# CSV Quality Auditor

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

- Skill: `qwqqwqis666/csv-quality-auditor-6` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add qwqqwqis666/csv-quality-auditor-6`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qwqqwqis666/csv-quality-auditor-6/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-6

---


# CSV Quality Auditor

Run the bundled auditor before trusting a CSV-shaped input:

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

Use `--delimiter` for comma, semicolon, tab (`tab` or `\t`), or any single
custom character. Prefer `--json` when another tool will consume the result.

Interpret exit codes before processing output:

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

Review each issue's `code`, `row`, and `message`. Fix source data rather than
silencing findings, then rerun the audit until it exits `0`. See
`references/rules.md` for exact rule and counting semantics.