Does it support international privacy regulations?

Yes, it includes built-in compliance checklists and validation rules for GDPR (EU), HIPAA (US Healthcare), CCPA (California), and PCI DSS.

Can I customize the anonymization methods?

Absolutely. You can configure the skill to use suppression, generalization, pseudonymization, perturbation (adding noise), or tokenization depending on your specific data utility needs.

What types of PII can this skill detect?

The skill detects direct identifiers like SSN, email, and phone numbers, quasi-identifiers such as zip codes and birth dates, and sensitive attributes like medical or financial records.

How does it prevent data leakage in synthetic data?

It uses statistical leakage scores to detect exact and partial matches between synthetic and original records, ensuring the AI hasn't simply memorized sensitive input data.

Privacy Checker & Anonymizer

Name: Privacy Checker & Anonymizer
Author: ksmuvva

byksmuvva

Data Science & ML

Detects PII, anonymizes sensitive information, and ensures regulatory compliance during synthetic data generation and processing.

About

The Privacy Checker skill is a comprehensive toolkit for developers managing sensitive datasets within Claude Code. It automates the detection of Personally Identifiable Information (PII), applies advanced anonymization techniques like pseudonymization and perturbation, and performs rigorous privacy risk assessments using metrics such as k-anonymity and differential privacy. By integrating compliance checks for GDPR, HIPAA, and CCPA, this skill ensures that synthetic data generation and data processing workflows remain secure, preventing accidental data leakage and meeting strict regulatory requirements.

Key Features

Automated PII detection for direct identifiers, quasi-identifiers, and sensitive attributes
Privacy risk assessment metrics including K-Anonymity, L-Diversity, and T-Closeness
Comprehensive anonymization techniques including suppression, generalization, and tokenization
Advanced data leakage detection to prevent synthetic data from mirroring real-world records
Regulatory compliance checking for GDPR, HIPAA, CCPA, and SOC 2
0 GitHub stars

Use Cases

Validating synthetic datasets for machine learning to ensure zero leakage of source data
Sanitizing production datasets for safe use in development and testing environments
Automating privacy audits and compliance reporting for sensitive data pipelines

About

Key Features

Automated PII detection for direct identifiers, quasi-identifiers, and sensitive attributes
Privacy risk assessment metrics including K-Anonymity, L-Diversity, and T-Closeness
Comprehensive anonymization techniques including suppression, generalization, and tokenization
Advanced data leakage detection to prevent synthetic data from mirroring real-world records
Regulatory compliance checking for GDPR, HIPAA, CCPA, and SOC 2
0 GitHub stars

Use Cases

Validating synthetic datasets for machine learning to ensure zero leakage of source data
Sanitizing production datasets for safe use in development and testing environments
Automating privacy audits and compliance reporting for sensitive data pipelines