skills/proffesor-for-testing__agentic-qe

mirror of https://github.com/proffesor-for-testing/agentic-qe.git synced 2026-09-19 08:45:47 +08:00

Files

T

Profa fd2f37eaa0 fix(v3): update README claims and init hooks to use correct package name

Changes:
- Fix README.md agent counts (48 QE agents = 41 main + 7 subagents)
- Fix README.md skill counts (15 QE-specific skills)
- Fix v3/README.md agent counts (47 → 48)
- Fix init-wizard.ts hooks from 'npx @agentic-qe/v3' to 'npx agentic-qe'
- Complete v2 → v2/ folder reorganization (54 items moved)
- Update root package.json to point to v3 as main version

Verified claims:
- 48 QE agents (41 main + 7 TDD subagents)
- 15 QE-specific skills
- 12 DDD bounded contexts
- ~5,600+ tests
- HNSW, ReasoningBank, Queen Coordinator features exist

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-17 18:03:40 +00:00

16 KiB

Raw Permalink Blame History

Agentic QE Fleet - Agent Reference

This document provides comprehensive reference for all 21 QE agents, 15 n8n workflow testing agents, and 11 subagents in the Agentic Quality Engineering Fleet.

Overview

The Agentic QE Fleet is a distributed swarm of AI agents for comprehensive software testing and quality assurance. Each agent specializes in specific quality engineering tasks and coordinates through the aqe/* memory namespace.

Core Testing Agents (5 agents)

qe-test-generator

AI-powered test generation with sublinear optimization

Capabilities:

Generates unit, integration, and E2E tests
Supports Jest, Mocha, Vitest, Playwright
Sublinear optimization algorithms for test selection
Property-based testing generation
Edge case discovery

Usage:

Task("Generate tests", "Create comprehensive test suite for UserService", "qe-test-generator")

Memory Namespace:

Stores: aqe/test-plan/generated
Reads: aqe/coverage/gaps

qe-test-executor

Multi-framework test execution with parallel processing

Capabilities:

Executes tests across multiple frameworks
Parallel test execution with worker pools
Real-time progress streaming
Test retry logic for flaky tests
Coverage collection

Usage:

Task("Execute tests", "Run test plan with 90% coverage target", "qe-test-executor")

Memory Namespace:

Stores: aqe/test-results/*
Reads: aqe/test-plan/generated

qe-coverage-analyzer

Real-time gap detection with O(log n) algorithms

Capabilities:

Incremental coverage analysis
Sublinear gap detection algorithms
Critical path identification
Coverage visualization
Untested code hotspot detection

Usage:

Task("Analyze coverage", "Find gaps using O(log n) algorithms", "qe-coverage-analyzer")

Memory Namespace:

Stores: aqe/coverage/gaps, aqe/coverage/results
Reads: aqe/test-results/*

qe-quality-gate

Intelligent quality gate with risk assessment

Capabilities:

Multi-factor risk assessment
Customizable quality thresholds
Trend analysis
Deployment readiness scoring
Automated go/no-go decisions

Usage:

Task("Quality check", "Run quality gate validation", "qe-quality-gate")

Memory Namespace:

Stores: aqe/quality/gate-results
Reads: aqe/coverage/results, aqe/test-results/*

qe-quality-analyzer

Comprehensive quality metrics analysis

Capabilities:

Quality metrics collection and analysis
Trend detection and prediction
Technical debt calculation
Code health scoring
Actionable insights generation

Usage:

Task("Quality analysis", "Analyze project quality metrics", "qe-quality-analyzer")

Memory Namespace:

Stores: aqe/quality/metrics
Reads: aqe/quality/*, aqe/test-results/*

Performance & Security Agents (2 agents)

qe-performance-tester

Load testing with k6, JMeter, Gatling integration

Capabilities:

Load, stress, and spike testing
Performance baseline establishment
Bottleneck identification
SLA validation
Multi-tool integration (k6, JMeter, Gatling)

Usage:

Task("Performance test", "Load test critical paths with 1000 concurrent users", "qe-performance-tester")

Memory Namespace:

Stores: aqe/performance/results
Reads: aqe/test-plan/*

qe-security-scanner

Multi-layer security with SAST/DAST scanning

Capabilities:

