# CSV Quality Auditor

> Audit CSV files for blank or duplicate headers, inconsistent row widths, and fully empty data rows. Use when Codex needs a deterministic, dependency-free structural quality check of comma-, semicolon-, tab-, or custom-delimited text data.

- Skill: `qwqqwqis666/csv-quality-auditor-8` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add qwqqwqis666/csv-quality-auditor-8`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qwqqwqis666/csv-quality-auditor-8/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-8

---


# CSV Quality Auditor

Run the bundled auditor before analyzing, importing, or transforming a CSV file.

## Workflow

1. Choose the delimiter from the file specification or a known sample. Do not guess from the filename.
2. Run:

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

3. Interpret exit status `0` as clean, `1` as quality issues found, and `2` as a usage, read, or parse failure.
4. Use `--json` when another tool will consume the result. Preserve issue row numbers when reporting or repairing data.
5. Read [references/rules.md](references/rules.md) when exact rule semantics or output fields matter.

Pass a literal tab or `\t` for tab-delimited input. Pass any other single character for a custom delimiter. Quote delimiters in the shell when they have special meaning.