Learning Evolution

Overview

The learning-evolution skill tracks, analyzes, and evolves learning patterns from skill usage and user interactions. It helps skills improve over time by identifying patterns, capturing insights, and suggesting evolutions based on real-world usage.

When to Use

• - Analyzing how skills are being used
• Identifying learning opportunities from usage patterns
• Tracking skill improvement over time
• Evolving skills based on user feedback
• Understanding what works and what doesn't
• Planning skill updates and improvements
• Measuring skill effectiveness

Core Concepts

Learning Dimensions

Evolution Patterns

Learning Sources

1. 1. Usage Analytics: Frequency, patterns, drop-offs
2. Error Analysis: Failures, edge cases, bugs
3. User Feedback: Explicit ratings and comments
4. Outcome Tracking: Success vs failure rates
5. Comparative Analysis: Vs alternatives, vs past versions

Input

Accepts:

• - Skill usage data
• User feedback and ratings
• Error logs and failure patterns
• Success/outcome metrics
• Time range for analysis

Output

Produces:

• - Learning reports
• Evolution recommendations
• Pattern analyses
• Improvement suggestions
• Trend forecasts

Workflow

Usage Pattern Analysis

1. 1. Collect usage data over time period
2. Identify frequency and timing patterns
3. Analyze completion rates
4. Find drop-off points
5. Compare to expected usage
6. Generate insights

Effectiveness Tracking

1. 1. Define success criteria
2. Track success/failure rates
3. Analyze error patterns
4. Identify common failure modes
5. Measure improvement over time
6. Recommend fixes

Evolution Planning

1. 1. Review learning insights
2. Prioritize improvement areas
3. Design evolution options
4. Estimate impact of changes
5. Create evolution roadmap
6. Plan measurement approach

Feedback Integration

1. 1. Collect user feedback
2. Categorize feedback themes
3. Correlate with usage data
4. Identify priority issues
5. Generate improvement ideas
6. Update skill accordingly

Commands

Analyze Usage Patterns

Track Effectiveness

Generate Learning Report

Suggest Evolutions

Compare Versions

Track Learning Metrics

Output Format

Learning Report

Evolution Suggestion

Learning Metrics

Usage Metrics

• - Total invocations
• Unique users
• Frequency distribution
• Time-to-completion
• Drop-off points

Quality Metrics

• - Success rate
• Error rate by type
• User ratings
• Return rate
• Net Promoter Score

Evolution Metrics

• - Version adoption rate
• Feature usage
• Improvement velocity
• Learning cycle time
• Knowledge transfer

Quality Rules

• - Base recommendations on data, not assumptions
• Correlate multiple data sources
• Validate insights with users when possible
• Track prediction accuracy
• Document learning for future reference
• Share insights across skills

Good Trigger Examples

• - "How is this skill performing?"
• "What can we learn from usage patterns?"
• "Suggest improvements based on feedback"
• "Analyze effectiveness over time"
• "What patterns emerge from errors?"
• "How should this skill evolve?"
• "Compare this version to the previous one"

Limitations

• - Requires sufficient usage data for meaningful analysis
• Patterns may not generalize to all users
• Correlation does not imply causation