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

family-health

Skill2 starsChanged 8 months agoMITView on GitHub

Family health history management and genetic risk assessment. Use when user mentions family medical history, hereditary diseases, family risk factors, parents' health conditions, genetic predisposition, or asks about inherited disease risks. Triggers on: family history, hereditary, genetic risk, family health, parents' conditions, inherited diseases, family disease pattern.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user about their family health history.

    line 22
  2. Distinctive:

    Start screening 5-10 years earlier than standard recommendation

    line 120
  3. Distinctive:

    Start screening at earliest recommended age or 10 years before earliest family diagnosis

    line 125
  4. Distinctive:

    Consider comprehensive screening panel

    line 127

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Family Health — Hereditary Risk Assessment & Family History Management

Manage family health history and assess genetic predisposition risk based on documented family disease patterns. Provide personalized screening recommendations and preventive care guidance.

When to Use

  • User mentions family medical history ("my father had...")
  • User asks about hereditary disease risks
  • User wants to understand genetic predisposition
  • User asks about screening recommendations based on family history
  • User wants to build a family health tree
  • Trigger phrases: "family history", "hereditary", "genetic risk", "parents' health", "inherited", "family disease"

Step 1: Gather Family Health Data

Ask the user about their family health history. Use Socratic approach:

First-degree relatives (ask about each):

  • Father: age, health conditions, age at diagnosis of any diseases
  • Mother: age, health conditions, age at diagnosis
  • Siblings: health conditions, age at diagnosis

Second-degree relatives (if provided):

  • Grandparents: health conditions, cause of death, age at death
  • Aunts/Uncles: health conditions

For each condition, record:

  • Who has it (relationship)
  • What condition
  • Age at diagnosis
  • Severity (if provided)

Step 2: Calculate Genetic Risk Score

Based on OpenClaw family-health-analyzer algorithm:

Weighted Risk Formula

Genetic Risk Score = (F1 × 0.4) + (F2 × 0.3) + (F3 × 0.3)

Where:
- F1 = First-degree relatives with condition (weight 0.4)
- F2 = Early-onset cases (<50 years) × 0.3
- F3 = Family clustering score × 0.3

Family Clustering Score

PatternScore
No family history0
1 second-degree relative0.2
1 first-degree relative0.4
2 first-degree relatives (same condition)0.6
3+ first-degree relatives0.8
Cross-generational (parent + grandparent)0.7

Early-Onset Multiplier

Age at DiagnosisMultiplier
≥60 years0
50-59 years0.2
40-49 years0.5
<40 years1.0

Step 3: Risk Classification

By Score Range

Risk LevelScoreInterpretation
Low<40Normal population risk, follow standard screening
Moderate40-69Elevated risk, consider earlier/more frequent screening
High≥70Significant genetic predisposition, personalized screening plan required

By Condition Category

Cardiovascular

  • High risk: 1 parent with MI/stroke <55 (male) or <65 (female)
  • Moderate risk: 2+ relatives with hypertension before 50
  • Elevated screening: lipid panel, BP monitoring from age 30

Diabetes

  • High risk: 1 first-degree relative with T2DM
  • Very high risk: 2+ first-degree relatives, or 1 with early onset (<50)
  • Elevated screening: HbA1c from age 35, or 10 years before earliest family diagnosis

Cancer

  • High risk: 2+ first-degree relatives with same cancer
  • Very high risk: Any first-degree relative diagnosed <50
  • BRCA/Lynch syndrome referral if indicated

Mental Health

  • Family history of depression, anxiety, or substance use
  • Triggers earlier PHQ-9/GAD-7 monitoring
  • Increased suicide risk awareness

Thyroid/Nodules

  • Family history of thyroid cancer or autoimmune thyroid disease
  • Triggers more frequent thyroid monitoring
  • Lower threshold for FNA biopsy consideration

Step 4: Personalized Screening Recommendations

Based on risk score, recommend:

Low Risk

  • Standard age-based screening per USPSTF guidelines
  • Maintain healthy lifestyle

Moderate Risk

  • Start screening 5-10 years earlier than standard recommendation
  • Increase frequency (e.g., annual instead of every 3 years)
  • Consider additional biomarkers

High Risk

  • Start screening at earliest recommended age or 10 years before earliest family diagnosis
  • Discuss with doctor about genetic referral if applicable
  • Consider comprehensive screening panel
  • Lifestyle intervention with highest priority

