
Healthcare Eval Harness
A deployment gate for healthcare apps that enforces patient safety through five test categories, three of which block deployment on any failure. CDSS accuracy, PHI exposure, and data integrity must hit 100% pass rate with bail on first failure, while clinical workflows and integration compliance need 95%+. The examples show Jest commands but the threshold logic works with any test runner. Contributed by Dr. Keyur Patel from Health1 Super Speciality Hospitals, so it reflects real clinical deployment constraints. The anti-patterns list is unusually specific (no mocking the CDSS engine, no skipping tests because they passed last time), which suggests this came from actual incidents. If you deploy EMR/EHR systems, the pass/fail matrix and CI examples are immediately useful.
- skills.sh installs
- 3.8K
- GitHub stars
- 229.1K
- last updated
- Jul 14, 2026
Install
$ npx -y skills add affaan-m/everything-claude-code --skill healthcare-eval-harness --agent claude-codeInstalls into .claude/skills of the current project.
Files
Healthcare Eval Harness — Patient Safety Verification
Automated verification system for healthcare application deployments. A single CRITICAL failure blocks deployment. Patient safety is non-negotiable.
Note: Examples use Jest as the reference test runner. Adapt commands for your framework (Vitest, pytest, PHPUnit, etc.) — the test categories and pass thresholds are framework-agnostic.
When to Use
- Before any deployment of EMR/EHR applications
- After modifying CDSS logic (drug interactions, dose validation, scoring)
- After changing database schemas that touch patient data
- After modifying authentication or access control
- During CI/CD pipeline configuration for healthcare apps
- After resolving merge conflicts in clinical modules
How It Works
The eval harness runs five test categories in order. The first three (CDSS Accuracy, PHI Exposure, Data Integrity) are CRITICAL gates requiring 100% pass rate — a single failure blocks deployment. The remaining two (Clinical Workflow, Integration) are HIGH gates requiring 95%+ pass rate.
Sponsors
Details
- Repository
- github.com/affaan-m/everything-claude-code
- First seen
- Apr 16, 2026
More from affaan-m/everything-claude-code
All 256- Manim Video3.8K
- Ui Demo3.8K
- Agent Introspection Debugging3.7K
- Connections Optimizer3.7K
- Dotnet Patterns3.7K
- Finance Billing Ops3.7K
- Gan Style Harness3.7K
- Google Workspace Ops3.7K
- Knowledge Ops3.7K
- Lead Intelligence3.7K
- Openclaw Persona Forge3.7K
- Opensource Pipeline3.7K
- Security Bounty Hunter3.7K
- Workspace Surface Audit3.7K
- Accessibility3.6K
- Agent Sort3.6K
- Api Connector Builder3.6K
- Automation Audit Ops3.6K
- Code Tour3.6K
- Csharp Testing3.6K
- Github Ops3.6K
- Hipaa Compliance3.6K
- Llm Trading Agent Security3.6K
- Project Flow Ops3.6K