openevidence-sdk-patterns
Best practices for implementing the OpenEvidence clinical AI integration.
Install
mkdir -p .claude/skills/openevidence-sdk-patterns && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3064" && unzip -o skill.zip -d .claude/skills/openevidence-sdk-patterns && rm skill.zipInstalls to .claude/skills/openevidence-sdk-patterns
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Sdk Patterns for OpenEvidence.Key capabilities
- →Query medical literature and clinical guidelines from OpenEvidence API
- →Authenticate API requests using an OPENEVIEVIDENCE_API_KEY
- →Handle healthcare-specific API errors, including retries for rate limits
- →Preserve citation chains for audit compliance
- →Build structured queries with specific parameters like specialty and evidence level
How it works
A singleton client manages API authentication and requests to the OpenEvidence REST endpoints. An error wrapper handles API responses, including retries and specific error messages.
Inputs & outputs
When to use openevidence-sdk-patterns
- →Integrate clinical evidence search
- →Implement secure API authentication
- →Handle medical-specific error responses
- →Maintain audit-compliant citation chains
About this skill
OpenEvidence SDK Patterns
Overview
Production-ready patterns for the OpenEvidence clinical evidence API. OpenEvidence provides REST endpoints for querying medical literature, retrieving clinical guidelines, and generating evidence-based recommendations. The API authenticates via OPENEVIDENCE_API_KEY and returns structured clinical data with citation provenance. A singleton client enforces consistent auth, handles healthcare-specific errors, and preserves citation chains for audit compliance.
Singleton Client
const OE_BASE = 'https://api.openevidence.com/v1';
let _client: OpenEvidenceClient | null = null;
export function getClient(): OpenEvidenceClient {
if (!_client) {
const apiKey = process.env.OPENEVIDENCE_API_KEY;
if (!apiKey) throw new Error('OPENEVIDENCE_API_KEY must be set — get it from openevidence.com/developer');
_client = new OpenEvidenceClient(apiKey);
}
return _client;
}
class OpenEvidenceClient {
private headers: Record<string, string>;
constructor(apiKey: string) { this.headers = { 'Authorization': `Bearer ${apiKey}`, 'Content-Type': 'application/json' }; }
async query(question: string, opts: { specialty?: string; maxResults?: number } = {}): Promise<EvidenceResponse> {
const res = await fetch(`${OE_BASE}/query`, { method: 'POST', headers: this.headers,
body: JSON.stringify({ question, specialty: opts.specialty, max_results: opts.maxResults ?? 10 }) });
if (!res.ok) throw new OEError(res.status, await res.text()); return res.json();
}
async getCitation(citationId: string): Promise<Citation> {
const res = await fetch(`${OE_BASE}/citations/${citationId}`, { headers: this.headers });
if (!res.ok) throw new OEError(res.status, await res.text()); return res.json();
}
}
Error Wrapper
export class OEError extends Error {
constructor(public status: number, message: string) { super(message); this.name = 'OEError'; }
}
export async function safeCall<T>(operation: string, fn: () => Promise<T>): Promise<T> {
try { return await fn(); }
catch (err: any) {
if (err instanceof OEError && err.status === 429) { await new Promise(r => setTimeout(r, 5000)); return fn(); }
if (err instanceof OEError && err.status === 401) throw new OEError(401, 'Invalid OPENEVIDENCE_API_KEY');
if (err instanceof OEError && err.status === 422) throw new OEError(422, `${operation}: query rejected — check terminology`);
throw new OEError(err.status ?? 0, `${operation} failed: ${err.message}`);
}
}
Request Builder
class OEQueryBuilder {
private body: Record<string, any> = {};
question(q: string) { this.body.question = q; return this; }
specialty(s: string) { this.body.specialty = s; return this; }
maxResults(n: number) { this.body.max_results = Math.min(n, 50); return this; }
evidenceLevel(level: 'meta-analysis' | 'rct' | 'cohort' | 'any') { this.body.evidence_level = level; return this; }
yearRange(from: number, to: number) { this.body.year_range = { from, to }; return this; }
build() { return this.body; }
}
// Usage: new OEQueryBuilder().question('statin efficacy in elderly').specialty('cardiology').evidenceLevel('rct').build();
