AI Skill Report Card

Analyzing Fitness Data

B-72·May 30, 2026·Source: Extension-page
10 / 15
Python
# Extract key metrics from fitness dashboard def analyze_fitness_dashboard(dashboard_text): metrics = { 'user': extract_user_name(dashboard_text), 'weight_progress': extract_weight_evolution(dashboard_text), 'training_frequency': count_training_sessions(dashboard_text), 'total_load': extract_total_load(dashboard_text), 'progress_trend': calculate_trend(dashboard_text) } return generate_insights(metrics)
Recommendation
Add concrete input/output examples showing actual dashboard text snippets with corresponding structured analysis results
12 / 15

Progress:

  • Parse dashboard interface elements
  • Extract quantitative metrics (weight, load, frequency)
  • Identify time periods and date ranges
  • Calculate progress trends
  • Generate actionable recommendations
  • Format insights for user consumption
Recommendation
Include a ready-to-use template or framework for fitness data analysis rather than just function names
15 / 20

Example 1: Input: Dashboard showing "Carga Total: 0 kg, Treinos: 0, Últimos 3 meses" Output:

Status: New user - no training history
Recommendation: Begin with assessment questionnaire
Next steps: Access "Meus Treinos" to start first workout

Example 2: Input: Weight evolution chart from 23/fev to 25/mai with 0.5-2kg variations Output:

Period: Feb 23 - May 25 (3 months)
Weight range: 0.5-2.0 kg progression
Trend: Gradual increase indicating strength gains
Average weekly progression: 0.2 kg
Recommendation
Expand completeness by covering edge cases like incomplete data, different fitness app formats, or missing metrics
  • Focus on progression trends rather than absolute values
  • Identify gaps in training consistency
  • Correlate load increases with time periods
  • Highlight milestone achievements
  • Provide context for zero values (new user vs. inactive period)
  • Extract date ranges accurately from Portuguese formats
  • Map interface elements to functional areas (questionnaires, exercises, muscle groups)
  • Don't assume zero values indicate failure - may indicate new user
  • Avoid comparing users without considering starting points
  • Don't ignore interface navigation elements - they show available features
  • Don't overlook date format differences (dd/mmm vs dd/mm)
  • Avoid making recommendations without understanding user's current phase
0
Grade B-AI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
10/15
Workflow
12/15
Examples
15/20
Completeness
8/20
Format
15/15
Conciseness
12/15