agentleFS
proffesor-for-testingproffesor-for-testing/agentic-qe/.claude/skills/compliance-testing/SKILL.md

compliance-testing

Skill515 starsChanged 22 days agoMITView on GitHub

Regulatory compliance testing for GDPR, CCPA, HIPAA, SOC2, PCI-DSS and industry-specific regulations. Use when ensuring legal compliance, preparing for audits, or handling sensitive data.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When validating regulatory compliance:

    line 25
  2. Distinctive:

    TEST data rights (access, erasure, portability)

    line 28
  3. Distinctive:

    VERIFY encryption and access logging

    line 29
  4. Distinctive:

    Test continuously, not just before audits </default_to_action>

    line 42
  5. Distinctive:

    Audit trail everything: Every access to sensitive data, every consent, every deletion must be logged with timestamps and user IDs.

    line 229

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Compliance Testing

<default_to_action> When validating regulatory compliance:

  1. IDENTIFY applicable regulations (GDPR, HIPAA, PCI-DSS, etc.)
  2. MAP requirements to testable controls
  3. TEST data rights (access, erasure, portability)
  4. VERIFY encryption and access logging
  5. GENERATE audit-ready reports with evidence

Quick Compliance Checklist:

  • Data subject rights work (access, delete, export)
  • PII is encrypted at rest and in transit
  • Access to sensitive data is logged
  • Consent is tracked with timestamps
  • Payment card data not stored (only tokenized)

Critical Success Factors:

  • Non-compliance = €20M or 4% revenue (GDPR)
  • Audit trail everything
  • Test continuously, not just before audits </default_to_action>

Quick Reference Card

When to Use

  • Legal compliance requirements
  • Before security audits
  • Handling PII/PHI/PCI data
  • Entering new markets (EU, CA, healthcare)

Major Regulations

RegulationScopeKey Focus
GDPREU dataPrivacy rights, consent
CCPACaliforniaConsumer data rights
HIPAAHealthcarePHI protection
PCI-DSSPaymentsCard data security
SOC2SaaSSecurity controls

Penalties

RegulationMaximum Fine
GDPR€20M or 4% revenue
HIPAA$1.5M per violation
PCI-DSS$100k/month
CCPA$7,500 per violation

GDPR Compliance Testing

// Test data subject rights
test('user can request their data', async () => {
  const response = await api.post('/data-export', { userId });

  expect(response.status).toBe(200);
  expect(response.data.downloadUrl).toBeDefined();

  const data = await downloadFile(response.data.downloadUrl);
  expect(data).toHaveProperty('profile');
  expect(data).toHaveProperty('orders');
});

test('user can delete their account', async () => {
  await api.delete(`/users/${userId}`);

  // All personal data deleted
  expect(await db.users.findOne({ id: userId })).toBeNull();
  expect(await db.orders.find({ userId })).toHaveLength(0);

  // Audit log retained (legal requirement)
  expect(await db.auditLogs.find({ userId })).toBeDefined();
});

test('consent is tracked', async () => {
  await api.post('/consent', {
    userId, type: 'marketing', granted: true,
    timestamp: new Date(), ipAddress: '192.168.1.1'
  });

  const consent = await db.consents.findOne({ userId, type: 'marketing' });
  expect(consent.timestamp).toBeDefined();
  expect(consent.ipAddress).toBeDefined();
});

HIPAA Compliance Testing

// Test PHI security
test('PHI is encrypted at rest', async () => {
  const patient = await db.patients.create({
    ssn: '123-45-6789',
    medicalHistory: 'Diabetes'
  });

  const raw = await db.raw('SELECT * FROM patients WHERE id = ?', patient.id);
  expect(raw.ssn).not.toBe('123-45-6789'); // Should be encrypted
});

test('access to PHI is logged', async () => {
  await api.get('/patients/123', {
    headers: { 'User-Id': 'doctor456' }
  });

  const auditLog = await db.auditLogs.findOne({
    resourceType: 'patient',
    resourceId: '123',
    userId: 'doctor456'
  });

  expect(auditLog.action).toBe('read');
  expect(auditLog.timestamp).toBeDefined();
});

PCI-DSS Compliance Testing

// Test payment card handling
test('credit card numbers not stored', async () => {
  await api.post('/payment', {
    cardNumber: '4242424242424242',
    expiry: '12/25', cvv: '123'
  });

  const payment = await db.payments.findOne({ /* ... */ });
  expect(payment.cardNumber).toBeUndefined();
  expect(payment.last4).toBe('4242'); // Only last 4
  expect(payment.tokenId).toBeDefined(); // Token from gateway
});

test('CVV never stored', async () => {
  const payments = await db.raw('SELECT * FROM payments');
  const hasCVV = payments.some(p =>
    JSON.stringify(p).toLowerCase().includes('cvv')
  );
  expect(hasCVV).toBe(false);
});

Agent-Driven Compliance

// Comprehensive compliance validation
await Task("Compliance Validation", {
  regulations: ['GDPR', 'PCI-DSS'],
  scope: 'full-application',
  generateAuditReport: true
}, "qe-security-scanner");

// Returns:
// {
//   gdpr: { compliant: true, controls: 12, passed: 12 },
//   pciDss: { compliant: false, controls: 8, passed: 7 },
//   violations: [{ control: 'card-storage', severity: 'critical' }],
//   auditReport: 'compliance-audit-2025-12-02.pdf'
// }

Agent Coordination Hints

Memory Namespace

aqe/compliance-testing/
├── regulations/*        - Regulation requirements
├── controls/*           - Control test results
├── audit-reports/*      - Generated audit reports
└── violations/*         - Compliance violations

Fleet Coordination

const complianceFleet = await FleetManager.coordinate({
  strategy: 'compliance-validation',
  agents: [
    'qe-security-scanner',   // Scan for vulnerabilities
    'qe-test-executor',      // Execute compliance tests
    'qe-quality-gate'        // Block non-compliant releases
  ],
  topology: 'sequential'
});

Related Skills

  • security-testing - Security vulnerabilities
  • test-data-management - PII handling
  • accessibility-testing - Legal requirements

Remember

Compliance is mandatory, not optional. Fines are severe: GDPR up to €20M or 4% of revenue, HIPAA up to $1.5M per violation. But beyond fines, non-compliance damages reputation and user trust.

Audit trail everything. Every access to sensitive data, every consent, every deletion must be logged with timestamps and user IDs.

With Agents: Agents validate compliance requirements continuously, detect violations early, and generate audit-ready reports. Catch compliance issues in development, not in audits.

Gotchas

  • Agent checks GDPR consent flow but misses data retention — always verify deletion/anonymization actually works
  • Compliance reports with "100% compliant" are suspicious — no real system is fully compliant, verify each claim
  • Agent may test US regulations only — explicitly specify jurisdiction (EU, CA, etc.) for correct requirements
  • PII in test data is itself a compliance violation — never use production PII, use synthetic generators
  • Audit trail gaps are invisible until audit time — verify logging exists for EVERY data access, not just writes

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.