data-quality-auditor

Audit CSV datasets for quality issues and generate remediation reports.

Updated Apr 16, 2026

Search Tags:#audit #profiling #data-quality #outliers #missing-values #data-quality-score

Ready to run

npx skills add https://github.com/devCharuzu/philfida-taskmanage --skill data-quality-auditor-devcharuzu

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-quality-auditor
Source: https://github.com/devCharuzu/philfida-taskmanage/tree/main/.windsurf/skills/data-quality-auditor
Command: npx skills add https://github.com/devCharuzu/philfida-taskmanage --skill data-quality-auditor-devcharuzu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Data quality issues in datasets lead to misleading analyses and poor decision-making. This skill systematically audits datasets for completeness, consistency, validity, and accuracy, surfaces anomalies, and produces an actionable remediation plan.

Core Features & Use Cases

Per-column profiling to understand data types, nulls, cardinality, and distributions.
Missing-value analysis to identify mechanisms (MCAR/MAR/MNAR) and recommended imputations.
Outlier detection with IQR, Z-score, and robust methods, contextualized by business impact.
Cross-column checks for referential integrity, duplicates, and logical constraints.
DQS computation and remediation playbooks; supports full audits, targeted scans, and ongoing monitoring.

Quick Start

Run data_profiler.py on a CSV file to generate the initial DQS audit report.

Frequently Asked Questions about data-quality-auditor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I audit CSV data quality and identify missing values or outliers?▼

Data profiling analyzes individual columns in a dataset to understand data types, null counts, cardinality, and distributions. It serves as the foundation for detecting completeness issues, spotting anomalies, and validating data consistency before deeper analysis.

What is the best way to detect outliers and missing values across multiple columns in a CSV file?▼

Run a Python data profiler script on the CSV file to detect outliers and analyze missing values. It applies IQR and Z-score methods for outlier identification, classifies missing data mechanisms (MCAR, MAR, MNAR), and recommends appropriate imputation strategies.

How do I generate an actionable data quality remediation playbook from a CSV audit?▼

Run a Python audit script on the CSV file to generate a remediation playbook. The script computes the Data Quality Score, identifies anomalies and missing values, and outputs an exportable report with targeted, actionable fixes for each identified issue.

Can I perform referential integrity and cross-column consistency checks during a data quality audit?▼

Yes, the audit performs cross-column checks to validate referential integrity, duplicates, and logical constraints. It evaluates these consistency rules across multiple columns and surfaces violations within an exportable report for remediation.

Does Python data profiling support ongoing monitoring and targeted scans for streaming-like data profiles?▼

Yes, the profiling approach supports ongoing monitoring and targeted scans for streaming-like data profiles. You can execute continuous or focused audits on specific columns to track completeness, validity, and anomalies over time.

What are the limitations of using Python scripts for data quality audits?▼

Python script audits are limited to static CSV datasets and streaming-like data profiles. They cannot directly query live databases without prior export, and running full audits on extremely large datasets may impact processing performance.