to be a different format (Excel binary, JSON, fixed-width), do not try to clean it as CSV. Tell the user what the file actually is and suggest the right tool.

If the file has fewer than 5 rows after deduplication, ask the user whether the input is correct before continuing.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: 0xelitesystem
• Source: 0xelitesystem/claude-skills-templates
• License: MIT
• Homepage: https://elitesystem.ai

Install and usage instructions live in the source repository linked above.