healthcare-eval-harness

Automate patient safety verification for healthcare deployments in CI/CD pipelines.

3|2|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/agentmatters/mullai-bot --skill healthcare-eval-harness
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: healthcare-eval-harness
Source: https://github.com/agentmatters/mullai-bot/tree/main/src/Mullai.Skills/Skills/claude-code-everything/healthcare-eval-harness
Command: npx skills add https://github.com/agentmatters/mullai-bot --skill healthcare-eval-harness

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automated patient safety verification for healthcare deployments. This harness enforces safety gates across CI/CD to block unsafe deployments in healthcare systems.

Core Features & Use Cases

  • Automated five-category evaluation with CRITICAL gates requiring 100% pass for safety-critical areas.
  • Configurable thresholds, pass/fail reporting, and remediation guidance to support rapid safety validation.
  • Use Case: Validate EMR/EHR deployments, CDSS logic changes, and authentication/schema updates before production release.

Quick Start

Run the eval harness to enforce safety gates before deployment.

Frequently Asked Questions about healthcare-eval-harness

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate patient safety verification for EMR and EHR deployments in CI/CD pipelines?

Patient safety verification is automated by enforcing five-category evaluation gates within CI/CD pipelines to block unsafe EMR and EHR deployments before production release. The harness checks CDSS logic, PHI exposure, and data integrity.

What are the pass thresholds for CDSS validation and clinical workflow safety checks?

CDSS validation, PHI exposure, and data integrity checks are CRITICAL gates requiring a strict 100% pass rate. Clinical workflow and integration evaluations enforce a 95% or higher pass threshold to permit deployment.

How does automated safety evaluation handle regulatory compliance for healthcare system releases?

Automated safety evaluation handles regulatory compliance by enforcing mandatory safety gates across five categories. It validates CDSS logic, checks PHI exposure, and blocks deployments failing these regulatory thresholds before release.

Can I configure evaluation thresholds and pass/fail reporting for CDSS logic changes?

Yes, evaluation thresholds are configurable for CDSS logic changes. The harness provides pass/fail reporting and remediation guidance to support rapid safety validation of authentication and schema updates before production.

What happens when a healthcare deployment fails data integrity or PHI exposure safety gates?

When a healthcare deployment fails data integrity or PHI exposure safety gates, the release is blocked automatically. The harness generates pass/fail reporting and provides remediation guidance to resolve the safety violations.