shine-pii-safe
CommunityPII anonymization for safe LLM ingestion.
AuthordiShine-digital-agency
Version1.0.0
Installs0
System Documentation
What problem does it solve?
PII present in datasets can leak sensitive information when processed by AI systems. This skill detects PII like phone numbers, IBANs, emails, tax codes, and addresses in your data before ingestion into LLMs, enabling safer data sharing.
Core Features & Use Cases
- Detects and flags sensitive fields (phone numbers, emails, IBANs, tax codes, addresses).
- Confirms with the user before applying anonymization to preserve intent and auditability.
- Applies dishine-data-safe-usb anonymization to preserve grouping and trends while removing raw PII.
- Outputs an anonymized dataset and a local mapping file for traceability (not uploaded).
Quick Start
To anonymize a CSV file named customers.csv, run the skill on the dataset and follow the prompts to confirm detected PII.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: shine-pii-safe Download link: https://github.com/diShine-digital-agency/SHINE-Code-System/archive/main.zip#shine-pii-safe Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.