What problem does it solve? Raw test output is hard to act on: teams struggle to spot failure patterns, judge release readiness, and communicate quality risk to stakeholders. This Skill turns test result data into statistical insights, defect predictions, and go/no-go recommendations. ## Core Features & Use Cases - Test Coverage & Failure Analysis: Evaluates line, branch, and function coverage, identifies gaps, and categorizes failures by type with root cause analysis. - Defect Prediction & Risk Assessment: Uses machine learning models (e.g., RandomForestClassifier) to predict defect-prone areas and compute release readiness with confidence levels. - Stakeholder Reporting: Produces executive dashboards and technical reports with quality KPIs, ROI analysis, and prioritized recommendations. - Use Case: After a CI pipeline run, feed the JSON test results to the analyzer to get a release readiness score, top quality risks, and a go/no-go recommendation backed by statistical confidence. ## Quick Start Analyze the test results in results.json and produce a release readiness report with coverage gaps, failure patterns, and a go/no-go recommendation.