Healthcare Eval Harness
Patient-safety deployment gates for healthcare apps with Muse: CDSS accuracy, PHI exposure, and data integrity as blocking tests, plus clinical workflow and integration thresholds.
- What
- Patient-safety deployment gates for healthcare apps with Muse: CDSS accuracy, PHI exposure, and data integrity as blocking tests, plus clinical workflow and integration thresholds.
- Cost
- Free
- Needs
- Use "Healthcare Eval Harness" with your Muse.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: an automated patient-safety verification system that makes Muse gate healthcare application deployments on five test categories. The first three are CRITICAL gates requiring a 100% pass rate, where a single failure blocks deployment: CDSS accuracy (drug interaction pairs in both directions, dose validation rules, clinical scoring against published specs, no false negatives, no silent failures), PHI exposure (leaks in API error responses, console output, URL parameters, browser storage, cross-facility isolation, unauthenticated access), and data integrity (locked encounters, audit trail entries, cascade delete protection, concurrent edits, no orphaned records). The remaining two are HIGH gates at 95%+: clinical workflow (encounter lifecycle, medication sets, prescription PDFs, red flag alerts) and integration compliance (HL7 v2.x parsing, FHIR validation, lab result mapping). The skill ships copy-ready CI pipelines that run critical gates with bail-on-first-failure semantics, anti-patterns to avoid (never mock the CDSS engine in integration tests, never lower critical thresholds below 100%), and an eval report template with a SAFE TO DEPLOY verdict. Contributed by Dr. Keyur Patel (Health1 Super Speciality Hospitals). By @affaan-m, listed here with credit to its creator. From the affaan-m/ECC repository (MIT). Honest caveats: examples use Jest, adapt commands to your framework; gates test what you wrote tests for, they do not replace clinical review or real-world validation; patient safety logic deserves a human expert in the loop. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseThe install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Use "Healthcare Eval Harness" with your Muse. Prerequisites: none to install. Pure guidance; a healthcare app with tests helps. 1. Open the skill: https://github.com/affaan-m/ECC/blob/main/skills/healthcare-eval-harness/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Set up the safety gate for this healthcare app: [paste project context]. Map my test suites to the five eval categories." 3. Ask it to draft the CI pipeline with critical gates at 100% (bail on first failure) and high gates at 95%+, plus the eval report template. Tip: ask "which of my current tests map to PHI exposure, and what is missing?" Safety: a skill is plain-text instructions; it runs nothing by itself. Never paste real PHI into any chat while testing.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.