Pii redaction
Skill a5c-ai/babysitter/library/specializations/ai-agents-conversational/skills/pii-redaction
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
npx -y skills add a5c-ai/babysitter --skill pii-redactionAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
PII detection and redaction utilities for privacy-compliant conversational AI
SKILL.md
1.6 KB, as published. Nobody here has run it
PII Redaction Skill
Capabilities
- Detect personally identifiable information
- Implement redaction strategies
- Configure detection for various PII types
- Design reversible anonymization
- Implement compliance logging
- Create audit trails for PII handling
Target Processes
- content-moderation-safety
- system-prompt-guardrails
Implementation Details
PII Types
- Names: Person names, usernames
- Contact: Email, phone, address
- Financial: Credit cards, bank accounts
- Government IDs: SSN, passport, driver's license
- Medical: Health information
- Custom: Organization-specific PII
Redaction Methods
- Masking ([REDACTED])
- Pseudonymization (fake values)
- Tokenization (reversible)
- Encryption
Configuration Options
- PII types to detect
- Detection sensitivity
- Redaction method
- Language support
- Custom patterns
Best Practices
- Comprehensive PII coverage
- Regular pattern updates
- Audit logging
- Compliance alignment
- Testing with diverse data
Dependencies
- presidio-analyzer
- presidio-anonymizer
- spacy