Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Execute use when you need to work with compliance checking. This skill provides compliance monitoring and validation with comprehensive guidance and automation. Trigger with phrases like "check compliance", "validate policies", or "audit compliance".
.claude/skills/jeremylongshore-checking-infrastructure-compliance/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 288% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 72% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 51% | 0% |
Audit infrastructure configurations against compliance frameworks (CIS Benchmarks, SOC 2, HIPAA, PCI-DSS, GDPR) using policy-as-code tools like Open Policy Agent (OPA), Checkov, and tfsec. Generate compliance reports, identify violations, and produce remediation plans for Terraform, Kubernetes, and cloud provider configurations.
checkov, tfsec, opa, or kube-benchjq for parsing JSON policy outputscheckov -d . or tfsec . to detect misconfigurationsaws iam access-analyzer)| Error | Cause | Solution | |-------|-------|---------| | checkov: no Terraform files found | Scanner run from wrong directory | Specify path explicitly with -d path/to/terraform/ | | tfsec: failed to parse HCL | Syntax error in Terraform files | Run terraform validate first to fix HCL syntax before compliance scan | | False positive on compliance check | Rule too broad for the specific use case | Add inline skip comments (#checkov:skip=CKV_AWS_18:Reason) or create a .checkov.yml skip list | | OPA policy evaluation error | Rego syntax error or missing input data | Test policies with opa eval -d policy.rego -i input.json and validate Rego syntax | | Scan timeout on large codebase | Too many files or complex module references | Use --compact mode, scan directories individually, or increase timeout limits |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 6,551 | 5,982 | -9% | 1 | 1 | 0% | 1,093 | 1,885 | +72% | 0 | 0 | — |
case-05 | fail→pass | 12,636 | 8,408 | -33% | 1 | 1 | 0% | 2,220 | 2,323 | +5% | 0 | 0 | — |
case-03 | pass→pass | 10,934 | 7,559 | -31% | 1 | 1 | 0% | 1,342 | 2,031 | +51% | 0 | 0 | — |
case-01 | fail→fail | 16,967 | 14,820 | -13% | 1 | 1 | 0% | 3,229 | 3,877 | +20% | 0 | 0 | — |
case-02 | pass→pass | 9,143 | 6,357 | -30% | 1 | 1 | 0% | 1,638 | 1,981 | +21% | 0 | 0 | — |
case-06 | pass→pass | 15,449 | 13,485 | -13% | 1 | 1 | 0% | 2,477 | 3,129 | +26% | 0 | 0 | — |
case-07 | pass→pass | 10,208 | 13,319 | +30% | 1 | 1 | 0% | 2,094 | 3,702 | +77% | 0 | 0 | — |
case-08 | pass→pass | 9,639 | 7,632 | -21% | 1 | 1 | 0% | 1,578 | 2,125 | +35% | 0 | 0 | — |
case-09 | fail→pass | 14,743 | 14,574 | -1% | 1 | 1 | 0% | 2,659 | 3,665 | +38% | 0 | 0 | — |
case-10 | pass→pass | 16,454 | 17,907 | +9% | 1 | 1 | 0% | 3,438 | 4,643 | +35% | 0 | 0 | — |
case-11 | pass→pass | 15,346 | 13,518 | -12% | 1 | 1 | 0% | 3,304 | 3,550 | +7% | 0 | 0 | — |
case-12 | pass→pass | 12,255 | 11,737 | -4% | 1 | 1 | 0% | 2,131 | 2,927 | +37% | 0 | 0 | — |
case-13 | pass→pass | 15,277 | 16,355 | +7% | 1 | 1 | 0% | 2,916 | 4,167 | +43% | 0 | 0 | — |
case-14 | pass→pass | 13,386 | 12,063 | -10% | 1 | 1 | 0% | 2,367 | 2,925 | +24% | 0 | 0 | — |
case-15 | pass→pass | 6,141 | 7,511 | +22% | 1 | 1 | 0% | 1,149 | 2,192 | +91% | 0 | 0 | — |
case-16 | pass→pass | 10,913 | 7,969 | -27% | 1 | 1 | 0% | 1,799 | 2,186 | +22% | 0 | 0 | — |
case-17 | pass→pass | 5,045 | 6,383 | +27% | 1 | 1 | 0% | 670 | 2,016 | +201% | 0 | 0 | — |
case-18 | pass→pass | 7,382 | 6,879 | -7% | 1 | 1 | 0% | 1,059 | 2,032 | +92% | 0 | 0 | — |
case-19 | pass→pass | 9,498 | 11,411 | +20% | 1 | 1 | 0% | 1,822 | 3,043 | +67% | 0 | 0 | — |
case-20 | fail→pass | 6,244 | 15,825 | +153% | 1 | 1 | 0% | 406 | 1,577 | +288% | 0 | 0 | — |
case-21 | fail→fail | 11,367 | 17,349 | +53% | 1 | 1 | 0% | 1,216 | 3,225 | +165% | 0 | 0 | — |
case-22 | fail→fail | 13,207 | 9,758 | -26% | 1 | 1 | 0% | 1,973 | 2,300 | +17% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.