Fitness analyzer

Exercise Analyzer Skill

Analyze exercise data, identify activity patterns, assess fitness progress, and provide personalized training advice.

Functions

1. Exercise-trend analysis

Analyze trends in exercise volume, frequency, and intensity; identify what is improving or needs adjustment.

Analysis dimensions:

• Exercise-volume trend (duration, distance, calories)
• Exercise-frequency trend (workout days per week)
• Intensity-distribution change (low/medium/high share)
• Change in exercise-type preference

Output:

• Trend direction (improving/stable/declining)
• Magnitude and percentage of change
• Trend significance
• Improvement suggestions

2. Progress tracking

Track progress in specific exercise types and quantify fitness gains.

Supported progress tracking:

• Running progress: pace improvement, distance increase, heart-rate improvement
• Strength-training progress: weight increase, volume increase, RPE change
• Endurance progress: longer duration, longer distance
• Flexibility progress: improved range of motion

Output:

• Starting value vs. current value
• Improvement percentage
• Progress visualization
• Milestones reached

3. Exercise-habit analysis

Identify the user's exercise habits and patterns.

Analysis content:

• Usual workout time (morning/afternoon/evening)
• Frequency pattern (days per week)
• Exercise-type preference
• Rest-day distribution
• Exercise-consistency score

Output:

• Habit summary
• Consistency score (0-100)
• Optimization suggestions
• Habit-formation advice

4. Correlation analysis

Analyze the correlation between exercise and other health metrics.

Supported correlations:

• Exercise ↔ weight: relationship between exercise burn and weight change
• Exercise ↔ blood pressure: long-term effect of exercise on blood pressure
• Exercise ↔ blood glucose: effect of exercise on glycemic control
• Exercise ↔ mood/sleep: effect of exercise on mood and sleep

Output:

• Correlation coefficient (-1 to 1)
• Correlation strength (weak/medium/strong)
• Statistical significance
• Causal-relationship inference
• Practical suggestions

5. Personalized recommendations

Generate personalized exercise advice from the user's data.

Recommendation types:

• Frequency: whether to increase/decrease workout frequency
• Intensity: intensity-adjustment advice
• Type: recommended exercise types to try
• Timing: best time to exercise
• Recovery: rest and recovery advice

Basis:

• WHO/ACSM/AHA exercise guidelines
• The user's exercise history
• The user's health status
• The user's fitness goals

Output Format

Trend-analysis report

# Exercise Trend Analysis Report

## Analysis period
2025-03-20 to 2025-06-20 (3 months)

## Exercise-volume trend

### Duration
- Trend: ⬆️ rising
- Start: avg 120 min/week
- Current: avg 180 min/week
- Change: +50% (+60 min/week)
- Interpretation: marked increase in exercise volume, excellent

### Calorie burn
- Trend: ⬆️ rising
- Start: avg 960 kcal/week
- Current: avg 1440 kcal/week
- Change: +50%
- Interpretation: higher burn supports weight management

### Distance
- Trend: ⬆️ rising
- Start: avg 10 km/week
- Current: avg 20 km/week
- Change: +100%
- Interpretation: marked improvement in endurance

## Exercise frequency

- Current frequency: 4 days/week
- Target frequency: 4-5 days/week
- Status: ✅ on target
- Suggestion: maintain current frequency

## Intensity distribution

| Intensity | Share | Change |
|-----------|-------|--------|
| Low | 25% | +5% |
| Medium | 55% | -10% |
| High | 20% | +5% |

**Analysis**: intensity distribution is reasonable, dominated by medium intensity, in line with aerobic-exercise guidance.

## Exercise-type distribution

| Exercise type | Share |
|---------------|-------|
| Running | 50% |
| Yoga | 25% |
| Strength training | 25% |

**Suggestion**: consider raising the strength-training share to 30-40%.

## Insights and Suggestions

### Strengths
1. ✅ Steady growth in exercise volume (+50%)
2. ✅ Stable frequency, 4 days/week
3. ✅ Adequate rest days, good recovery

### Improvement suggestions
1. 📈 Add 2 strength-training sessions per week
2. 📈 Try different exercise types to avoid monotony
3. 📈 Add some high-intensity interval training (HIIT)

### Cautions
1. ⚠️ Keep intensity from being too high; favor medium intensity

Correlation-analysis report

# Exercise vs. Blood-Pressure Correlation Analysis

## Data sources
- Exercise data: fitness-logs (2025-03-20 to 2025-06-20)
- Blood-pressure data: hypertension-tracker (same period)

## Results

### Correlation coefficient
- Variables: weekly exercise duration ↔ systolic blood pressure
- Correlation: r = -0.68
- Strength: **strong negative correlation**
- Significance: p < 0.01 **highly significant**

### Interpretation
Exercise duration is strongly negatively correlated with systolic blood pressure, meaning:
- More exercise → lower blood pressure
- Each additional 30 minutes of exercise lowers systolic BP by 3-5 mmHg on average

### Practical suggestions
1. ✅ Keep exercising regularly, 5-7 days/week
2. ✅ 30-60 minutes per session, medium intensity
3. ✅ Prefer aerobic exercise (brisk walking, jogging, cycling)
4. ⚠️ Avoid breath-holding and sudden explosive movements

### Medical reference
- AHA statement: regular aerobic exercise can lower systolic BP by 5-7 mmHg
- Your exercise effect: about 10 mmHg reduction  significant!

