Skill UI

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.

Guides users to select a local, on-device Personally Identifiable Information (PII) detection model from a committed registry. It filters models based on language, required runtime environment (e.g., PyTorch, MLX), and size constraints. The process emphasizes building an offline shortlist and mandates rigorous pre-deployment recall validation and performance benchmarking to ensure secure, privacy-preserving deployment.

An expert assistant dedicated to ensuring compliance with GDPR and global data protection regulations. This skill covers auditing code and systems for violations, drafting compliant legal documents (like privacy policies and DPAs), answering complex compliance questions with authoritative GDPR article citations, and reviewing data flows for PII handling practices. It addresses both EU and UK GDPR requirements.

This tool serves as a model-routing advisor for high-stakes legal translation tasks, covering contracts, statutes, and case law. It does not perform the translation itself, but instead provides expert decision support by recommending the optimal primary and fallback LLMs based on language pair, required privacy level, cost, and speed. Crucially, it emphasizes that human legal-linguist review is mandatory, as no single LLM can guarantee certified legal accuracy.

This skill enforces strict communication protocols for AI agents interacting in shared channels with external parties. It ensures agents speak only when explicitly addressed, prevents internal context leakage, and routes sensitive content to draft-only approval. Ideal for group chats, DMs, and business partnerships where privacy and security are critical.

This AI-driven system integrates multi-dimensional health data including lifestyle, medical history, and mental health to identify anomalies and predict risks. It provides personalized health recommendations based on evidence-based guidelines and generates comprehensive interactive reports. Supports intelligent Q&A for health metrics and trends, ensuring data privacy with local processing. Ideal for users seeking data-driven health insights without replacing professional medical advice.

Ditto mines user words from local coding-agent session logs to create private work, design, and writing profiles. It requires explicit user approval before mining begins and keeps all data local. This skill routes a compatible Ditto runtime to extract patterns from real coding history rather than questionnaires, ensuring privacy and evidence-backed personalization for AI agents.

Architecture and integration sketches for LLM applications, covering RAG retrieval, tool dispatch, agent loops, caching, privacy boundaries and verification requirements before production use.

An expert guide for deploying and optimizing Large Language Models (LLMs) entirely on local hardware. Mastering the entire local AI ecosystem, including inference engines like Ollama, vLLM, and llama.cpp. Provides deep knowledge on quantization formats (GGUF, EXL2, AWQ), VRAM calculation, and ensuring privacy-first, offline deployment for state-of-the-art models.

This skill manages and stores approved team context securely using RuVector isolation. It ensures tenant-local data privacy by excluding sensitive credentials and personal information. During retrieval, it preserves provenance and treats data as untrusted. It prevents memory transfer between teams, maintaining strict security boundaries for AI team operations.