Skill UI

This skill outlines security best practices for the TwinMind AI meeting assistant. It covers crucial aspects like on-device audio processing, encrypted cloud backups, and managing microphone permissions. Use it when setting up new TwinMind instances or managing AI operations to ensure data privacy, compliance, and robust security for sensitive meeting data.

A comprehensive guide for building applications with Claude, ensuring responsible data handling. This skill covers critical patterns such as PII redaction (stripping sensitive data like emails, phone numbers, and card numbers), optimizing the 200K token context window through conversation trimming, and implementing best practices for data retention and privacy compliance when interacting with the Anthropic API.

This skill provides robust mechanisms to ensure data privacy when interacting with Cohere APIs (Chat, Embed, etc.). It implements advanced PII detection (emails, SSNs, IP addresses, etc.), performs pre-call redaction to mask sensitive information, and includes post-call scrubbing and detailed audit logging. Essential for achieving GDPR/CCPA compliance and safely handling sensitive user data.

A comprehensive tool designed to scan any agent skill for potential security risks and vulnerabilities before implementation or use. Powered by local static analysis (A.I.G.), it ensures that no file contents, credentials, or personal data ever leave your device, providing maximum privacy and safety for integrating new AI capabilities across various agent platforms.

A comprehensive guide detailing advanced security threats in Machine Learning and AI systems. Covers model supply chain attacks (RCE via pickle, poisoning), adversarial examples (FGSM, PGD, physical-world), data privacy breaches, and LLM-specific vulnerabilities. Essential for building robust, secure AI pipelines.

This skill de-identifies sensitive PII from clinical notes across numerous languages, including Spanish, German, French, and Arabic. It automatically selects language-specific PII models, national ID regex patterns, and generates locale-aware fake surrogates. Designed for global healthcare datasets, it runs entirely on-device, ensuring maximum privacy and linguistic accuracy for diverse international clinical records.

This skill deploys the OpenMed Model Context Protocol (MCP) server, exposing critical clinical NLP tools such as NER, PII extraction, and de-identification. It enables AI coding agents and chat clients to interact with OpenMed's capabilities via simple tool calls, running locally on-device to ensure user data privacy and security. Supports both stdio and Streamable HTTP deployment modes.

This skill implements a critical CI gate to ensure the privacy and performance integrity of de-identification models. It automatically fails the build if the model's recall on held-out PHI data drops below the defined threshold, or if any critical Personally Identifiable Information (PHI) is leaked (leakage must be zero). It enforces strict privacy standards in continuous integration pipelines, blocking unsafe merges.