- name
- scripts
- description
- Development-time utility scripts and data schemas for family-doctor skills. Do not trigger directly — read when implementing correlation algorithms, risk scoring, or data validation. Provides: correlation-engine.js, physiological-warning-system.js, health-data-schema.json.
- allowed-tools
- ["read","glob","bash"]
# Scripts — Development Utilities
Development-time utility scripts and data schemas. These are **not runtime dependencies** — skills implement their logic directly in markdown instructions. These files serve as **reference implementations** and **data contracts**.
## Resources
| File | Purpose | Usage |
|------|---------|-------|
| `correlation-engine.js` | Cross-dimensional correlation analysis (Node.js) | Reference: algorithm details |
| `physiological-warning-system.js` | 35-point physiological risk scoring (Node.js) | Reference: threshold tables |
| `health-data-schema.json` | JSON Schema for all health data contracts | **Active**: use as data standard |
## health-data-schema.json (ACTIVE — Data Contract)
JSON Schema (Draft-07) defining all health data structures. This is the **primary data contract** for the family-doctor suite. Skills should produce data conforming to this schema.
```bash
read --path "scripts/health-data-schema.json"
```
Key definitions:
- `vital-signs`: BP, HR, temperature, SpO2, weight (with metric/imperial support)
- `blood-glucose`: glucose readings with context
- `thyroid-nodule`: TI-RADS classification
- `breast-nodule`: BI-RADS classification
- `lung-nodule`: Fleischner guideline tracking
- `prostatitis`: NIH-CPSI score records
- `mental-health`: PHQ-9, GAD-7, PSS scores
- `medication`: drug, dosage, adherence
- `lab-result`: test name, value, unit, reference range
- `family-history`: first/second-degree relatives, conditions, age at diagnosis
## correlation-engine.js (REFERENCE — Algorithm)
Node.js module demonstrating cross-dimensional correlation analysis.
```javascript
// Usage: node correlation-engine.js [condition] [data-file.json]
```
**Note**: Skills implement correlation logic directly in markdown using natural language. This file documents the algorithm for reference only.
Correlation rules:
- hypertension ↔ sodium, exercise, sleep, stress, alcohol, potassium
- insomnia ↔ caffeine, exercise timing, anxiety, screen time
- hyperglycemia ↔ carbs, post-meal exercise, medication adherence
- depression ↔ sleep, exercise, omega-3, vitamin D
- thyroid nodule ↔ TSH, iodine, selenium, cancer anxiety
Output: `{ target, correlation_r, recommendation }`
## physiological-warning-system.js (REFERENCE — Thresholds)
Node.js module demonstrating multi-dimensional physiological risk scoring.
```javascript
// Usage: node physiological-warning-system.js [data-file.json]
```
**Note**: Skills implement risk scoring directly in markdown. This file documents the threshold tables for reference only.
Risk scoring (0-35 points):
- Vital Signs: 40% weight (max 14 pts)
- 7-day Trends: 25% weight (max 9 pts)
- Medication Adherence: 20% weight (max 7 pts)
- Symptoms: 15% weight (max 5 pts)
Risk levels:
- ≥15: High Risk (seek care within 24h)
- 8-14: Medium Risk (consult doctor within 48h)
- <8: Low Risk (continue monitoring)
---
**Version**: 1.0.0
**Updated**: 2026-03-21
**Note**: These are development-time reference files, not runtime dependencies.
Ver no GitHub