agentic-qe 1.3.3 → 1.3.4

package/.claude/agents/qe-api-contract-validator.md

@@ -33,6 +33,26 @@ metadata:
 
 The API Contract Validator agent **prevents breaking API changes** by validating contracts against consumer expectations, detecting backward compatibility issues, and ensuring semantic versioning compliance. Using contract-first testing, schema validation, and consumer-driven contracts, this agent catches 95% of integration issues before deployment. It transforms API evolution from a risky breaking-change minefield into a safe, predictable process with confidence in backward compatibility.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **api-testing-patterns**: Comprehensive API testing patterns including contract testing, REST/GraphQL testing
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **contract-testing**: Consumer-driven contract testing for microservices using Pact and API versioning
+- **regression-testing**: Strategic regression testing with test selection, impact analysis, and continuous regression management
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show contract-testing
+
+# Via Skill tool in Claude Code
+Skill("contract-testing")
+Skill("regression-testing")
+```
+
 ## Core Capabilities
 
 ### 1. Schema Validation

package/.claude/agents/qe-chaos-engineer.md

@@ -37,6 +37,26 @@ metadata:
 7. **Rollback Automation**: Automatically abort and rollback failed experiments
 8. **Observability Integration**: Correlate chaos events with system metrics
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **risk-based-testing**: Focus testing effort on highest-risk areas using risk assessment
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **chaos-engineering-resilience**: Chaos engineering principles, controlled failure injection, and resilience testing
+- **shift-right-testing**: Testing in production with feature flags, canary deployments, synthetic monitoring, and chaos engineering
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show chaos-engineering-resilience
+
+# Via Skill tool in Claude Code
+Skill("chaos-engineering-resilience")
+Skill("shift-right-testing")
+```
+
 ## Analysis Workflow
 
 ### Phase 1: Experiment Planning

package/.claude/agents/qe-coverage-analyzer.md

@@ -44,6 +44,27 @@ Specialized agent for intelligent test coverage analysis and optimization using
 - **Coverage Trend Analysis**: Track coverage patterns across test runs with temporal modeling
 - **Multi-framework Support**: Unified analysis across Jest, Mocha, Pytest, JUnit
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **quality-metrics**: Measure quality effectively with actionable metrics and KPIs
+- **risk-based-testing**: Focus testing effort on highest-risk areas using risk assessment
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **regression-testing**: Strategic regression testing with test selection, impact analysis, and continuous regression management
+- **test-reporting-analytics**: Comprehensive test reporting with metrics, trends, and actionable insights
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show regression-testing
+
+# Via Skill tool in Claude Code
+Skill("regression-testing")
+Skill("test-reporting-analytics")
+```
+
 ### 2. Sublinear Algorithm Integration
 - **Matrix Optimization**: Apply spectral sparsification to coverage matrices
 - **Dimensionality Reduction**: JL-transform for large codebases (>10k LOC)

package/.claude/agents/qe-deployment-readiness.md

@@ -33,6 +33,26 @@ metadata:
 
 The Deployment Readiness agent is the **final guardian before production**. It aggregates quality signals from all testing stages, calculates comprehensive risk scores, and provides data-driven go/no-go deployment decisions. By analyzing code quality, test coverage, performance benchmarks, security scans, and historical deployment patterns, this agent prevents 90% of production incidents and reduces MTTR by 65%. It transforms deployment from a high-stress gamble into a confident, predictable process backed by quantitative evidence.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **risk-based-testing**: Focus testing effort on highest-risk areas using risk assessment
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **shift-right-testing**: Testing in production with feature flags, canary deployments, synthetic monitoring, and chaos engineering
+- **compliance-testing**: Regulatory compliance testing for GDPR, CCPA, HIPAA, SOC2, and PCI-DSS
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show shift-right-testing
+
+# Via Skill tool in Claude Code
+Skill("shift-right-testing")
+Skill("compliance-testing")
+```
+
 ## Core Capabilities
 
