Skill UI

Automates onnx converter work for ML deployment, providing best-practice guidance on serving, pipelines, monitoring, and optimization while generating production-ready code and configs.

Automates OpenAPI specification work by guiding API developers through best practices, generating production-ready code/configs, and validating outputs for REST, GraphQL, and authentication design patterns.

This system implements Role-Based Access Control (RBAC) for OpenEvidence, an AI-powered clinical decision support platform. It strictly manages access to sensitive data, including PHI-adjacent datasets and medical literature, ensuring compliance with regulations like HIPAA. The system defines distinct roles—Admin, Clinician, Researcher, Student, and Auditor—with granular permissions for querying, data export, and institutional configuration, maintaining a secure and auditable data environment.

This guide outlines the strict multi-environment setup for the OpenEvidence clinical AI system, crucial for maintaining HIPAA compliance. It details how to configure and validate separate environments (Development, Staging, Production) to manage different data classifications—synthetic, de-identified, and full PHI. The process emphasizes environment validation checks, BAA adherence, and robust audit logging to prevent regulatory violations and PHI exposure.

A comprehensive guide for auditing and ensuring regulatory compliance (SOC2, GDPR, HIPAA) when integrating Large Language Models (LLMs) via OpenRouter. It covers best practices for data handling, access control, PII redaction, implementing robust audit trails, and configuring provider routing to maintain data sovereignty and meet strict industry standards.

A comprehensive guide on implementing failover and fallback mechanisms for Large Language Models (LLMs) when using OpenRouter. This skill covers native model fallbacks, provider routing strategies, and advanced client-side fallback chains. Use this pattern when building mission-critical or highly resilient systems that must maintain service availability even if a primary model or an entire provider goes offline. It ensures robust API integration and graceful degradation.

This guide provides a comprehensive walkthrough for setting up and authenticating with the OpenRouter API. It covers generating secure API keys, configuring environment variables, and initializing clients in Python and TypeScript. Learn best practices for secure integration, including key management, verification, and key rotation, ensuring reliable connectivity to various large language models (LLMs).

This skill implements a sophisticated, config-driven rules engine for OpenRouter API calls. It dynamically determines the optimal large language model (LLM) by evaluating a comprehensive context, including user subscription tier, remaining cost budget, specific task type (code, chat), required tools, and latency requirements. This is essential for building production-grade, cost-aware, and robust LLM orchestration systems.

Enables Claude to act as a FinOps expert by analyzing cloud usage, generating cost reports, and recommending configuration changes to lower AWS, Azure, or GCP spending whenever the user asks to optimize cloud costs.

Guides the user through configuring and tuning database connection pools across languages, from selecting pool sizes to setting timeouts and monitoring usage to boost application performance.

Orchestrates complex multi-stage deployment pipelines by generating production-ready configs and setup code based on user requirements, ideal for automating CI/CD and reliable software releases.

Automated guidance for DevOps practitioners handling package json manager tasks, offering best practices, configuration generation, and validation for foundational CI/CD and infrastructure workflows.