Step 5: Cross-Dimensional Correlation

Family history should inform other skills:

Family HistoryAuto-Correlations to Trigger
Cardiovascularvital-monitor (BP priority), chronic-care (hypertension), preventive-care (cardiac screening)
Diabeteschronic-care (glucose monitoring), nutrition-advisor (carbs control)
Cancerpreventive-care (cancer screening), mental-health (cancer anxiety)
Thyroidchronic-care (thyroid nodule monitoring), vital-monitor (TSH tracking)
Mental Healthmental-health (more frequent PHQ-9), sleep-analyzer (sleep-health link)

Step 6: Create Family Health Record

Store in health/ directory:

health/
├── Family History.md
└── Family History.json

JSON Schema

{
  "family_history": {
    "first_degree": [
      {
        "relative": "father",
        "conditions": [
          {
            "name": "Type 2 Diabetes",
            "age_at_diagnosis": 55,
            "severity": "controlled",
            "notes": "On metformin"
          }
        ]
      }
    ],
    "second_degree": [
      {
        "relative": "maternal_grandmother",
        "conditions": [
          {
            "name": "Breast Cancer",
            "age_at_diagnosis": 62,
            "severity": "treated",
            "notes": "Early stage, no recurrence"
          }
        ]
      }
    ]
  },
  "risk_assessment": {
    "cardiovascular": {
      "score": 52,
      "level": "moderate",
      "factors": ["father MI at 58"]
    },
    "diabetes": {
      "score": 40,
      "level": "moderate",
      "factors": ["father T2DM at 55"]
    }
  },
  "screening_recommendations": [
    {
      "test": "HbA1c",
      "start_age": 35,
      "frequency": "annual",
      "reason": "Family history of T2DM"
    }
  ],
  "last_updated": "2026-03-21"
}

Output Format

# Family Health Assessment — [Date]

## Family History Summary

| Relative | Condition | Age at Dx | Notes |
|----------|-----------|-----------|-------|
| Father | Type 2 Diabetes | 55 | On metformin |
| Mother | Hypertension | 58 | Controlled |
| Mat. Grandmother | Breast Cancer | 62 | Treated |

## Genetic Risk Scores

| Condition | Score | Risk Level | Key Factors |
|-----------|-------|------------|-------------|
| Type 2 Diabetes | 52 | Moderate | Father T2DM at 55 |
| Cardiovascular | 45 | Moderate | Father MI at 58 |
| Breast Cancer | 32 | Low | 1 second-degree, age >50 |

## Screening Recommendations

**Diabetes Screening**
- Start: Age 35 (10 years before father's diagnosis)
- Frequency: Annual
- Test: HbA1c or fasting glucose

**Cardiovascular Screening**
- Start: Age 30 (earlier due to family history)
- Frequency: Annual lipid panel + BP check
- Consider: CAC scoring after 40

## Cross-Dimensional Correlations

🔗 Family history of T2DM + cardiovascular disease → increased monitoring priority
→ Recommend: nutrition-advisor (carb awareness), vital-monitor (BP + glucose tracking)

## Action Plan

- [ ] Complete detailed family health interview
- [ ] Schedule HbA1c test at next checkup
- [ ] Discuss lipid panel with doctor
- [ ] Add BP monitoring to weekly routine

Safety Boundaries

Can Do:

  • Collect and document family health history
  • Calculate statistical risk scores based on family patterns
  • Recommend screening schedules based on risk level
  • Provide lifestyle modification guidance
  • Cross-correlate family history with current health data
  • Educate about genetic risk factors

Cannot Do:

  • Diagnose genetic or hereditary diseases
  • Predict individual disease probability with certainty
  • Recommend specific treatment plans
  • Replace genetic counseling
  • Interpret genetic test results (refer to genetic counselor)

Every output must include:

⚠️ This risk assessment is based on family health history patterns and is for informational purposes only. It does not constitute a medical diagnosis. Consult your healthcare provider for personalized screening plans and medical advice. Genetic counseling is recommended for high-risk families.

Reference Standards

  • ACC/AHA: Cardiovascular risk screening with family history
  • ADA: Diabetes risk screening based on family history
  • USPSTF: Age-based screening modifications for high-risk individuals
  • NCCN: Cancer family history assessment guidelines

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.