Progress-tracking report

# Running Progress Tracking

## Analysis period
2025-01-01 to 2025-06-20 (6 months)

## Pace progress

| Metric | Start | Current | Improvement |
|--------|-------|---------|-------------|
| Average pace | 7:30 min/km | 6:00 min/km | +20% ⬆️ |
| Fastest pace | 7:00 min/km | 5:30 min/km | +22% ⬆️ |
| 5 km time | 37:30 | 30:00 | +20% ⬆️ |

**Trend**: steady pace improvement  significant progress!

## Distance progress

| Metric | Start | Current | Improvement |
|--------|-------|---------|-------------|
| Longest single distance | 3 km | 12 km | +300% ⬆️ |
| Monthly total distance | 40 km | 86 km | +115% ⬆️ |
| Average distance | 5 km | 6 km | +20% ⬆️ |

**Trend**: large endurance gains; able to cover longer distances.

## Heart-rate improvement

| Metric | Start | Current | Improvement |
|--------|-------|---------|-------------|
| Resting heart rate | 78 bpm | 72 bpm | -6 bpm ⬇️ |
| HR at same pace | 155 bpm | 145 bpm | -10 bpm ⬇️ |

**Analysis**: marked cardiorespiratory improvement; lower heart rate at the same pace.

## Milestones

- ✅ 2025-03-15: first 5 km run
- ✅ 2025-05-20: first 10 km run
- ✅ 2025-06-10: pace broke 6:00 min/km

## Next goals

- 🎯 Complete a half marathon (21 km)
- 🎯 Improve pace to 5:30 min/km
- 🎯 Try interval training to boost speed

Data Sources

Primary data sources

1. Exercise logs

   • Path: data/fitness-logs/YYYY-MM/YYYY-MM-DD.json
   • Content: workout records (type, duration, intensity, heart rate, distance, etc.)
   • Frequency: updated after each workout

2. User profile

   • Path: data/fitness-tracker.json
   • Content: user profile, fitness goals, statistics
   • Updates: periodically

3. Linked health data

   • data/hypertension-tracker.json (blood-pressure data)
   • data/diabetes-tracker.json (blood-glucose data)
   • data/profile.json (weight, BMI, etc.)

Data-quality checks

• Completeness: check that required fields exist
• Plausibility: check that values are within reasonable ranges
• Time consistency: check that timestamps are reasonable
• Duplicates: detect and handle duplicate records

Algorithm Notes

1. Linear-regression trend analysis

Use linear regression to analyze the time trend of exercise data.

Formula: y = a + bx

Where:

• y: exercise metric (duration, calories, distance, etc.)
• x: time
• a: intercept
• b: slope (trend direction and speed)

Interpretation:

• b > 0: rising trend
• b < 0: declining trend
• b ≈ 0: stable

2. Pearson correlation coefficient

Used to analyze the linear correlation between two variables.

Formula: r = Σ[(xi - x̄)(yi - ȳ)] / √[Σ(xi - x̄)² × Σ(yi - ȳ)²]

Range: -1 ≤ r ≤ 1

Interpretation:

• r = 1: perfect positive correlation
• r = -1: perfect negative correlation
• r = 0: no linear correlation

Strength:

• |r| < 0.3: weak
• 0.3 ≤ |r| < 0.7: medium
• |r| ≥ 0.7: strong

3. Pace calculation

Pace = exercise duration / distance

Units: min/km or min/mile

Example:

• 30 minutes to run 5 km
• Pace = 30 / 5 = 6 min/km

4. MET energy calculation

Calories burned = MET × weight(kg) × time(hours)

Common MET values:

• Walking (3-5 km/h): 3.5-5 MET
• Jogging (8 km/h): 8 MET
• Fast running (10 km/h): 10 MET
• Swimming: 6-10 MET
• Cycling (leisure): 4 MET
• Strength training: 5 MET
• Yoga: 3 MET

Medical Safety Boundaries

⚠️ Important note This analysis is for health reference only and does not constitute medical advice.

Scope of analysis

✅ Can do:

• Statistics and analysis of exercise data
• Trend identification and visualization
• Correlation calculation and interpretation
• General exercise suggestions

❌ Cannot do:

• Disease diagnosis
• Exercise-risk assessment
• Designing specific exercise prescriptions
• Diagnosing or treating exercise injuries

Danger-sign detection

Detect the following danger signs during analysis:

1. Abnormal heart rate

   • Exercise HR > 95% of max HR
   • Resting HR > 100 bpm

2. Abnormal blood pressure

   • Systolic ≥ 180 mmHg
   • Diastolic ≥ 110 mmHg

3. Signs of overtraining

   • 7 consecutive days of high-intensity exercise
   • Continuously worsening perceived exertion (RPE > 17)

4. Rapid weight loss

   • Weekly loss > 1 kg (possibly unhealthy)

Recommendation tiers

Level 1: general advice

• Based on WHO/ACSM guidelines
• For the general population

Level 2: informational advice

• Based on user data
• Must be combined with personal context

Level 3: medical advice

• Involves disease management
• Requires physician confirmation

Usage Examples

Example 1: generate an exercise-trend report

/fitness trend 3months

Output:

• 3-month exercise-trend analysis
• Changes in volume, frequency, intensity
• Insights and suggestions

Example 2: track running progress

/fitness analysis progress running

Output:

• Pace progress
• Distance progress
• Heart-rate improvement
• Milestones reached

Example 3: analyze exercise–blood-pressure correlation

/fitness analysis correlation blood_pressure

Output:

• Correlation coefficient
• Correlation strength
• Significance test
• Practical suggestions

---

Skill version: v1.0 Last updated: 2026-01-02 Maintainer: MedClawMini