SAST (Static Application Security Testing)
DAST (Dynamic Application Security Testing)
Dependency vulnerability scanning
OWASP Top 10 validation
Security compliance checking

Usage:

Task("Security scan", "Run comprehensive security checks", "qe-security-scanner")

Memory Namespace:

Stores: aqe/security/findings
Reads: aqe/test-plan/*

Strategic Planning Agents (3 agents)

qe-requirements-validator

INVEST criteria validation and BDD generation

Capabilities:

Requirements testability analysis
INVEST criteria validation
BDD scenario generation (Gherkin)
Acceptance criteria validation
Requirements ambiguity detection

Usage:

Task("Validate requirements", "Check testability and generate BDD scenarios", "qe-requirements-validator")

Memory Namespace:

Stores: aqe/requirements/validated
Reads: aqe/test-plan/*

qe-production-intelligence

Production data to test scenarios conversion

Capabilities:

Production incident replay
RUM (Real User Monitoring) analysis
Log-based test generation
Production pattern extraction
Edge case discovery from production

Usage:

Task("Production intelligence", "Convert production incidents to test scenarios", "qe-production-intelligence")

Memory Namespace:

Stores: aqe/production/insights
Reads: Production logs, incident data

qe-fleet-commander

Hierarchical fleet coordination (50+ agents)

Capabilities:

Multi-agent orchestration
Resource allocation
Task decomposition and distribution
Agent performance monitoring
Coordination topology optimization

Usage:

Task("Fleet coordination", "Orchestrate 20 agents for comprehensive testing", "qe-fleet-commander")

Memory Namespace:

Stores: aqe/swarm/coordination
Reads: All aqe/* namespaces

Deployment Agent (1 agent)

qe-deployment-readiness

Multi-factor risk assessment for deployments

Capabilities:

Deployment risk scoring
Rollback plan validation
Production readiness checklist
Release notes generation
Deployment window optimization

Usage:

Task("Deployment check", "Assess deployment readiness", "qe-deployment-readiness")

Memory Namespace:

Stores: aqe/deployment/readiness
Reads: aqe/quality/*, aqe/test-results/*

Code Understanding Agent (1 agent)

qe-code-intelligence

Knowledge graph-based code understanding with 80% token reduction

Capabilities:

Tree-sitter multi-language parsing (TypeScript, Python, Go, Rust, JavaScript)
Semantic embeddings via Ollama nomic-embed-text (768 dimensions)
RuVector PostgreSQL storage with vector similarity search
Hybrid search (BM25 + Vector with RRF fusion)
Knowledge graph with entity relationships (imports, extends, calls)
Context building for other agents with 80% token reduction
Mermaid diagram generation (class diagrams, dependency graphs)
Incremental indexing with git change detection

Usage:

// Index codebase
Task("Index codebase", "Parse and index all TypeScript files in src/", "qe-code-intelligence")

// Semantic search
Task("Find auth code", "Search for code related to JWT authentication", "qe-code-intelligence")

// Build context for another agent
Task("Build test context", "Create context for UserService to pass to test-generator", "qe-code-intelligence")

CLI Commands:

aqe kg index              # Index codebase
aqe kg query "search"     # Semantic search
aqe kg graph file.ts      # Generate diagram
aqe kg stats              # Show statistics

Memory Namespace:

Stores: aqe/code-intelligence/index-stats, aqe/code-intelligence/context/*
Reads: aqe/project-metadata/*

Prerequisites: Ollama + nomic-embed-text, RuVector PostgreSQL. See Code Intelligence Quick Start.

