Skip to content
Testing
Skill

/cicd-pipeline-qe-orchestrator

Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing shift-left/shift-right testing.

From plugin
agentic-qe
436200 skills169 agents149 commands
Install
$ npx -y skills add proffesor-for-testing/agentic-qe --skill cicd-pipeline-qe-orchestrator --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/cicd-pipeline-qe-orchestrator

Context preview

The summary Claude sees to decide when to auto-load this skill.

Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing shift-left/shift-right testing.

SKILL.md

cicd-pipeline-qe-orchestrator.SKILL.md
name: cicd-pipeline-qe-orchestrator
description: "Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing shift-left/shift-right testing."
category: infrastructure
priority: critical
tokenEstimate: 1300
agents: [qe-fleet-commander, qe-test-generator, qe-test-executor, qe-coverage-analyzer, qe-quality-gate, qe-deployment-readiness]
implementation_status: optimized
optimization_version: 1.0
last_optimized: 2025-12-02
dependencies: [agentic-quality-engineering, shift-left-testing]
quick_reference_card: true
tags: [cicd, pipeline, orchestration, quality-gates, shift-left, shift-right, fleet]
trust_tier: 3
validation:
  schema_path: schemas/output.json
  validator_path: scripts/validate-config.json
  eval_path: evals/cicd-pipeline-qe-orchestrator.yaml

CI/CD Pipeline QE Orchestrator

<default_to_action> When orchestrating quality across CI/CD pipeline: 1. ANALYZE pipeline phases: commit, build, test, staging, production 2. SELECT optimal skills and agents for each phase 3. CONFIGURE quality gates with measurable thresholds 4. EXECUTE with parallel agent coordination 5. ADAPT strategy based on risk, complexity, and environment

**Quick Phase Selection:**

  • Commit (Shift-Left) → TDD, code review, unit tests
  • Build → Coverage analysis, mutation testing, flaky detection
  • Integration → API contracts, performance, security
  • Staging → Chaos testing, visual regression, accessibility
  • Production (Shift-Right) → Synthetic monitoring, RUM, compliance

**Critical Success Factors:**

  • Quality gates block bad deployments
  • Agents coordinate through memory namespaces
  • Adapt strategy based on risk level

</default_to_action>

Quick Reference Card

When to Use

  • Designing pipeline test strategies
  • Implementing quality gates
  • Coordinating multiple QE agents
  • Shift-left and shift-right testing

Phase-Agent Matrix

| Phase | Primary Agents | Key Skills | |-------|---------------|------------| | Commit | qe-test-generator, qe-requirements-validator | tdd-london-chicago, shift-left | | Build | qe-test-executor, qe-coverage-analyzer, qe-flaky-test-hunter | test-automation, mutation-testing | | Test | qe-api-contract-validator, qe-performance-tester, qe-security-scanner | api-testing, performance, security | | Staging | qe-chaos-engineer, qe-visual-tester, qe-deployment-readiness | chaos-engineering, accessibility | | Prod | qe-production-intelligence, qe-quality-analyzer | shift-right, compliance |

Quality Gate Thresholds

| Phase | Metric | Threshold | Blocking | |-------|--------|-----------|----------| | Commit | Unit coverage | > 80% | Yes | | Build | All tests pass | 100% | Yes | | Build | Mutation score | > 70% | No | | Test | API contracts | No breaking changes | Yes | | Test | p95 response | < 200ms | Yes | | Test | Security critical | 0 | Yes | | Staging | Deployment readiness | > 85% | Yes |

Fleet Configuration

  • **Topology**: hierarchical
  • **Max Agents**: 10 per phase
  • **Coordination**: aqe/* memory namespace

---

Pipeline Phases

Phase 1: Commit (Shift-Left)

**Goal:** Catch defects early, ensure testability

**Agents:**

  • `qe-test-generator` - Generate unit tests
  • `qe-requirements-validator` - BDD scenarios, INVEST criteria

**Skills:** `shift-left-testing`, `tdd-london-chicago`, `code-review-quality`

// Parallel execution
Task("Generate Tests", "Create unit tests for new methods", "qe-test-generator")
Task("Validate Requirements", "Check BDD scenarios", "qe-requirements-validator")

**Gates:** Unit coverage > 80%, Static analysis clean, Code review approved

---

Phase 2: Build

**Goal:** Validate integration, ensure coverage

**Agents:**

  • `qe-test-executor` - Run test suites
  • `qe-coverage-analyzer` - Coverage gaps (O(log n))
  • `qe-flaky-test-hunter` - Detect/stabilize flaky tests
  • `qe-regression-risk-analyzer` - Minimal regression suite

**Skills:** `test-automation-strategy`, `mutation-testing`, `regression-testing`

Task("Execute Tests", "Run full suite, store in aqe/test-results/*", "qe-test-executor")
Task("Coverage Analysis", "Identify gaps", "qe-coverage-analyzer")
Task("Flaky Detection", "Analyze test history", "qe-flaky-test-hunter")

**Gates:** All tests pass, Coverage > 90% critical paths, No new flaky tests

---

Phase 3: Integration/Test

**Goal:** Validate contracts, performance, security

**Agents:**

  • `qe-api-contract-validator` - Breaking changes detection
  • `qe-performance-tester` - Load test critical paths
  • `qe-security-scanner` - SAST/DAST scans
  • `qe-test-data-architect` - Realistic test data (10k+/sec)

**Skills:** `api-testing-patterns`, `performance-testing`, `security-testing`

// Parallel testing
Task("API Contracts", "Validate for breaking changes", "qe-api-contract-validator")
Task("Performance", "Load test 1000 users", "qe-performance-tester")
Task("Security", "SAST/DAST scan", "qe-security-scanner")

**Gates:** No breaking API changes, p95 < 200ms, No critical vulnerabilities

---

Phase 4: Staging

**Goal:** Validate production-like environment, resilience

**Agents:**

  • `qe-chaos-engineer` - Fault injection
  • `qe-visual-tester` - Visual regression
  • `qe-deployment-readiness` - Risk assessment

**Skills:** `chaos-engineering-resilience`, `accessibility-testing`, `visual-testing`

Task("Chaos Testing", "Controlled failure injection", "qe-chaos-engineer")
Task("Visual Testing", "Visual regression", "qe-visual-tester")
Task("Deployment Check", "Risk assessment", "qe-deployment-readiness")

**Gates:** Chaos tests pass, No visual regressions, Readiness > 85%

---

Phase 5: Production (Shift-Right)

**Goal:** Monitor real usage, validate compliance

**Agents:**

  • `qe-production-intelligence` - Incident → test scenarios
  • `qe-quality-analyzer` - Quality metrics and trends

**Skills:** `shift-right-testing`, `compliance-testing`

Task("Production
Read more
Ships withagentic-qe

AI-powered quality engineering agents that generate tests, find coverage gaps, detect flaky tests, and learn your codebase patterns — across 11 coding agent platforms.

Get the whole plugin

Other skills on agentic-qe.