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

health-trend-analyzer

Skill2 starsChanged 8 months agoMITView on GitHub

Analyze health data trends and patterns over time. Identify changes, correlations, and provide data-driven health insights. Use when user asks about health trends, patterns, changes over time, or 'how is my health changing?'. Supports multi-dimensional analysis (weight/BMI, symptoms, medication adherence, lab results, mood/sleep), correlation analysis, change detection, and predictive insights. Triggers on: health trends, health changes, health patterns, am I getting better, is my health improving, health trajectory, health forecast, health prediction, how has my health changed, health progress, wellness trends, vitality trends. Also triggers on Chinese: 健康趋势, 健康变化, 有没有改善, 病情变化, 身体状况变化.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read data from health/ directory:

    line 48
  2. Distinctive:

    If current trends continue, expected outcomes

    line 135

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Health Trend Analyzer

Analyze health data trends and patterns over time. Identify changes, correlations, and provide data-driven health insights.

When to Use

Activate this skill when user asks:

English Triggers:

  • "How has my health changed?"
  • "What are my health trends?"
  • "Am I getting better or worse?"
  • "Is my health improving?"
  • "What patterns do you see in my health data?"
  • "How is my [condition] progressing?"
  • "Predict my future health"
  • "What should I expect?"

Intent Matching (Claude should analyze intent, not just keywords):

  • User wants to understand changes over time
  • User wants to know if treatment is working
  • User wants predictions about future health
  • User wants to identify patterns in their data

Execution Steps

Step 1: Determine Time Range

Extract time range from user input, or use default (3 months).

User SaidTime Range
"past month" / "last month"1 month
"past 3 months" / "recently"3 months (default)
"past 6 months" / "half year"6 months
"past year" / "this year"12 months
"since [date]"From date to now

Step 2: Read Health Data

Read data from health/ directory:

health/
├── Health Profile.md          # Basic info, BMI, allergies, medications
├── Conditions/*.md            # Disease profiles with status
├── Conditions/*.json          # Structured condition data
├── Reports/*.md               # Lab results, test reports
└── Visits/*.md                # Visit notes

Data to extract:

  • Vital signs (BP, HR, weight, temperature)
  • Lab results (glucose, cholesterol, etc.)
  • Medication history and adherence
  • Condition status changes
  • Symptom records

Step 3: Trend Analysis

Analyze each dimension:

3.1 Vital Signs Trends

  • Blood pressure: Systolic/diastolic over time
  • Heart rate: Average, variability
  • Weight/BMI: Direction and magnitude of change
  • Temperature: Any fever patterns

3.2 Condition Progression

  • Status changes (stable, improving, worsening)
  • Follow-up results comparison
  • New symptoms or complications

3.3 Medication Effectiveness

  • Correlate medication start with symptom improvement
  • Check adherence patterns
  • Identify side effects

3.4 Lab Results Trends

  • Compare values across multiple reports
  • Flag abnormal values
  • Track improvement or deterioration

Step 4: Correlation Analysis

Identify relationships between dimensions:

Primary FactorCheck Correlations With
Blood pressureSodium intake, sleep, exercise, stress, medication adherence
Blood sugarDiet, exercise, medication, sleep
WeightDiet, exercise, sleep, stress
Mood/EnergySleep, exercise, social activity, chronic conditions
SymptomsMedication changes, lifestyle changes, environmental factors

Correlation Strength:

  • Strong: |r| >= 0.7
  • Moderate: 0.3 <= |r| < 0.7
  • Weak: |r| < 0.3

Step 5: Change Detection

Identify significant changes:

Positive Changes (improvements):

  • Vital signs moving toward normal range
  • Symptom frequency/severity decreasing
  • Lab results improving
  • Medication adherence improving

Negative Changes (concerns):

  • Vital signs moving away from normal
  • New symptoms appearing
  • Lab results deteriorating
  • Medication adherence declining

Threshold Alerts:

  • BP >= 180/110: Critical
  • BP >= 160/100: Urgent
  • Glucose > 300 or < 50: Critical
  • Weight change > 5% in 1 month: Significant

Step 6: Generate Predictions

Based on current trajectory:

Short-term (1-3 months):

  • If current trends continue, expected outcomes
  • Probability of reaching health goals
  • Risk of complications

Medium-term (6-12 months):

  • Long-term trend projections
  • Cumulative effects of lifestyle changes
  • Disease progression estimates

Important: Predictions are statistical estimates, not guarantees. Always emphasize that lifestyle changes can alter trajectories.

Step 7: Generate Report

Output format:

Health Trend Analysis Report
============================
Generated: [date]
Analysis Period: [start] to [end] ([duration])

Overall Assessment
------------------
[Improving/Stable/Declining] - [brief summary]

Vital Signs Trends
------------------
Blood Pressure:
  Current: [value] mmHg
  Trend: [direction] ([change] mmHg)
  Assessment: [emoji] [status]

Weight/BMI:
  Current: [weight] kg / BMI [value]
  Trend: [direction] ([change] kg)
  Assessment: [emoji] [status]

Condition Progression
---------------------
[Condition name]:
  Status: [current status]
  Change: [improvement/stable/worsening]
  Notes: [any relevant observations]

Medication Effectiveness
------------------------
[Medication name]:
  Adherence: [percentage]%
  Effectiveness: [assessment based on target metrics]
  Notes: [any side effects or concerns]

Correlation Analysis
--------------------
- [Factor A] <-> [Factor B]: [strength] [direction] (r=[value])
  Insight: [interpretation]

Significant Changes
-------------------
Positive:
- [improvement 1]
- [improvement 2]

Concerns:
- [concern 1]
- [concern 2]

Predictions (Based on Current Trajectory)
-----------------------------------------
Short-term (1-3 months):
- [prediction 1]
- [prediction 2]

Risk Assessment:
- [Risk level]: [description]

Recommendations
---------------
Priority 1: [most important action]
Priority 2: [second priority]
Priority 3: [third priority]

Monitoring Plan
---------------
- [What to track]
- [How often]
- [When to follow up]

---
Disclaimer: This analysis is based on your recorded data and is for reference only. It does not replace professional medical diagnosis or treatment advice. Consult your healthcare provider for any health concerns.

Safety Boundaries

Can Do:

  • Analyze historical trends
  • Identify correlations
  • Provide statistical projections
  • Suggest lifestyle modifications
  • Recommend monitoring plans

Cannot Do:

  • Diagnose diseases
  • Predict specific outcomes with certainty
  • Prescribe or adjust medications
  • Replace professional medical judgment

Every output must include:

This analysis is based on your recorded data and is for reference only. It does not replace professional medical diagnosis or treatment advice. Consult your healthcare provider for any health concerns. For emergencies, call your local emergency number immediately.


Version: 1.0.0 Updated: 2026-03-21 Based on: OpenClaw Medical Skills health-trend-analyzer (MIT License)

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.