growth-learning

randysalars's avatarfrom randysalars

Analytics, feedback processing, and continuous improvement

0stars🔀0forks📁View on GitHub🕐Updated Jan 9, 2026

When & Why to Use This Skill

This Claude skill facilitates a comprehensive 'Growth & Learning' feedback loop designed for continuous system optimization. By integrating performance analytics, audience feedback processing, and automated code reviews, it enables users to transform raw session data into a structured knowledge base of lessons learned and evolving best practices.

Use Cases

  • Performance Benchmarking: Automatically evaluate YouTube engagement and retention metrics against industry-standard benchmarks to identify specific growth opportunities.
  • Audience Sentiment Analysis: Process viewer comments and feedback to extract qualitative insights and integrate 'Voice of the Customer' into future project planning.
  • Iterative System Improvement: Maintain an evolving knowledge base of lessons learned to ensure successful patterns are replicated and known pitfalls are avoided in subsequent sessions.
  • Technical Quality Assurance: Conduct automated code quality reviews to ensure development standards are met and continuously improved over time.
nameGrowth & Learning
tier4
load_policyconditional
descriptionAnalytics, feedback processing, and continuous improvement
version1.0.0

Growth & Learning Skill (Tier 4)

The Feedback Loop That Makes Us Better

This tier contains skills for analyzing performance and improving future sessions.


Purpose

Process feedback, analyze metrics, and continuously improve the Dreamweaving system.


Load Conditions

This tier loads conditionally when:

  • Processing YouTube analytics data
  • Analyzing viewer comments
  • Reviewing code quality
  • Applying lessons to new sessions

Sub-Skills

Skill Location Purpose
Analytics Learning analytics-learning/ Process YouTube metrics
Feedback Integration feedback-integration/ Extract insights from comments

Feedback Loop

Session Published
       ↓
Analytics Collected (30-90 days)
       ↓
Lessons Extracted
       ↓
Knowledge Base Updated
       ↓
Applied to Next Session
       ↓
[Repeat]

Key Metrics Tracked

Category Metrics
Engagement Views, likes, comments, shares
Retention Average view duration, retention %
Growth Subscribers gained, impressions
Quality Like ratio, comment sentiment

Benchmarks

Metric Good Average Needs Work
Retention (30 min) >50% 30-50% <30%
Like Ratio >8% 4-8% <4%
Comment Rate >1% 0.5-1% <0.5%
Sub Conversion >2% 1-2% <1%

Knowledge Base Files

File Purpose
knowledge/lessons_learned.yaml Accumulated insights
knowledge/best_practices.md Evolving standards
knowledge/analytics_history/ Historical data

Commands

# Process analytics for a session
/learn-analytics session-name

# Analyze comments
/learn-comments session-name

# Review code quality
/review-code

# Show accumulated lessons
/show-lessons

Integration with Production

When creating new sessions:

  1. Check lessons_learned.yaml first
  2. Apply successful patterns
  3. Avoid known pitfalls
  4. Test new approaches systematically

Related Resources

  • Serena Memory: session_learnings_system
  • Doc: docs/CANONICAL_WORKFLOW.md (learning section)
growth-learning – AI Agent Skills | Claude Skills