AGENT SKILL

openevidence-reference-architecture

Implement OpenEvidence reference architecture with best-practice project layout. Use when designing new clinical AI integrations, reviewing project structure, or establishing architecture standards for healthcare applications. Trigger with phrases like "openevidence architecture", "openevidence best practices", "openevidence project structure", "clinical ai architecture".

License 许可
MIT
最近更新
2026-05-26
Stars
★ 0
Forks
0

01 前言 Front Matter

name
openevidence-reference-architecture
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Implement OpenEvidence reference architecture with best-practice project layout. Use when designing new clinical AI integrations, reviewing project structure, or establishing architecture standards for healthcare applications. Trigger with phrases like "openevidence architecture", "openevidence best practices", "openevidence project structure", "clinical ai architecture".
allowed-tools
Read, Grep
compatible-with
claude-code, codex, openclaw

02 资源文件 1

03 SKILL.md 正文

OpenEvidence Reference Architecture

Table of Contents

Overview

Production-ready layered architecture for OpenEvidence clinical AI integrations. Covers project structure, client wrapper with caching/monitoring, service facade with PHI handling, EHR integration (FHIR/CDS Hooks), and configuration management.

Prerequisites

  • Understanding of layered architecture
  • OpenEvidence SDK knowledge
  • Healthcare compliance requirements (HIPAA)
  • TypeScript/Node.js project setup

Layer Architecture

API Layer          -> Controllers, Routes, Webhooks, Middleware
Service Layer      -> Business Logic, Orchestration, Validation
OpenEvidence Layer -> Client, Types, Caching, Error Handling
Compliance Layer   -> HIPAA Audit, PHI Handling, Encryption
Integration Layer  -> EHR/FHIR, Notifications, External Services
Infrastructure     -> Database, Cache, Queue, Monitoring

Instructions

Step 1: Set Up Project Structure

Organize into src/openevidence/ (client, config, types, errors, cache), src/services/clinical/ (query, deepconsult, drug-info), src/api/ (routes, middleware), src/compliance/ (HIPAA audit, PHI, encryption), and src/integrations/ (EHR, notifications).

Step 2: Build Client Wrapper

Create OpenEvidenceService with caching, metrics collection, HIPAA audit logging, and health check. Use singleton pattern with cache-first strategy.

Step 3: Create Service Facade

Build ClinicalEvidenceService that sanitizes PHI before queries, formats responses for clinical use, and handles drug interaction checks.

Step 4: Implement EHR Integration

Add FHIR CDS Hooks endpoints for patient-view and medication-prescribe hooks. Extract conditions and medications from FHIR prefetch data.

Step 5: Configure Management

Use convict for typed configuration with environment-specific JSON files. Mark sensitive fields (apiKey) and validate strictly.

Output

  • Layered architecture with separation of concerns
  • Client wrapper with caching, metrics, and audit logging
  • Service facade with PHI sanitization
  • EHR integration (FHIR CDS Hooks)
  • Typed configuration management (convict)

Error Handling

Architecture Issue Detection Resolution
Layer violation Code review Enforce import boundaries
PHI leak Audit log review Add PHI detection middleware
Cache stale data Clinical complaint Review TTL strategy
EHR integration fails CDS Hook errors Check FHIR endpoint config

Examples

Data Flow

User -> API Gateway -> PHI Sanitizer -> Cache Check -> OpenEvidence API -> Cache Store -> Response
                          |                                                      |
                     HIPAA Audit Log                                       Audit Log

See detailed implementation for advanced patterns.

Resources

04 同仓库更多 Skills

SamuelChien
SamuelChien/mega-skills-collection

zustand-store-ts

Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

zustand-store-creator

Zustand Store Creator - Auto-activating skill for Frontend Development. Triggers on: zustand store creator, zustand store creator Part of the Frontend Development skill category.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

zero-trust-config-helper

Zero Trust Config Helper - Auto-activating skill for Security Advanced. Triggers on: zero trust config helper, zero trust config helper Part of the Security Advanced skill category.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

zapier-integration-helper

Zapier Integration Helper - Auto-activating skill for Business Automation. Triggers on: zapier integration helper, zapier integration helper Part of the Business Automation skill category.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

zai-cli

Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP. Use when user needs image/video analysis, OCR, UI-to-code conversion, error diagnosis, real-time web search, web page to markdown extraction, or GitHub code exploration. Trigger with phrases like "analyze this image", "search the web for", "read this page", "explore this repo", or "use zai". Requires Z_AI_API_KEY.

★ 0
SamuelChien
SamuelChien/mega-skills-collection

yt-research

Research competitor YouTube channels, niches, and trending topics for your content strategy. Use this skill whenever the user says "research channels", "analyze competitors", "find trending topics", "niche analysis", "competitive research", "what are other creators doing", "scrape YouTube channels", or wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.

★ 0