Communitygithub.com

healthcare-eval-harness

Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.

healthcare-eval-harness란 무엇인가요?

healthcare-eval-harness is a Claude Code agent skill that patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.

지원 대상~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/healthcare-eval-harness

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

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.

Each category maps to a Jest test path pattern. The CI pipeline runs CRITICAL gates with --bail (stop on first failure) and enforces coverage thresholds with --coverage --coverageThreshold.

Eval Categories

1. CDSS Accuracy (CRITICAL — 100% required)

Tests all clinical decision support logic: drug interaction pairs (both directions), dose validation rules, clinical scoring vs published specs, no false negatives, no silent failures.

npx jest --testPathPattern='tests/cdss' --bail --ci --coverage

2. PHI Exposure (CRITICAL — 100% required)

Tests for protected health information leaks: API error responses, console output, URL parameters, browser storage, cross-facility isolation, unauthenticated access, service role key absence.

npx jest --testPathPattern='tests/security/phi' --bail --ci

3. Data Integrity (CRITICAL — 100% required)

Tests clinical data safety: locked encounters, audit trail entries, cascade delete protection, concurrent edit handling, no orphaned records.

npx jest --testPathPattern='tests/data-integrity' --bail --ci

4. Clinical Workflow (HIGH — 95%+ required)

Tests end-to-end flows: encounter lifecycle, template rendering, medication sets, drug/diagnosis search, prescription PDF, red flag alerts.

tmp_json=$(mktemp)
npx jest --testPathPattern='tests/clinical' --ci --json --outputFile="$tmp_json" || true
total=$(jq '.numTotalTests // 0' "$tmp_json")
passed=$(jq '.numPassedTests // 0' "$tmp_json")
if [ "$total" -eq 0 ]; then
  echo "No clinical tests found" >&2
  exit 1
fi
rate=$(echo "scale=2; $passed * 100 / $total" | bc)
echo "Clinical pass rate: ${rate}% ($passed/$total)"

5. Integration Compliance (HIGH — 95%+ required)

Tests external systems: HL7 message parsing (v2.x), FHIR validation, lab result mapping, malformed message handling.

tmp_json=$(mktemp)
npx jest --testPathPattern='tests/integration' --ci --json --outputFile="$tmp_json" || true
total=$(jq '.numTotalTests // 0' "$tmp_json")
passed=$(jq '.numPassedTests // 0' "$tmp_json")
if [ "$total" -eq 0 ]; then
  echo "No integration tests found" >&2
  exit 1
fi
rate=$(echo "scale=2; $passed * 100 / $total" | bc)
echo "Integration pass rate: ${rate}% ($passed/$total)"

Pass/Fail Matrix

CategoryThresholdOn Failure
CDSS Accuracy100%BLOCK deployment
PHI Exposure100%BLOCK deployment
Data Integrity100%BLOCK deployment
Clinical Workflow95%+WARN, allow with review
Integration95%+WARN, allow with review

CI/CD Integration

name: Healthcare Safety Gate
on: [push, pull_request]

jobs:
  safety-gate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: '20'
      - run: npm ci

      # CRITICAL gates — 100% required, bail on first failure
      - name: CDSS Accuracy
        run: npx jest --testPathPattern='tests/cdss' --bail --ci --coverage --coverageThreshold='{"global":{"branches":80,"functions":80,"lines":80}}'

      - name: PHI Exposure Check
        run: npx jest --testPathPattern='tests/security/phi' --bail --ci

      - name: Data Integrity
        run: npx jest --testPathPattern='tests/data-integrity' --bail --ci

      # HIGH gates — 95%+ required, custom threshold check
      # HIGH gates — 95%+ required
      - name: Clinical Workflows
        run: |
          TMP_JSON=$(mktemp)
          npx jest --testPathPattern='tests/clinical' --ci --json --outputFile="$TMP_JSON" || true
          TOTAL=$(jq '.numTotalTests // 0' "$TMP_JSON")
          PASSED=$(jq '.numPassedTests // 0' "$TMP_JSON")
          if [ "$TOTAL" -eq 0 ]; then
            echo "::error::No clinical tests found"; exit 1
          fi
          RATE=$(echo "scale=2; $PASSED * 100 / $TOTAL" | bc)
          echo "Pass rate: ${RATE}% ($PASSED/$TOTAL)"
          if (( $(echo "$RATE < 95" | bc -l) )); then
            echo "::warning::Clinical pass rate ${RATE}% below 95%"
          fi

      - name: Integration Compliance
        run: |
          TMP_JSON=$(mktemp)
          npx jest --testPathPattern='tests/integration' --ci --json --outputFile="$TMP_JSON" || true
          TOTAL=$(jq '.numTotalTests // 0' "$TMP_JSON")
          PASSED=$(jq '.numPassedTests // 0' "$TMP_JSON")
          if [ "$TOTAL" -eq 0 ]; then
            echo "::error::No integration tests found"; exit 1
          fi
          RATE=$(echo "scale=2; $PASSED * 100 / $TOTAL" | bc)
          echo "Pass rate: ${RATE}% ($PASSED/$TOTAL)"
          if (( $(echo "$RATE < 95" | bc -l) )); then
            echo "::warning::Integration pass rate ${RATE}% below 95%"
          fi

Anti-Patterns

  • Skipping CDSS tests "because they passed last time"
  • Setting CRITICAL thresholds below 100%
  • Using --no-bail on CRITICAL test suites
  • Mocking the CDSS engine in integration tests (must test real logic)
  • Allowing deployments when safety gate is red
  • Running tests without --coverage on CDSS suites

Examples

Example 1: Run All Critical Gates Locally

npx jest --testPathPattern='tests/cdss' --bail --ci --coverage && \
npx jest --testPathPattern='tests/security/phi' --bail --ci && \
npx jest --testPathPattern='tests/data-integrity' --bail --ci

Example 2: Check HIGH Gate Pass Rate

tmp_json=$(mktemp)
npx jest --testPathPattern='tests/clinical' --ci --json --outputFile="$tmp_json" || true
jq '{
  passed: (.numPassedTests // 0),
  total: (.numTotalTests // 0),
  rate: (if (.numTotalTests // 0) == 0 then 0 else ((.numPassedTests // 0) / (.numTotalTests // 1) * 100) end)
}' "$tmp_json"
# Expected: { "passed": 21, "total": 22, "rate": 95.45 }

Example 3: Eval Report

## Healthcare Eval: 2026-03-27 [commit abc1234]

### Patient Safety: PASS

| Category | Tests | Pass | Fail | Status |
|----------|-------|------|------|--------|
| CDSS Accuracy | 39 | 39 | 0 | PASS |
| PHI Exposure | 8 | 8 | 0 | PASS |
| Data Integrity | 12 | 12 | 0 | PASS |
| Clinical Workflow | 22 | 21 | 1 | 95.5% PASS |
| Integration | 6 | 6 | 0 | PASS |

### Coverage: 84% (target: 80%+)
### Verdict: SAFE TO DEPLOY

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

api-connector-builder

Build a new API connector or provider by matching the target repo

관련 스킬