 ### 1. Risk Scoring

package/.claude/agents/qe-flaky-test-hunter.md

@@ -41,6 +41,26 @@ metadata:
 
 The Flaky Test Hunter agent **eliminates test flakiness** through intelligent detection, root cause analysis, and automated stabilization. Using statistical analysis, pattern recognition, and ML-powered prediction, this agent identifies flaky tests with 98% accuracy, diagnoses root causes, and auto-remediates common flakiness patterns. It transforms unreliable test suites into rock-solid confidence builders, achieving 95%+ test reliability and eliminating the "just rerun it" anti-pattern.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **exploratory-testing-advanced**: Advanced exploratory testing techniques with Session-Based Test Management (SBTM)
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **mutation-testing**: Test quality validation through mutation testing and measuring test suite effectiveness
+- **test-reporting-analytics**: Comprehensive test reporting with metrics, trends, and actionable insights
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show mutation-testing
+
+# Via Skill tool in Claude Code
+Skill("mutation-testing")
+Skill("test-reporting-analytics")
+```
+
 ## Core Capabilities
 
 ### 1. Flaky Detection

package/.claude/agents/qe-fleet-commander.md

@@ -37,6 +37,26 @@ metadata:
 7. **Scaling Orchestration**: Auto-scale agent pools based on demand and performance metrics
 8. **Performance Monitoring**: Track fleet-wide metrics and optimize coordination patterns
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **risk-based-testing**: Focus testing effort on highest-risk areas using risk assessment
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **test-environment-management**: Manage test environments, infrastructure as code, and environment provisioning
+- **test-reporting-analytics**: Comprehensive test reporting with metrics, trends, and actionable insights
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show test-environment-management
+
+# Via Skill tool in Claude Code
+Skill("test-environment-management")
+Skill("test-reporting-analytics")
+```
+
 ## Analysis Workflow
 
 ### Phase 1: Fleet Initialization

package/.claude/agents/qe-performance-tester.md

@@ -62,6 +62,27 @@ description: "Multi-tool performance testing with load orchestration, bottleneck
 
 **Role**: Performance validation specialist focused on load testing, bottleneck detection, and SLA validation for quality engineering workflows.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **performance-testing**: Test application performance, scalability, and resilience with load testing
+- **quality-metrics**: Measure quality effectively with actionable metrics and KPIs
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **shift-right-testing**: Testing in production with feature flags, canary deployments, synthetic monitoring, and chaos engineering
+- **test-environment-management**: Manage test environments, infrastructure as code, and environment provisioning
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show shift-right-testing
+
+# Via Skill tool in Claude Code
+Skill("shift-right-testing")
+Skill("test-environment-management")
+```
+
 ## Core Capabilities
 
 ### 🚀 Load Testing Orchestration

package/.claude/agents/qe-production-intelligence.md

@@ -33,6 +33,26 @@ metadata:
 
 The Production Intelligence agent creates a **continuous feedback loop** from production to testing by converting real user behavior, incidents, and anomalies into comprehensive test scenarios. By analyzing RUM (Real User Monitoring) data, replaying incidents, and mining error patterns, this agent eliminates the 80% of bugs that only appear in production. It ensures that testing environments accurately reflect real-world usage, transforming production into the ultimate source of truth for test case generation and validation.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **exploratory-testing-advanced**: Advanced exploratory testing techniques with Session-Based Test Management (SBTM)
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **shift-right-testing**: Testing in production with feature flags, canary deployments, synthetic monitoring, and chaos engineering
+- **test-reporting-analytics**: Comprehensive test reporting with metrics, trends, and actionable insights
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show shift-right-testing
+
+# Via Skill tool in Claude Code
+Skill("shift-right-testing")
+Skill("test-reporting-analytics")
+```
+
 ## Core Capabilities
 
 ### 1. Incident Replay

package/.claude/agents/qe-quality-analyzer.md

@@ -35,6 +35,26 @@ integration_points:
 
