OP

openevidence-prod-checklist

Enforces security, HIPAA compliance, and performance standards for OpenEvidence clinical AI.

Install

mkdir -p .claude/skills/openevidence-prod-checklist && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4841" && unzip -o skill.zip -d .claude/skills/openevidence-prod-checklist && rm skill.zip

Installs to .claude/skills/openevidence-prod-checklist

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.

Prod Checklist for OpenEvidence.
32 charsno explicit “when” trigger
Advanced

Key capabilities

  • Store API keys in a secrets manager with rotation
  • Configure request timeouts and monitor response time SLAs
  • Implement pagination for evidence result sets
  • De-identify clinical query payloads before sending
  • Validate citation URLs before displaying to clinicians
  • Configure circuit breakers and retry logic for API calls

How it works

This skill provides a checklist and validation script to ensure an OpenEvidence integration meets production readiness standards, focusing on security, compliance, and resilience.

Inputs & outputs

You give it
OpenEvidence API integration
You get back
A production-ready OpenEvidence integration with secure authentication, reliable API integration, complete error handling, and HIPAA-compliant security

When to use openevidence-prod-checklist

  • Conducting pre-deployment reviews
  • Auditing integration for HIPAA compliance
  • Setting up secrets management

About this skill

OpenEvidence Production Checklist

Overview

OpenEvidence provides clinical decision support backed by peer-reviewed medical literature. A production integration handles Protected Health Information (PHI) subject to HIPAA, serves evidence-based answers where accuracy directly impacts patient outcomes, and must maintain complete audit trails for regulatory review. Misconfigurations can expose PHI in logs, serve stale clinical guidance, or fail compliance audits that shut down your integration entirely. This checklist enforces HIPAA-grade security, citation verification, and the SLA discipline required for healthcare-adjacent systems.

Prerequisites

  • Production OpenEvidence API credentials (not trial/sandbox keys)
  • Secrets manager configured (Vault, AWS Secrets Manager, or GCP Secret Manager)
  • HIPAA-compliant monitoring stack (no PHI in log aggregators without BAA)
  • Business Associate Agreement (BAA) executed with OpenEvidence
  • Compliance officer sign-off on data flow architecture

Authentication & Secrets

  • API keys stored in vault/secrets manager (never in code, env files, or CI logs)
  • Key rotation schedule configured (every 90 days, with zero-downtime swap)
  • Separate keys for staging vs production (staging keys cannot reach production data)
  • Service account permissions scoped to query-only (no admin endpoints)
  • API key exposure detection automated (scan logs/repos for leaked credentials)

API Integration

  • Base URL points to production endpoint (not sandbox/staging)
  • Request timeout set to 15 seconds for clinical queries (evidence synthesis is compute-heavy)
  • Response time SLA monitored: p95 < 3 seconds per contractual agreement
  • Pagination implemented for evidence result sets (token-based cursor)
  • Clinical query payloads never include patient identifiers (de-identify before sending)
  • Citation URLs in responses validated before displaying to clinicians
  • Fallback behavior defined when evidence confidence score is below threshold (0.7)

Error Handling & Resilience

  • Circuit breaker configured for OpenEvidence API calls (open after 3 consecutive failures)
  • Retry logic with exponential backoff for 429 (rate limit) and 5xx responses
  • Clinical query failures surface explicit "no evidence available" (never silent failure)
  • Timeout responses distinguished from empty-result responses in UI
  • Stale cache clearly labeled with retrieval timestamp when serving cached evidence
  • Degraded mode displays disclaimer: "Results may not reflect latest evidence"
  • All API errors logged with correlation ID (without PHI in the log entry)

Monitoring & Alerting

  • API latency tracked (p50, p95, p99) with 3s p95 SLA threshold
  • Error rate alerts configured (threshold: >0.5% over 5-minute window — stricter for clinical)
  • Evidence citation link validity checked daily (alert on broken DOI/PubMed links)
  • Query volume anomalies detected (sudden spike may indicate misuse or bot traffic)
  • Response confidence score distribution tracked (alert if median drops below 0.8)
  • Audit log completeness verified daily (every query must have a log entry)

Security

  • PHI never included in API request payloads (queries de-identified before transmission)
  • PHI never written to application logs, error reports, or monitoring dashboards
  • All data in transit encrypted via TLS 1.2+ (certificate pinning recommended)
  • All cached clinical responses encrypted at rest (AES-256)
  • Access to clinical query history restricted by role (clinician-only, auditor read-only)
  • Audit log captures: user ID, query timestamp, evidence IDs returned, confidence scores
  • Data retention policy enforced: clinical query logs retained per HIPAA minimum (6 years)
  • Annual HIPAA risk assessment includes OpenEvidence integration scope

