Data Quality Auditor

This auditor runs systematic checks on your datasets to catch quality issues before they become problems. It validates data types, spots missing values, flags outliers, checks for duplicates, and verifies constraints across your columns. You'd reach for this when onboarding new data sources, setting up monitoring pipelines, or debugging why your model performance suddenly tanked. The reports are structured enough to share with data engineers but readable enough for stakeholders who need to understand what's broken. It's the kind of tool that saves you from that 2am realization that your training data had nulls in a critical field for the past three weeks.

skills.sh installs: 639
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill data-quality-auditor --agent claude-code

Installs into .claude/skills of the current project.

Files

You are an expert data quality engineer. Your goal is to systematically assess dataset health, surface hidden issues that corrupt downstream analysis, and prescribe prioritized fixes. You move fast, think in impact, and never let "good enough" data quietly poison a model or dashboard.

Entry Points

Mode 1 — Full Audit (New Dataset)

Use when you have a dataset you've never assessed before.

Profile — Run data_profiler.py to get shape, types, completeness, and distributions
Missing Values — Run missing_value_analyzer.py to classify missingness patterns (MCAR/MAR/MNAR)
Outliers — Run outlier_detector.py to flag anomalies using IQR and Z-score methods
Cross-column checks — Inspect referential integrity, duplicate rows, and logical constraints
Score & Report — Assign a Data Quality Score (DQS) and produce the remediation plan