 # Quality Analyzer Agent
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **quality-metrics**: Measure quality effectively with actionable metrics and KPIs
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **test-reporting-analytics**: Comprehensive test reporting with metrics, trends, and actionable insights
+- **compliance-testing**: Regulatory compliance testing for GDPR, CCPA, HIPAA, SOC2, and PCI-DSS
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show test-reporting-analytics
+
+# Via Skill tool in Claude Code
+Skill("test-reporting-analytics")
+Skill("compliance-testing")
+```
+
 ## Core Responsibilities
 
 ### Primary Functions

package/.claude/agents/qe-quality-gate.md

@@ -35,6 +35,26 @@ integration_points:
 
 # Quality Gate Agent
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **quality-metrics**: Measure quality effectively with actionable metrics and KPIs
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **test-reporting-analytics**: Comprehensive test reporting with metrics, trends, and actionable insights
+- **compliance-testing**: Regulatory compliance testing for GDPR, CCPA, HIPAA, SOC2, and PCI-DSS
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show test-reporting-analytics
+
+# Via Skill tool in Claude Code
+Skill("test-reporting-analytics")
+Skill("compliance-testing")
+```
+
 ## Core Responsibilities
 
 ### Primary Functions

package/.claude/agents/qe-regression-risk-analyzer.md

@@ -33,6 +33,26 @@ metadata:
 
 The Regression Risk Analyzer agent revolutionizes CI/CD efficiency by **intelligently selecting the minimal set of tests** required to validate code changes. Using static analysis, dynamic dependency tracking, and ML-powered historical pattern learning, this agent reduces CI execution time by 90% while maintaining 95% defect detection rate. It transforms regression testing from "run everything" to "run exactly what matters," enabling 10x faster feedback loops without sacrificing quality.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **risk-based-testing**: Focus testing effort on highest-risk areas using risk assessment
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **regression-testing**: Strategic regression testing with test selection, impact analysis, and continuous regression management
+- **test-design-techniques**: Advanced test design using equivalence partitioning, boundary value analysis, and decision tables
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show regression-testing
+
+# Via Skill tool in Claude Code
+Skill("regression-testing")
+Skill("test-design-techniques")
+```
+
 ## Core Capabilities
 
 ### 1. Change Impact Analysis

package/.claude/agents/qe-requirements-validator.md

@@ -33,6 +33,26 @@ metadata:
 
 The Requirements Validator agent is the **first line of defense** in the quality engineering process. It validates requirements for testability, completeness, and clarity BEFORE any code is written. By converting ambiguous requirements into concrete BDD scenarios and identifying missing acceptance criteria, this agent prevents 70% of late-stage defects and reduces rework by 60%. It ensures that every requirement is measurable, testable, and traceable from conception to deployment.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **risk-based-testing**: Focus testing effort on highest-risk areas using risk assessment
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **shift-left-testing**: Move testing activities earlier in development lifecycle with TDD, BDD, and design for testability
+- **test-design-techniques**: Advanced test design using equivalence partitioning, boundary value analysis, and decision tables
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show shift-left-testing
+
+# Via Skill tool in Claude Code
+Skill("shift-left-testing")
+Skill("test-design-techniques")
+```
+
 ## Core Capabilities
 
 ### 1. Testability Analysis

package/.claude/agents/qe-security-scanner.md

@@ -67,6 +67,27 @@ description: "Multi-layer security scanning with SAST/DAST, vulnerability detect
 
 **Role**: Security validation specialist focused on SAST/DAST scanning, vulnerability detection, and compliance validation for comprehensive security testing.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **security-testing**: Test for security vulnerabilities using OWASP principles and security testing techniques
+- **risk-based-testing**: Focus testing effort on highest-risk areas using risk assessment
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **compliance-testing**: Regulatory compliance testing for GDPR, CCPA, HIPAA, SOC2, and PCI-DSS
+- **shift-left-testing**: Move testing activities earlier in development lifecycle with TDD, BDD, and design for testability
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show compliance-testing
+
+# Via Skill tool in Claude Code
+Skill("compliance-testing")
+Skill("shift-left-testing")
+```
+
 ## Core Capabilities
 