Validation Script

async function validateOpenEvidenceProduction(apiKey: string): Promise<void> {
  const base = process.env.OPENEVIDENCE_API_URL ?? 'https://api.openevidence.com/v1';
  const headers = { Authorization: `Bearer ${apiKey}`, 'Content-Type': 'application/json' };

  // 1. Connectivity check
  const ping = await fetch(`${base}/health`, { headers, signal: AbortSignal.timeout(5000) });
  console.assert(ping.ok, `API unreachable: ${ping.status}`);

  // 2. Auth validation
  const auth = await fetch(`${base}/me`, { headers });
  console.assert(auth.status !== 401, 'Invalid API key');
  console.assert(auth.status !== 403, 'Insufficient permissions — check scope');

  // 3. Clinical query round-trip (de-identified test query)
  const query = await fetch(`${base}/query`, {
    method: 'POST',
    headers,
    body: JSON.stringify({ question: 'What is the standard treatment for hypertension?' }),
    signal: AbortSignal.timeout(15000),
  });
  console.assert(query.ok, `Clinical query failed: ${query.status}`);
  const result = await query.json();
  console.assert(result.citations?.length > 0, 'No citations returned — evidence pipeline may be down');

  // 4. Response time SLA
  const start = Date.now();
  await fetch(`${base}/query`, {
    method: 'POST',
    headers,
    body: JSON.stringify({ question: 'Recommended dosage for metformin in type 2 diabetes?' }),
    signal: AbortSignal.timeout(15000),
  });
  const elapsed = Date.now() - start;
  console.assert(elapsed < 3000, `Response time ${elapsed}ms exceeds 3s SLA`);

  // 5. Audit log endpoint accessible
  const audit = await fetch(`${base}/audit-log?limit=1`, { headers });
  console.assert(audit.ok, `Audit log endpoint failed: ${audit.status}`);
  console.log('All OpenEvidence production checks passed');
}

Risk Matrix

CheckRisk if SkippedPriority
PHI excluded from API payloadsHIPAA violation, regulatory penalty, BAA breachCritical
PHI excluded from logsData breach via log aggregator, OCR enforcement actionCritical
Audit log completenessFailed compliance audit, integration shutdownCritical
Citation URL validationClinicians follow broken links, lose trust in evidenceHigh
Confidence score monitoringLow-quality answers served without clinician awarenessHigh

Resources

Next Steps

See openevidence-security-basics.

Prerequisites

Production OpenEvidence API credentialsSecrets manager configured (Vault, AWS Secrets Manager, or GCP Secret Manager)HIPAA-compliant monitoring stackBusiness Associate Agreement (BAA) executed with OpenEvidence

How it compares

This checklist enforces HIPAA-grade security, citation verification, and SLA discipline for healthcare-adjacent systems, which is more rigorous than a general API integration.

Compared to similar skills

openevidence-prod-checklist side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
openevidence-prod-checklist (this skill)127dReviewAdvanced
windows-ui-automation178moReviewAdvanced
linux-production-shell-scripts76moReviewIntermediate
cursor-prod-checklist427dReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

You might also like

windows-ui-automation

martinholovsky

Expert in Windows UI Automation (UIA) and Win32 APIs for desktop automation. Specializes in accessible, secure automation of Windows applications including element discovery, input simulation, and process interaction. HIGH-RISK skill requiring strict security controls for system access.

17126

linux-production-shell-scripts

davila7

This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration.

746

cursor-prod-checklist

jeremylongshore

Execute production readiness checklist for Cursor IDE setup. Triggers on "cursor production", "cursor ready", "cursor checklist", "optimize cursor setup". Use when working with cursor prod checklist functionality. Trigger with phrases like "cursor prod checklist", "cursor checklist", "cursor".

434

posthog-enterprise-rbac

jeremylongshore

Configure PostHog enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls for PostHog. Trigger with phrases like "posthog SSO", "posthog RBAC", "posthog enterprise", "posthog roles", "posthog permissions", "posthog SAML".

13

prowler-provider

prowler-cloud

Creates new Prowler cloud providers or adds services to existing providers. Trigger: When extending Prowler SDK provider architecture (adding a new provider or a new service to an existing provider).

13

custom-workers

ruvnet

Create and run custom background analysis workers with composable phases. Use when you need automated code analysis, security scanning, pattern learning, or API documentation generation.

12

Search skills

Search the agent skills registry