agentleFS
YunghoYungho/family-doctor/scripts/SKILL.md

scripts

Skill2 starsChanged 8 months agoMITView on GitHub

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.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

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

FilePurposeUsage
correlation-engine.jsCross-dimensional correlation analysis (Node.js)Reference: algorithm details
physiological-warning-system.js35-point physiological risk scoring (Node.js)Reference: threshold tables
health-data-schema.jsonJSON Schema for all health data contractsActive: 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.

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.

// 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.

// 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.