Skill UI

This provides a local development loop for integrating the OpenEvidence clinical decision support API. Developers can build health-tech tools and quickly iterate using mock evidence queries, citation responses, and clinical summaries. It supports toggling between mock mode for rapid development and sandbox mode for validation against the real platform, ensuring development uses de-identified data.

This comprehensive checklist guides the secure and compliant deployment of OpenEvidence, a clinical decision support system. It covers critical requirements for handling Protected Health Information (PHI), including HIPAA-grade security, robust API integration best practices, mandatory monitoring setup, and resilience testing. Use this guide to ensure your healthcare-adjacent system meets the highest standards of compliance and reliability.

This guide demonstrates how to implement robust rate limiting and retry logic for critical healthcare APIs using a token bucket pattern. It covers managing specific service limits (e.g., clinical queries, evidence synthesis) and implementing strategies like exponential backoff and batch processing to ensure graceful degradation and reliable data retrieval in clinical decision support systems.

This comprehensive reference architecture guides the integration of OpenEvidence into clinical decision support systems (CDS). It is designed for healthcare platforms needing evidence-based query processing, deterministic citation tracking, and full audit logging. Key considerations include HIPAA compliance, optimizing for sub-second response times in point-of-care workflows, and establishing robust data models and event pipelines.

This guide provides comprehensive documentation and code examples for integrating OpenEvidence webhooks. Learn how to subscribe to real-time events (e.g., query completion, evidence updates, new citations) to keep clinical decision support systems fresh. Use these webhooks to trigger downstream audit workflows and ensure immediate data synchronization.

This skill provides comprehensive tools to monitor the real-time availability, status, and performance of various large language models (LLMs) accessed via OpenRouter. It supports active health probes, catalog checks, and scheduled monitoring via Python and Bash, ensuring robust fault detection and failover logic for production systems that rely on external AI APIs.

OpenRouter provides a unified API gateway to access leading AI models (OpenAI, Anthropic, Google, Meta, etc.) from a single endpoint. This skill is essential for developers who need to compare model performance (latency, tokens) across different providers, build resilient cross-provider fallback workflows, or manage complex AI pipelines without writing provider-specific code. It supports feature normalization and BYOK (Bring Your Own Key) for high-volume production use.

Flash Attention optimizer delivers 2-4x speedup and 10-20x memory savings for transformer attention, ideal when training or running long-context models that hit GPU memory or latency limits; supports PyTorch native scaled_dot_product_attention, the flash-attn library, H100 FP8 precision, and sliding-window attention.

This tool is designed to collect comprehensive diagnostic evidence for troubleshooting Perplexity API issues. It automatically gathers critical environment details (OS, Node/Python versions), tests API connectivity, and captures redacted configuration settings. The resulting secure bundle is ideal for submitting detailed support tickets or sharing with technical teammates.

Generates tailored disaster recovery plans and setup code that automate infrastructure configuration, encryption, testing, and multi-region failover for AWS or other environments when you request DR strategy or business continuity support.

Automates the collection of comprehensive diagnostic evidence for PostHog support tickets. This bundle gathers runtime environment details (Node, Python versions), SDK versions, API connectivity status to US/EU clouds, feature flag settings, event flow testing results, and redacts sensitive environment variables. It provides a structured, support-ready archive for rapid troubleshooting.

This skill provides comprehensive capabilities for working with PowerPoint files (.pptx). It supports end-to-end workflows, including creating new presentations from scratch based on design principles, sophisticated content editing, and deep structural analysis. Users can extract plain text, access raw underlying XML (for notes, comments, and layouts), and apply expert design knowledge—such as selecting appropriate color palettes and establishing visual hierarchy—to ensure professional and effective presentations.