Advanced Testing Agents (4 agents)

qe-regression-risk-analyzer

Smart test selection with ML patterns

Capabilities:

Change impact analysis
Intelligent test selection
Regression risk prediction
Test prioritization
Historical failure pattern analysis

Usage:

Task("Regression analysis", "Select minimal test suite for code changes", "qe-regression-risk-analyzer")

Memory Namespace:

Stores: aqe/regression/risk-analysis
Reads: aqe/test-results/*, learning patterns

qe-test-data-architect

High-speed realistic data generation (10k+ records/sec)

Capabilities:

Schema-aware data generation
Relationship preservation
Edge case coverage
GDPR-compliant data masking
High-performance generation (10k+ records/sec)

Usage:

Task("Generate test data", "Create 10k realistic user records", "qe-test-data-architect")

Memory Namespace:

Stores: aqe/test-data/generated
Reads: Database schemas

qe-api-contract-validator

Breaking change detection across API versions

Capabilities:

API contract validation
Breaking change detection
Backward compatibility verification
OpenAPI/Swagger validation
Consumer-driven contract testing

Usage:

Task("Validate API contracts", "Check for breaking changes", "qe-api-contract-validator")

Memory Namespace:

Stores: aqe/api/contract-validation
Reads: API specifications

qe-flaky-test-hunter

Statistical flakiness detection and auto-stabilization

Capabilities:

Flaky test detection with ML
Root cause analysis
Auto-stabilization strategies
Statistical significance testing
Retry policy optimization

Usage:

Task("Hunt flaky tests", "Detect and stabilize flaky tests", "qe-flaky-test-hunter")

Memory Namespace:

Stores: aqe/flaky-tests/detected
Reads: aqe/test-results/*, historical test data

Specialized Agents (2 agents)

qe-visual-tester

Visual regression with AI-powered comparison

Capabilities:

Screenshot-based visual testing
AI-powered image comparison
Layout shift detection
Accessibility visual validation
Cross-browser visual testing

Usage:

Task("Visual testing", "Run visual regression tests", "qe-visual-tester")

Memory Namespace:

Stores: aqe/visual/results
Reads: aqe/test-plan/*

qe-chaos-engineer

Resilience testing with controlled fault injection

Capabilities:

Controlled fault injection
Resilience testing
Blast radius management
Recovery validation
System stability verification

Usage:

Task("Chaos testing", "Test system resilience with controlled failures", "qe-chaos-engineer")

Memory Namespace:

Stores: aqe/chaos/results
Reads: aqe/test-plan/*

Intelligent accessibility testing with WCAG 2.2 compliance Contributed by @fndlalit

Capabilities:

WCAG 2.2 Level A, AA, AAA validation using axe-core
Context-aware ARIA label generation
Intelligent remediation with code examples
Keyboard navigation and screen reader testing
Color contrast optimization
AI video analysis (OpenAI, Anthropic, Ollama, moondream)
WebVTT caption generation
EN 301 549 EU compliance mapping
ARIA Authoring Practices Guide (APG) patterns

Usage:

Task("Accessibility scan", "Run WCAG 2.2 AA compliance check", "qe-a11y-ally")
Task("Generate captions", "Create WebVTT captions for video", "qe-a11y-ally")
Task("Remediation", "Fix accessibility issues with code suggestions", "qe-a11y-ally")

Memory Namespace:

Stores: aqe/accessibility/scan-results, aqe/accessibility/remediation
Reads: aqe/test-plan/*

MCP Tools (10 tools):

scan-comprehensive - Full WCAG 2.2 scan
remediation-code-generator - Auto-fix code generation
html-report-generator - Detailed HTML reports
video-vision-analyzer - AI video accessibility analysis
webvtt-generator - Caption file generation

n8n Workflow Testing Agents (15 agents)

Contributed by @fndlalit

The n8n workflow testing agents provide comprehensive testing capabilities for n8n automation workflows.

n8n-workflow-executor

Execute and validate n8n workflows programmatically

Capabilities:

Execute workflows via n8n REST API
Inject test data at workflow start or specific nodes
Validate node-to-node data flow
Assert expected outputs per node
Measure execution time and resource usage

Usage:

Task("Execute n8n workflow", "Test workflow with sample data", "n8n-workflow-executor")

n8n-chaos-tester

Fault injection and resilience testing for n8n workflows

Capabilities:

Controlled fault injection using N8nTestHarness
Network failure simulation
Node timeout testing
Error propagation validation
Recovery path verification

n8n-security-auditor

Security scanning for n8n workflows

Capabilities:

40+ secret patterns detection
Runtime credential leak detection
API key exposure scanning
Node permission validation
OWASP compliance checking

n8n-performance-tester

Load and stress testing for n8n workflows

Capabilities:

Concurrent execution testing
Timing metrics and percentiles
Bottleneck identification
Resource usage monitoring
SLA validation

n8n-compliance-validator

GDPR/HIPAA/SOC2/PCI-DSS compliance validation

Capabilities:

Data handling compliance checks
PII detection and tracing
Audit trail validation
Regulatory mapping
Compliance reporting

Additional n8n Agents

Agent	Purpose
n8n-bdd-scenario-tester	Cucumber-style BDD testing with real execution
n8n-expression-validator	Safe expression validation using pattern matching
n8n-integration-test	Real API connectivity testing via workflow execution
n8n-trigger-test	Webhook testing with correct n8n URL patterns
n8n-monitoring-validator	SLA compliance checking with runtime metrics
n8n-node-validator	Node configuration validation
n8n-unit-tester	Unit testing for individual workflow nodes
n8n-version-comparator	Version compatibility analysis
n8n-ci-orchestrator	CI/CD pipeline integration for n8n workflows
n8n-base-agent	Base agent with common n8n testing functionality

Setup Guide: n8n Real Instance Setup

MCP Tool Discovery System

The Agentic QE Fleet uses lazy-loaded MCP tools to reduce initial context by 87%.

Tool Discovery

// Discover available tool domains
mcp__agentic_qe__tools_discover()
// Returns: security, coverage, test-generation, test-execution, quality-gates,
//          fleet-management, memory, learning, patterns, reporting

// Load specific domain tools
mcp__agentic_qe__tools_load_domain({ domain: "security" })
mcp__agentic_qe__tools_load_domain({ domain: "coverage" })

Automatic Loading

Tools are auto-loaded based on keywords when agents work:

"security", "vulnerability" → loads security tools
"coverage", "gaps" → loads coverage tools
"generate", "create tests" → loads test-generation tools
"execute", "run tests" → loads test-execution tools

Benefits

87% context reduction (from 15,000 to 2,000 tokens initially)
Faster agent spawning with minimal overhead
On-demand loading only when tools are needed

Agent Coordination

All agents coordinate through the aqe/* memory namespace:

aqe/test-plan/* - Test planning and requirements
aqe/coverage/* - Coverage analysis and gaps
aqe/quality/* - Quality metrics and gates
aqe/performance/* - Performance test results
aqe/security/* - Security scan findings
aqe/swarm/coordination - Cross-agent coordination

Parallel Agent Execution

Execute multiple agents concurrently for maximum efficiency:

// Execute multiple agents in parallel
Task("Test Generation", "Generate unit tests", "qe-test-generator")
Task("Coverage Analysis", "Analyze current coverage", "qe-coverage-analyzer")
Task("Security Scan", "Run security checks", "qe-security-scanner")
Task("Performance Test", "Load test critical paths", "qe-performance-tester")

Related Documentation:

Skills Reference - All 46 QE skills
Usage Guide - Complete usage examples
AQE Hooks - Agent coordination details

Related Policies:

16 KiB Raw Permalink Blame History

Agentic QE Fleet - Agent Reference

Overview

Core Testing Agents (5 agents)

qe-test-generator

qe-test-executor

qe-coverage-analyzer

qe-quality-gate

qe-quality-analyzer

Performance & Security Agents (2 agents)

qe-performance-tester

qe-security-scanner

Strategic Planning Agents (3 agents)

qe-requirements-validator

qe-production-intelligence

qe-fleet-commander

Deployment Agent (1 agent)

qe-deployment-readiness

Code Understanding Agent (1 agent)

qe-code-intelligence

Advanced Testing Agents (4 agents)

qe-regression-risk-analyzer

qe-test-data-architect

qe-api-contract-validator

qe-flaky-test-hunter

Specialized Agents (2 agents)

qe-visual-tester

qe-chaos-engineer

qe-a11y-ally

n8n Workflow Testing Agents (15 agents)

n8n-workflow-executor

n8n-chaos-tester

n8n-security-auditor

n8n-performance-tester

n8n-compliance-validator

Additional n8n Agents

MCP Tool Discovery System

Tool Discovery

Automatic Loading

Benefits

Agent Coordination

Parallel Agent Execution

16 KiB

Raw Permalink Blame History