 ### 🔒 Static Application Security Testing (SAST)

package/.claude/agents/qe-test-data-architect.md

@@ -32,6 +32,25 @@ metadata:
 
 The Test Data Architect agent **eliminates manual test data creation** by generating realistic, schema-aware test data that preserves relationships, satisfies constraints, and covers edge cases. Using schema analysis, production data patterns, and intelligent faker libraries, this agent creates comprehensive test datasets in seconds instead of hours. It ensures data privacy through anonymization, maintains referential integrity, and generates both common and edge-case scenarios, enabling thorough testing without the burden of manual data management.
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **test-data-management**: Realistic test data generation, GDPR compliance, and data masking strategies
+- **database-testing**: Database schema validation, data integrity testing, migration testing, and query performance
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show test-data-management
+
+# Via Skill tool in Claude Code
+Skill("test-data-management")
+Skill("database-testing")
+```
+
 ## Core Capabilities
 
 ### 1. Schema-Aware Generation

package/.claude/agents/qe-test-executor.md

@@ -36,6 +36,26 @@ The Test Executor Agent orchestrates parallel test execution across multiple fra
 - **Resource Optimization**: Dynamically allocate workers based on system capacity
 - **Progress Monitoring**: Provide real-time test execution status and metrics
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **test-automation-strategy**: Design and implement comprehensive test automation strategies
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **test-environment-management**: Manage test environments, infrastructure as code, and environment provisioning
+- **test-reporting-analytics**: Comprehensive test reporting with metrics, trends, and actionable insights
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show test-environment-management
+
+# Via Skill tool in Claude Code
+Skill("test-environment-management")
+Skill("test-reporting-analytics")
+```
+
 ## Execution Workflow
 
 ### 1. Pre-Execution Phase

package/.claude/agents/qe-test-generator.md

@@ -39,6 +39,28 @@ metadata:
 4. **Framework Integration**: Support multiple testing frameworks with adaptive generation
 5. **Quality Assurance**: Ensure generated tests meet quality standards and best practices
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **api-testing-patterns**: Comprehensive API testing patterns including contract testing, REST/GraphQL testing
+- **tdd-london-chicago**: Apply both London and Chicago school TDD approaches
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **shift-left-testing**: Move testing activities earlier in development lifecycle with TDD, BDD, and design for testability
+- **test-design-techniques**: Advanced test design using equivalence partitioning, boundary value analysis, and decision tables
+- **test-data-management**: Realistic test data generation, GDPR compliance, and data masking strategies
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show shift-left-testing
+
+# Via Skill tool in Claude Code
+Skill("shift-left-testing")
+Skill("test-design-techniques")
+```
+
 ## Analysis Workflow
 
 ### Phase 1: Code Analysis

package/.claude/agents/qe-visual-tester.md

@@ -37,6 +37,28 @@ metadata:
 7. **Color Contrast Validation**: Ensure sufficient color contrast ratios
 8. **Performance Monitoring**: Track visual rendering performance metrics
 
+## Skills Available
+
+### Core Testing Skills (Phase 1)
+- **agentic-quality-engineering**: Using AI agents as force multipliers in quality work
+- **exploratory-testing-advanced**: Advanced exploratory testing techniques with Session-Based Test Management (SBTM)
+
+### Phase 2 Skills (NEW in v1.3.0)
+- **visual-testing-advanced**: Advanced visual regression testing with AI-powered screenshot comparison and UI validation
+- **accessibility-testing**: WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification
+- **compatibility-testing**: Cross-browser, cross-platform, and cross-device compatibility testing
+
+Use these skills via:
+```bash
+# Via CLI
+aqe skills show visual-testing-advanced
+
+# Via Skill tool in Claude Code
+Skill("visual-testing-advanced")
+Skill("accessibility-testing")
+Skill("compatibility-testing")
+```
+
 ## Analysis Workflow
 
 ### Phase 1: Baseline Capture