# CSV Quality Auditor

> Audit CSV files for blank or duplicate headers, inconsistent row widths, and fully empty data rows. Use when validating CSV structure before import, analysis, or handoff.

- Skill: `qwqqwqis666/csv-quality-auditor-4` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add qwqqwqis666/csv-quality-auditor-4`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qwqqwqis666/csv-quality-auditor-4/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Data & Analytics
- Author: qwqqwqis666 (https://skillmd.com/u/qwqqwqis666)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/qwqqwqis666/csv-quality-auditor-4

---


# CSV Quality Auditor

Run the bundled auditor before consuming a CSV file:

```bash
python scripts/audit_csv.py INPUT [--delimiter DELIM] [--json]
```

Use `--delimiter comma`, `semicolon`, or `tab`, their literal character, or one
custom character. The default is a comma.

Interpret exit status as follows:

- `0`: the CSV is readable and no quality issues were found.
- `1`: the CSV is readable but has one or more quality issues.
- `2`: arguments, reading, or CSV parsing failed.

Prefer `--json` when another tool will consume the result. Inspect every entry
in `issues`, fix the source data, and rerun until the command exits `0`.

See [references/rules.md](references/rules.md) for exact detection and counting
rules. Do not silently rewrite the input file.