learning-loop-engine

Analyze L2 skill report histories to identify recurring patterns and recommend improvements across three modes.

1|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/mytechsonamy/VibeFlow --skill learning-loop-engine
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learning-loop-engine
Source: https://github.com/mytechsonamy/VibeFlow/tree/main/skills/learning-loop-engine
Command: npx skills add https://github.com/mytechsonamy/VibeFlow --skill learning-loop-engine

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Consumes the full history of reports from every L2 skill, detects recurring patterns, traces production bugs back to missed test opportunities, detects quality drift across sprint baselines, and recommends the next maturity-stage improvements. Operates in three modes — test-history / production-feedback / drift-analysis — each with its own pattern-detection flow. Gate contract — every recommendation must be actionable, every pattern must carry ≥ 3 supporting observations, every production bug must trace to a specific test gap or be marked irreducible with justification. PIPELINE-6 step 1 / PIPELINE-7 step 1.

Core Features & Use Cases

  • The skill aggregates historical reports across L2/L3 to identify recurring quality patterns and growth opportunities.
  • It provides mode-specific recommendations for test-history, production-feedback, and drift-analysis, with traceable evidence to baselines, bugs, and tests.
  • It evaluates maturity stage against predefined criteria and surfaces actionable next steps for improvement.

Quick Start

Use the learning-loop-engine to generate an actionable improvement plan from historical sprint reports.

Frequently Asked Questions about learning-loop-engine

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect recurring quality patterns from sprint test history?

Recurring quality patterns from sprint test history are detected by aggregating L2 skill reports to identify repeated gaps and derive actionable improvements. This analysis requires at least three supporting observations with traceability to specific tests or scenarios.

How can I trace production bugs back to missed test opportunities?

Production bugs are traced to missed test opportunities using production-feedback pattern detection, which maps each bug to a specific test gap. If a bug cannot be traced, it must be explicitly marked as irreducible with justification.

What is quality drift analysis and how does it work across sprint baselines?

Quality drift analysis across sprint baselines detects degrading patterns by comparing historical L2 skill reports over time. The drift-analysis mode identifies these shifts and generates mode-specific recommendations to enforce gate constraints for actionable improvements.

Do I need a minimum number of observations to generate actionable sprint improvements?

Yes, a minimum of three supporting observations is required to validate any detected pattern and generate actionable sprint improvements. This gate constraint ensures every recommendation carries traceable evidence to specific tests or scenarios.

Can I use historical skill reports to evaluate and improve my maturity stage?

Historical skill reports can be evaluated against predefined criteria to determine your current maturity stage. The analysis surfaces actionable next steps, recommending targeted improvements to advance quality maturity based on detected recurring patterns.