anth-data-handling

name	anth-data-handling
description	Implement data privacy, PII handling, and compliance patterns for Claude API. Use when handling sensitive data, implementing PII redaction, or configuring data retention for GDPR/CCPA compliance with Claude. Trigger with phrases like "anthropic data privacy", "claude PII", "anthropic gdpr", "claude data handling", "redact data claude".
allowed-tools	Read, Write, Edit, Grep
version	1.6.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","ai","anthropic"]
compatibility	Designed for Claude Code

Anthropic Data Handling

Overview

Anthropic's data policies: API inputs/outputs are NOT used for model training (commercial API). Zero-day retention is available. This skill covers PII redaction before sending to Claude and compliance patterns.

Anthropic Data Policies

Policy	Details
Training data	API data is NOT used for training (commercial API)
Data retention	30-day default; 0-day available via agreement
Encryption	TLS 1.2+ in transit, AES-256 at rest
SOC 2 Type II	Certified
HIPAA BAA	Available for eligible customers

PII Redaction Before API Calls

import re
import anthropic

def redact_pii(text: str) -> tuple[str, dict]:
    """Redact PII before sending to Claude, return redaction map for restoration."""
    redaction_map = {}
    patterns = [
        (r'\b\d{3}-\d{2}-\d{4}\b', 'SSN', '[SSN-REDACTED-{}]'),
        (r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', 'EMAIL', '[EMAIL-REDACTED-{}]'),
        (r'\b\d{3}[-.]?\d{3}[-.]?\d{4}\b', 'PHONE', '[PHONE-REDACTED-{}]'),
        (r'\b\d{4}[- ]?\d{4}[- ]?\d{4}[- ]?\d{4}\b', 'CARD', '[CARD-REDACTED-{}]'),
    ]

    counter = 0
    for pattern, label, replacement in patterns:
        for match in re.finditer(pattern, text):
            counter += 1
            placeholder = replacement.(counter)
            redaction_map[placeholder] = .group()
            text = text.replace(.group(), placeholder, )

     text, redaction_map

 () -> :
    
     placeholder, original  redaction_map.items():
        text = text.replace(placeholder, original)
     text


user_input = 
safe_input, redactions = redact_pii(user_input)


client = anthropic.Anthropic()
msg = client.messages.create(
    model=,
    max_tokens=,
    messages=[{: , : safe_input}]
)
final_output = restore_pii(msg.content[].text, redactions)