From agentic-qe-fleet
Prioritizes testing effort on highest-risk areas using probability-impact scoring, effort allocation (60% critical, 25% high), and dynamic reassessment for test strategy, resource allocation, and coverage decisions.
npx claudepluginhub proffesor-for-testing/agentic-qe --plugin agentic-qe-fleetThis skill is limited to using the following tools:
<default_to_action>
Generates a structured testing plan prioritized by risk, covering unit, integration, e2e tests, edge cases, and negative scenarios. Analyzes impact, probability, and visibility to focus on critical areas.
Produce a test strategy for a project or feature — risk map, test type decisions, coverage targets, CI config. Use when asked to "create test strategy", "what should we test", "testing plan", or "improve test coverage".
Provides QA strategies including risk-based testing, pyramid allocation, quality gates for pre-commit/merge/production, test categories, and planning templates for improving test coverage.
Share bugs, ideas, or general feedback.
<default_to_action> When planning tests or allocating testing resources:
| Score | Priority | Effort | Action |
|---|---|---|---|
| 20-25 | Critical | 60% | Comprehensive testing, multiple techniques |
| 12-19 | High | 25% | Thorough testing, automation priority |
| 6-11 | Medium | 10% | Standard testing, basic automation |
| 1-5 | Low | 5% | Smoke test, exploratory only |
await Task("Risk-Based Test Generation", {
critical: {
features: ['checkout', 'payment'],
depth: 'comprehensive',
techniques: ['unit', 'integration', 'e2e', 'performance', 'security']
},
high: {
features: ['auth', 'user-profile'],
depth: 'thorough',
techniques: ['unit', 'integration', 'e2e']
},
medium: {
features: ['search', 'notifications'],
depth: 'standard',
techniques: ['unit', 'integration']
},
low: {
features: ['admin-panel', 'settings'],
depth: 'smoke',
techniques: ['smoke-tests']
}
}, "qe-test-generator");
// Production incident increases risk
await Task("Update Risk Score", {
feature: 'search',
event: 'production-incident',
previousRisk: 9,
newProbability: 5, // Increased due to incident
newRisk: 15 // Now HIGH priority
}, "qe-regression-risk-analyzer");
// Agent predicts risk using historical data
const riskAnalysis = await Task("ML Risk Analysis", {
codeChanges: changedFiles,
historicalBugs: bugDatabase,
prediction: {
model: 'gradient-boosting',
factors: ['complexity', 'change-frequency', 'author-experience', 'file-age']
}
}, "qe-regression-risk-analyzer");
// Output: 95% accuracy risk prediction per file
aqe/risk-based/
├── risk-scores/* - Current risk assessments
├── historical-bugs/* - Bug patterns by area
├── production-data/* - Incident data for risk
└── coverage-map/* - Test depth by risk level
const riskFleet = await FleetManager.coordinate({
strategy: 'risk-based-testing',
agents: [
'qe-regression-risk-analyzer', // Risk scoring
'qe-test-generator', // Risk-appropriate tests
'qe-production-intelligence', // Production feedback
'qe-quality-gate' // Risk-based gates
],
topology: 'sequential'
});
# Risk-based test selection in pipeline
- name: Risk Analysis
run: aqe risk-analyze --changes ${{ github.event.pull_request.files }}
- name: Run Critical Tests
if: risk.critical > 0
run: npm run test:critical
- name: Run High Tests
if: risk.high > 0
run: npm run test:high
- name: Skip Low Risk
if: risk.low_only
run: npm run test:smoke
With Agents: Agents calculate risk using ML on historical data, select risk-appropriate tests, and adjust scores from production feedback. Use agents to maintain dynamic risk profiles at scale.