Install any skill in seconds. Free to start, no credit card required.
Get Started Free →borghei/infrastructure-compliance-auditor
Cross-framework infrastructure security audit across cloud, network, and CI/CD.
Passed 19 of 22 test cases with the skill, and 5 of 22 without it.
and 16 more in the full report
14 fixed5 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to run a dedicated security check specifically for our domain DNS configuration on target domain primary-domain.example. Write the exact terminal command to execute this check and output JSON results to dns_results.json.
| Checked | Without skill | With skill |
|---|---|---|
| Includes dns_security_checker.py in the command. | Missed | Passed |
| Includes the --domain primary-domain.example flag in the command. | Missed | Passed |
| Includes the --output dns_results.json flag in the command. | Missed | Passed |
The instructions your model reads when the skill loads.
Cross-cutting infrastructure security audit across ALL compliance frameworks. Replaces manual Vanta-style checks with deterministic, repeatable, evidence-generating infrastructure audits covering cloud, DNS, TLS, endpoints, access control, network, containers, CI/CD, secrets, logging, and physical security. Maps 250+ controls to 10 standards (SOC 2, ISO 27001, HIPAA, GDPR, PCI-DSS, NIS2, DORA, NIST CSF, FedRAMP, CCPA) with severity-weighted scoring.
Reach for this skill on: "infrastructure audit", "cloud security audit", "infrastructure compliance", "DNS security audit", "TLS audit", "endpoint security", "access control audit", "network security assessment", "infrastructure security", "cloud compliance", "Vanta alternative", "compliance automation", "security posture assessment", "hardware security keys", or "YubiKey compliance".
Before running the audit, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the audit report.
python scripts/infra_audit_runner.py --config infrastructure.json --output audit_report.json
python scripts/dns_security_checker.py --domain example.com --output dns_report.json
test cases passed, vs 5 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.