From openevidence-pack
Sets up CI/CD pipelines for OpenEvidence clinical decision support integrations, including unit tests with mocked evidence queries and integration tests for live API connectivity.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openevidence-pack:openevidence-ci-integrationThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Set up CI/CD for OpenEvidence clinical decision support integrations: run unit tests with mocked evidence query and citation responses on every PR, validate live API connectivity for clinical queries on merge to main. OpenEvidence provides AI-powered medical evidence retrieval and clinical decision support, so CI pipelines verify query formatting, evidence parsing, citation extraction, and resp...
Set up CI/CD for OpenEvidence clinical decision support integrations: run unit tests with mocked evidence query and citation responses on every PR, validate live API connectivity for clinical queries on merge to main. OpenEvidence provides AI-powered medical evidence retrieval and clinical decision support, so CI pipelines verify query formatting, evidence parsing, citation extraction, and response quality scoring.
# .github/workflows/openevidence-ci.yml
name: OpenEvidence CI
on:
pull_request:
paths: ['src/openevidence/**', 'tests/**']
push:
branches: [main]
jobs:
unit-tests:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with: { node-version: '20' }
- run: npm ci
- run: npm test -- --reporter=verbose
integration-tests:
if: github.ref == 'refs/heads/main'
needs: unit-tests
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with: { node-version: '20' }
- run: npm ci
- run: npm run test:integration
env:
OPENEVIDENCE_API_KEY: ${{ secrets.OPENEVIDENCE_API_KEY }}
// tests/openevidence-service.test.ts
import { describe, it, expect, vi } from 'vitest';
import { queryEvidence, extractCitations } from '../src/openevidence-service';
vi.mock('../src/openevidence-client', () => ({
OpenEvidenceClient: vi.fn().mockImplementation(() => ({
query: vi.fn().mockResolvedValue({
answer: 'Current evidence supports early intervention with GLP-1 agonists...',
confidence: 0.92,
citations: [
{ title: 'NEJM 2025 Meta-Analysis', doi: '10.1056/NEJMoa2501234', year: 2025 },
{ title: 'Lancet Diabetes Review', doi: '10.1016/S2213-8587(25)00123', year: 2025 },
],
evidenceLevel: 'high',
}),
listQueries: vi.fn().mockResolvedValue({
queries: [{ id: 'q_abc', question: 'GLP-1 efficacy', status: 'completed' }],
}),
})),
}));
describe('OpenEvidence Service', () => {
it('queries clinical evidence with citations', async () => {
const result = await queryEvidence('GLP-1 agonist efficacy for type 2 diabetes');
expect(result.confidence).toBeGreaterThan(0.9);
expect(result.citations).toHaveLength(2);
});
it('extracts citation DOIs from response', async () => {
const citations = await extractCitations('q_abc');
expect(citations[0].doi).toMatch(/^10\.\d+/);
});
});
// tests/integration/openevidence.integration.test.ts
import { describe, it, expect } from 'vitest';
const hasKey = !!process.env.OPENEVIDENCE_API_KEY;
describe.skipIf(!hasKey)('OpenEvidence Live API', () => {
it('queries clinical evidence', async () => {
const res = await fetch('https://api.openevidence.com/v1/query', {
method: 'POST',
headers: {
'Authorization': `Bearer ${process.env.OPENEVIDENCE_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({ question: 'Aspirin dosing for secondary prevention' }),
});
expect(res.status).toBe(200);
const body = await res.json();
expect(body).toHaveProperty('answer');
expect(body).toHaveProperty('citations');
});
});
| CI Issue | Cause | Fix |
|---|---|---|
401 Unauthorized | Invalid API key | Regenerate at openevidence.com account settings |
| Empty citations array | Query too vague for evidence matching | Use specific clinical terms with condition and intervention |
| Low confidence score | Insufficient published evidence | Check evidence level field and handle low confidence gracefully |
| Rate limit (429) | Too many queries in test suite | Add throttling between clinical queries (1 req/sec) |
| Response timeout | Complex query requiring deep search | Increase fetch timeout to 30s for clinical evidence lookups |
See openevidence-deploy-integration.
npx claudepluginhub fleet-to-force/claude-code-plugins-plus --plugin openevidence-pack5plugins reuse this skill
First indexed Jul 10, 2026
Sets up CI/CD pipelines for OpenEvidence clinical decision support integrations, including unit tests with mocked evidence queries and integration tests for live API connectivity.
Guides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.