Fitness Analyzer Skill
Analyze sports data, identify exercise patterns, evaluate fitness progress, and provide personalized training recommendations.
Features
1. Exercise Trend Analysis
Analyze the changing trends of exercise volume, frequency, and intensity, and identify areas for improvement or adjustment.
Analysis Dimensions:
- Exercise volume trends (duration, distance, calories)
- Exercise frequency trends (number of exercise days per week)
- Intensity distribution changes (proportion of low/medium/high intensity)
- Changes in exercise type preferences
Output:
- Trend direction (improvement/stable/decline)
- Magnitude and percentage of change
- Trend significance
- Improvement suggestions
2. Fitness Progress Tracking
Track progress in specific exercise types and quantify fitness effects.
Supported Progress Tracking:
- Running Progress: Pace improvement, distance increase, heart rate improvement
- Strength Training Progress: Weight increase, volume improvement, RPE changes
- Endurance Progress: Exercise duration increase, distance extension
- Flexibility Progress: Joint mobility improvement
Output:
- Starting value vs. current value
- Improvement percentage
- Progress visualization
- Achieved milestones
3. Exercise Habit Analysis
Identify users' exercise habits and patterns.
Analysis Content:
- Common exercise times (morning/afternoon/evening)
- Exercise frequency patterns (number of days per week)
- Exercise type preferences
- 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 indicators.
Supported Correlation Analysis:
- Exercise ↔ Weight: Relationship between exercise consumption and weight changes
- Exercise ↔ Blood Pressure: Long-term impact of exercise on blood pressure
- Exercise ↔ Blood Glucose: Effect of exercise on blood glucose control
- Exercise ↔ Mood/Sleep: Impact of exercise on mood and sleep
Output:
- Correlation coefficient (-1 to 1)
- Correlation strength (weak/medium/strong)
- Statistical significance
- Causal inference
- Practical suggestions
5. Personalized Recommendation Generation
Generate personalized exercise recommendations based on user data.
Recommendation Types:
- Exercise Frequency Suggestions: Whether to increase/decrease exercise frequency
- Exercise Intensity Suggestions: Intensity adjustment recommendations
- Exercise Type Suggestions: Recommended exercise types to try
- Exercise Time Suggestions: Optimal exercise time
- Recovery Suggestions: Rest and recovery recommendations
Recommendation Basis:
- WHO/ACSM/AHA exercise guidelines
- User's exercise history data
- User's health status
- User's fitness goals
Output Formats
Trend Analysis Report
markdown
# Exercise Trend Analysis Report
## Analysis Period
2025-03-20 to 2025-06-20 (3 months)
## Exercise Volume Trends
### Exercise Duration
- Trend: ⬆️ Increasing
- Starting: Average 120 minutes/week
- Current: Average 180 minutes/week
- Change: +50% (+60 minutes/week)
- Interpretation: Exercise volume has increased significantly, excellent performance
### Calorie Burn
- Trend: ⬆️ Increasing
- Starting: Average 960 calories/week
- Current: Average 1440 calories/week
- Change: +50%
- Interpretation: Exercise consumption has increased, which is beneficial for weight management
### Exercise Distance
- Trend: ⬆️ Increasing
- Starting: Average 10 km/week
- Current: Average 20 km/week
- Change: +100%
- Interpretation: Endurance has improved significantly
## Exercise Frequency
- Current frequency: 4 days/week
- Target frequency: 4-5 days/week
- Status: ✅ Meeting standard
- Suggestion: Maintain current frequency
## Intensity Distribution
|------|------|------|
| Low intensity | 25% | +5% |
| Medium intensity | 55% | -10% |
| High intensity | 20% | +5% |
**Analysis**: The intensity distribution is reasonable, with medium intensity as the main focus, which is in line with aerobic exercise recommendations.
## Exercise Type Distribution
|---------|------|
| Running | 50% |
| Yoga | 25% |
| Strength Training | 25% |
**Suggestion**: Appropriately increase the proportion of strength training to 30-40%.
## Insights and Suggestions
### Strengths
1. ✅ Exercise volume has grown steadily (+50%)
2. ✅ Exercise frequency is stable, 4 days per week
3. ✅ Sufficient rest days, good recovery
### Improvement Suggestions
1. 📈 Add 2 strength training sessions per week
2. 📈 Try different exercise types to avoid monotony
3. 📈 Appropriately increase high-intensity interval training (HIIT)
### Warnings
1. ⚠️ Avoid excessive exercise intensity, focus on medium intensity as the mainstay
Correlation Analysis Report
markdown
# Correlation Analysis between Exercise and Blood Pressure
## Data Sources
- Exercise data: fitness-logs (2025-03-20 to 2025-06-20)
- Blood pressure data: hypertension-tracker (same period)
## Analysis Results
### Correlation Coefficient
- Variables: Weekly exercise duration ↔ Systolic blood pressure
- Correlation coefficient: r = -0.68
- Correlation strength: **Strong negative correlation**
- Statistical significance: p < 0.01 **Highly significant**
### Interpretation
There is a strong negative correlation between exercise duration and systolic blood pressure, which means:
- The more exercise, the lower the blood pressure
- For every additional 30 minutes of exercise, systolic blood pressure decreases by an average of 3-5 mmHg
### Practical Suggestions
1. ✅ Continue regular exercise, 5-7 days per week
2. ✅ Exercise for 30-60 minutes each time, medium intensity
3. ✅ Prioritize aerobic exercise (brisk walking, jogging, cycling)
4. ⚠️ Avoid breath-holding movements and sudden explosive exercises
### Medical Reference
- AHA statement: Regular aerobic exercise can reduce systolic blood pressure by 5-7 mmHg
- Your exercise effect: Reduced by approximately 10 mmHg, significant effect!
