data-anonymizer

Detect and mask PII in text and CSV files using pandas and faker.

86|18|Updated Dec 14, 2025
One-click install
npx skills add https://github.com/dkyazzentwatwa/chatgpt-skills --skill data-anonymizer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-anonymizer
Source: https://github.com/dkyazzentwatwa/chatgpt-skills/tree/main/data-anonymizer
Command: npx skills add https://github.com/dkyazzentwatwa/chatgpt-skills --skill data-anonymizer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, faker, and includes scripts (resource) components.

What problem does it solve?

This Skill safeguards sensitive information by detecting and masking Personally Identifiable Information (PII) in text and CSV files, ensuring data privacy and compliance.

Core Features & Use Cases

  • PII Detection: Identifies names, emails, phone numbers, SSNs, addresses, and more.
  • Flexible Masking: Offers strategies like masking, redacting, hashing, or replacing with fake data.
  • CSV Processing: Handles large datasets, allowing for column-specific anonymization.
  • Reversible Option: Optionally creates a token map for de-anonymization.
  • Use Case: Securely anonymize customer support logs or export a database for testing without exposing real user data.

Quick Start

Use the data-anonymizer skill to mask PII in the provided text.

Frequently Asked Questions about data-anonymizer

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

FAQPage Schema
How do I mask PII in a CSV file for data privacy compliance?

Mask PII in a CSV file for data privacy by using this skill to automatically detect names, emails, and SSNs, then apply redaction, hashing, or fake data replacement strategies directly to specific dataset columns.

What is the best way to anonymize customer support logs containing text and PII?

Anonymizing customer support logs containing text and PII involves detecting sensitive details like names and phone numbers, then applying hashing or redaction strategies to ensure the exported data remains safe and compliant.

Can I replace real PII with realistic fake data for database testing?

Yes, you can replace real PII with realistic fake data for database testing by utilizing the faker library integration, which generates plausible replacement values for sensitive columns while maintaining dataset structure.

Does reversible tokenization allow de-anonymization of masked data later?

Reversible tokenization allows de-anonymization of masked data later by generating a secure token map during the initial masking process, enabling authorized users to restore the original PII when necessary.

What masking strategies are available for protecting sensitive text files?

Available masking strategies for protecting sensitive text files include complete redaction of PII, cryptographic hashing of values, and substitution with synthetically generated fake data, providing flexible compliance options.

Do I need pandas to process large datasets for column-specific anonymization?

You need pandas to process large datasets for column-specific anonymization because this skill relies on the framework to efficiently manipulate CSV files, isolate specific columns, and apply targeted PII masking strategies.