Response Types
interface EvidenceResponse {
answer: string; confidence: number; citations: Citation[]; specialty: string;
}
interface Citation {
id: string; title: string; authors: string[]; journal: string; year: number;
doi: string; evidence_level: 'meta-analysis' | 'rct' | 'cohort' | 'case-report'; abstract: string;
}
interface Guideline {
id: string; organization: string; title: string; year: number;
recommendation: string; strength: 'strong' | 'moderate' | 'weak';
}
interface DrugInteraction {
drug_a: string; drug_b: string; severity: 'major' | 'moderate' | 'minor';
description: string; citations: Citation[];
}
Testing Utilities
export function mockCitation(overrides: Partial<Citation> = {}): Citation {
return { id: 'cite-001', title: 'Statin Therapy in Older Adults', authors: ['Smith J', 'Doe A'],
journal: 'NEJM', year: 2024, doi: '10.1056/NEJMoa2401234',
evidence_level: 'rct', abstract: 'Background: ...', ...overrides };
}
export function mockEvidenceResponse(citationCount = 3): EvidenceResponse {
return { answer: 'Evidence supports moderate-intensity statin therapy...', confidence: 0.87,
citations: Array.from({ length: citationCount }, (_, i) => mockCitation({ id: `cite-${i}` })),
specialty: 'cardiology' };
}
Error Handling
| Pattern | When to Use | Example |
|---|---|---|
safeCall wrapper | All API calls | Structured error with clinical operation context |
| Retry on 429 | Batch evidence queries | 5s backoff before retry |
| 422 validation | Malformed clinical queries | Clear message on rejected terminology |
| Citation chain audit | Compliance reporting | Preserve full provenance from response |
Resources
Next Steps
Apply patterns in openevidence-core-workflow-a.
Limitations
- →OPENEVIDENCE_API_KEY must be set
- →Query rejected if terminology is malformed (422 error)
- →API calls may be rate-limited (429 error)
How it compares
This skill provides production-ready patterns for integrating with the OpenEvidence clinical evidence API, offering structured error handling and query building beyond basic API calls.
Compared to similar skills
openevidence-sdk-patterns side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| openevidence-sdk-patterns (this skill) | 1 | 27d | Review | Intermediate |
| mcp-builder | 136 | 3mo | Review | Advanced |
| telegram-mini-app | 62 | 6mo | Review | Advanced |
| stripe-integration | 48 | 2mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
mcp-builder
anthropics
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
telegram-mini-app
davila7
Expert in building Telegram Mini Apps (TWA) - web apps that run inside Telegram with native-like experience. Covers the TON ecosystem, Telegram Web App API, payments, user authentication, and building viral mini apps that monetize. Use when: telegram mini app, TWA, telegram web app, TON app, mini app.
stripe-integration
wshobson
Implement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks. Use when integrating Stripe payments, building subscription systems, or implementing secure checkout flows.
backend-dev-guidelines
langfuse
Comprehensive backend development guide for Langfuse's Next.js 14/tRPC/Express/TypeScript monorepo. Use when creating tRPC routers, public API endpoints, BullMQ queue processors, services, or working with tRPC procedures, Next.js API routes, Prisma database access, ClickHouse analytics queries, Redis queues, OpenTelemetry instrumentation, Zod v4 validation, env.mjs configuration, tenant isolation patterns, or async patterns. Covers layered architecture (tRPC procedures → services, queue processors → services), dual database system (PostgreSQL + ClickHouse), projectId filtering for multi-tenant isolation, traceException error handling, observability patterns, and testing strategies (Jest for web, vitest for worker).
swapper-integration
shapeshift
Integrate new DEX aggregators, swappers, or bridge protocols (like Bebop, Portals, Jupiter, 0x, 1inch, etc.) into ShapeShift Web. Activates when user wants to add, integrate, or implement support for a new swapper. Guides through research, implementation, and testing following established patterns.
copilot-sdk
github
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.