Skill UI

NVIDIA’s NeMo Guardrails adds runtime safety rails to LLM apps, covering jailbreak detection, hallucination and fact-checking, PII filtering, and toxicity checks via Colang 2.0 rules and integrations for production use on T4 GPUs.

Provides a comprehensive guide and code examples for configuring Sentry across development, staging, and production environments. It ensures data isolation by using separate DSNs, allows tuning of sample rates (e.g., 10% for production, 100% for dev), and implements environment-specific logic for PII scrubbing and event filtering, optimizing visibility while maintaining data security.

A comprehensive guide to implementing secure and compliant data handling within Algolia. This skill demonstrates how to transform source records, strip Personally Identifiable Information (PII), implement attribute filtering, and enforce data access controls. It provides robust workflows for GDPR and CCPA compliance, including data deletion (Right to Erasure) and Data Subject Access Requests (DSAR).

This comprehensive skill provides multi-layered guardrails for integrating with LLMs like Claude. It enforces security and compliance by implementing input validation (PII detection, length checks), system prompt restriction (scope control, safety rules), output filtering (preventing sensitive data leakage), cost governance, and model access policies. Ideal for building secure, robust, and governed AI applications.

This skill governs the secure ingestion and indexing of enterprise documents from diverse connectors (e.g., Google Drive, Confluence, Jira). Key functions include mandatory PII filtering (stripping emails, phones, SSNs) before indexing, preserving strict permission boundaries, and enforcing data retention policies to ensure compliance with global regulations like GDPR and CCPA.