Progress Tracking Report
markdown
# Running Progress Tracking
## Analysis Period
2025-01-01 to 2025-06-20 (6 months)
## Pace Progress
|------|------|------|------|
| Average pace | 7:30 min/km | 6:00 min/km | +20% ⬆️ |
| Fastest pace | 7:00 min/km | 5:30 min/km | +22% ⬆️ |
| 5km time | 37:30 | 30:00 | +20% ⬆️ |
**Trend**: Pace has continued to improve steadily, significant progress!
## Distance Progress
|------|------|------|------|
| Longest single distance | 3 km | 12 km | +300% ⬆️ |
| Monthly total distance | 40 km | 86 km | +115% ⬆️ |
| Average distance | 5 km | 6 km | +20% ⬆️ |
**Trend**: Endurance has improved significantly, able to complete longer distances.
## Heart Rate Improvement
|------|------|------|------|
| Resting heart rate | 78 bpm | 72 bpm | -6 bpm ⬇️ |
| Heart rate at same pace | 155 bpm | 145 bpm | -10 bpm ⬇️ |
**Analysis**: Cardiopulmonary function has improved significantly, with lower heart rate at the same pace.
## Milestones
- ✅ 2025-03-15: Completed 5km run for the first time
- ✅ 2025-05-20: Completed 10km run for the first time
- ✅ 2025-06-10: Pace broke through 6:00 min/km
## Next Goals
- 🎯 Complete a half marathon (21 km)
- 🎯 Improve pace to 5:30 min/km
- 🎯 Try interval training to improve speed
Data Sources
Main Data Sources
-
Fitness Logs
- Path:
data/fitness-logs/YYYY-MM/YYYY-MM-DD.json
- Content: Exercise records (type, duration, intensity, heart rate, distance, etc.)
- Frequency: Updated after each exercise
-
User Profile
- Path:
data/fitness-tracker.json
- Content: User profile, fitness goals, statistical data
- Update: Regularly updated
-
Health Data Correlation
data/hypertension-tracker.json
data/diabetes-tracker.json
- (weight, BMI, etc.)
Data Quality Check
- Data completeness: Check if necessary fields exist
- Data rationality: Check if values are within reasonable ranges
- Time consistency: Check if timestamps are reasonable
- Duplicate data: Detect and handle duplicate records
Algorithm Description
1. Linear Regression Trend Analysis
Use linear regression to analyze the time trend of exercise data.
Formula:
y = a + bx
Where:
- y: Exercise indicator (duration, calories, distance, etc.)
- x: Time
- a: Intercept
- b: Slope (trend direction and speed)
Interpretation:
- b > 0: Increasing trend
- b < 0: Decreasing 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
Intensity Judgment:
- |r| < 0.3: Weak correlation
- 0.3 ≤ |r| < 0.7: Medium correlation
- |r| ≥ 0.7: Strong correlation
3. Pace Calculation
Pace = Exercise duration / Distance
Unit: min/km or min/mile
Example:
- Run 5 km in 30 minutes
- Pace = 30 / 5 = 6 min/km
4. MET Metabolic Equivalent Calculation
Calorie Burn = MET × Weight(kg) × Time(hours)
MET Values for Common Exercises:
- Walking (3-5 km/h): 3.5-5 MET
- Jogging (8 km/h): 8 MET
- 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 Notice
This analysis is for health reference only and does not constitute medical advice.
Scope of Analysis Capabilities
✅ Can Do:
- Statistics and analysis of exercise data
- Trend identification and visualization
- Correlation calculation and interpretation
- General exercise recommendations
❌ Cannot Do:
- Disease diagnosis
- Exercise risk assessment
- Design of specific exercise prescriptions
- Diagnosis and treatment of exercise injuries
Warning Signal Detection
Detect the following warning signals during analysis:
-
Abnormal Heart Rate
- Exercise heart rate > 95% of maximum heart rate
- Resting heart rate > 100 bpm
-
Abnormal Blood Pressure
- Systolic blood pressure ≥ 180 mmHg
- Diastolic blood pressure ≥ 110 mmHg
-
Signs of Overtraining
- 7 consecutive days of high-intensity exercise
- Continuous decline in exercise feeling (RPE > 17)
-
Rapid Weight Loss
- Weight loss > 1kg per week (may be unhealthy)
Recommendation Levels
Level 1: General Recommendations
- Based on WHO/ACSM guidelines
- Suitable for general population
Level 2: Reference Recommendations
- Based on user data
- Need to be combined with personal situation
Level 3: Medical Recommendations
- Involves disease management
- Need doctor's confirmation
Usage Examples
Example 1: Generate Exercise Trend Report
Output:
- 3-month exercise trend analysis
- Changes in exercise volume, frequency, and intensity
- Insights and suggestions
Example 2: Track Running Progress
bash
/fitness analysis progress running
Output:
- Pace improvement
- Distance improvement
- Heart rate improvement
- Milestones achieved
Example 3: Analyze Correlation between Exercise and Blood Pressure
bash
/fitness analysis correlation blood_pressure
Output:
- Correlation coefficient
- Correlation strength
- Significance test
- Practical suggestions
Skill Version: v1.0
Last Updated: 2026-01-02
Maintainer: WellAlly Tech