AGENT SKILL

openevidence-hello-world

Create a minimal working OpenEvidence clinical query example. Use when starting a new OpenEvidence integration, testing your setup, or learning basic clinical query patterns. Trigger with phrases like "openevidence hello world", "openevidence example", "openevidence quick start", "first clinical query".

License 许可
MIT
最近更新
2026-11-15
Stars
★ 2.0k
Forks
233

01 前言 Front Matter

name
openevidence-hello-world
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
version
1.0.0
description
Create a minimal working OpenEvidence clinical query example. Use when starting a new OpenEvidence integration, testing your setup, or learning basic clinical query patterns. Trigger with phrases like "openevidence hello world", "openevidence example", "openevidence quick start", "first clinical query".
allowed-tools
Read, Write, Edit

03 SKILL.md 正文

OpenEvidence Hello World

Overview

Minimal working example demonstrating core OpenEvidence clinical query functionality.

Prerequisites

  • Completed openevidence-install-auth setup
  • Valid API credentials configured
  • Development environment ready

Instructions

Step 1: Create Entry File

// src/openevidence-demo.ts
import { OpenEvidenceClient } from '@openevidence/sdk';

const client = new OpenEvidenceClient({
  apiKey: process.env.OPENEVIDENCE_API_KEY,
  orgId: process.env.OPENEVIDENCE_ORG_ID,
});

Step 2: Make Your First Clinical Query

async function firstClinicalQuery() {
  // Simple clinical question
  const response = await client.query({
    question: "What are the first-line treatments for type 2 diabetes in adults?",
    context: {
      specialty: "internal-medicine",
      urgency: "routine",
    },
  });

  console.log('Answer:', response.answer);
  console.log('Sources:', response.citations.map(c => c.source));
  console.log('Confidence:', response.confidence);
}

firstClinicalQuery().catch(console.error);

Step 3: Run the Example

# With TypeScript
npx ts-node src/openevidence-demo.ts

# With Node.js (after compilation)
node dist/openevidence-demo.js

Output

  • Working code file with OpenEvidence client initialization
  • Successful API response with evidence-based answer
  • Console output showing:
Answer: First-line treatment for type 2 diabetes in adults typically includes...
Sources: ["NEJM 2024", "ADA Standards of Care 2025", "JAMA Internal Medicine"]
Confidence: 0.95

Response Structure

interface ClinicalQueryResponse {
  answer: string;              // Evidence-based clinical answer
  citations: Citation[];       // Peer-reviewed sources
  confidence: number;          // 0-1 confidence score
  lastUpdated: string;         // When evidence was last reviewed
  disclaimer: string;          // Clinical use disclaimer
  deepConsultAvailable: boolean; // Whether DeepConsult can provide more detail
}

interface Citation {
  source: string;              // Journal/guideline name
  title: string;               // Article title
  authors: string[];           // Author list
  year: number;                // Publication year
  doi?: string;                // DOI if available
  url?: string;                // Link to source
}

Error Handling

Error Cause Solution
Import Error SDK not installed Verify with npm list @openevidence/sdk
Auth Error Invalid credentials Check environment variables are set
Timeout Complex query or network issues Increase timeout or retry
Rate Limit Too many requests Wait and retry with exponential backoff
Invalid Query Question not clinical Ensure query is medically relevant

Examples

TypeScript Example with Error Handling

import { OpenEvidenceClient, OpenEvidenceError } from '@openevidence/sdk';

const client = new OpenEvidenceClient({
  apiKey: process.env.OPENEVIDENCE_API_KEY,
  orgId: process.env.OPENEVIDENCE_ORG_ID,
});

async function queryClinicalEvidence(question: string) {
  try {
    const response = await client.query({
      question,
      context: {
        specialty: "family-medicine",
        urgency: "routine",
      },
      options: {
        maxCitations: 5,
        includeGuidelines: true,
      },
    });

    return {
      answer: response.answer,
      sources: response.citations,
      confidence: response.confidence,
    };
  } catch (error) {
    if (error instanceof OpenEvidenceError) {
      console.error(`OpenEvidence Error [${error.code}]:`, error.message);
    }
    throw error;
  }
}

// Example usage
queryClinicalEvidence(
  "What is the recommended antibiotic for community-acquired pneumonia?"
).then(result => {
  console.log('Clinical Answer:', result.answer);
  console.log('Evidence Sources:', result.sources.length);
});

Python Example

from openevidence import OpenEvidenceClient, OpenEvidenceError

client = OpenEvidenceClient()

def query_clinical_evidence(question: str) -> dict:
    try:
        response = client.query(
            question=question,
            context={
                "specialty": "emergency-medicine",
                "urgency": "urgent"
            }
        )

        return {
            "answer": response.answer,
            "sources": [c.source for c in response.citations],
            "confidence": response.confidence
        }
    except OpenEvidenceError as e:
        print(f"Error [{e.code}]: {e.message}")
        raise

# Example usage
result = query_clinical_evidence(
    "What are the contraindications for tPA in acute ischemic stroke?"
)
print(f"Answer: {result['answer']}")

Resources

Next Steps

Proceed to openevidence-local-dev-loop for development workflow setup.

04 同仓库更多 Skills

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

neuropixels-analysis

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

notebooklm

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Skill与智能体开发
★ 2.0k