Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Review identity and access management using NIST SP 800-63B guidelines with MFA enforcement, password policy, and least privilege validation.
.claude/skills/williamzujkowski-iam-security-reviewer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 91% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 83% | 0% |
Trigger conditions:
Not for:
Time normalization:
NOW_ET using NIST/time.gov semantics (America/New_York, ISO-8601): 2025-10-26T01:33:55-04:00NOW_ET for all citation access datesInput validation:
identity_provider must be non-empty stringiam_scope must be one of: authentication, authorization, accounts, all]authenticator_level must be one of: AAL1, AAL2, AAL3] or omittedSource freshness:
Authentication:
Authorization:
Account Management:
If authenticator_level specified, validate:
Token budgets:
Ambiguity thresholds:
Abort conditions:
Severity classification:
Required fields:
json{ "identity_provider": "string", "iam_scope": "authentication|authorization|accounts|all", "authenticator_level": "AAL1|AAL2|AAL3 or null", "timestamp": "ISO-8601 with timezone", "findings": [ { "id": "unique identifier", "category": "authentication|authorization|account-management", "severity": "critical|high|medium|low", "cvss_score": 0.0, "title": "brief description", "description": "detailed finding", "nist_reference": "SP 800-63B section X.Y or SP 800-53 AC-2", "affected_accounts": ["account names or roles"], "remediation": "specific fix steps", "remediation_policy": "IAM policy JSON or config snippet" } ], "nist_aal_compliance": { "target_level": "AAL1|AAL2|AAL3", "current_level": "AAL1|AAL2|AAL3", "compliant": true, "gaps": ["list of gaps if not compliant"] }, "summary": { "total_findings": 0, "critical_count": 0, "high_count": 0, "overall_risk": "critical|high|medium|low" } }
Example: MFA Enforcement Check
yaml# Input identity_provider: "corporate-idp" iam_scope: "authentication" authenticator_level: "AAL2" # Output (abbreviated) { "identity_provider": "corporate-idp", "findings": [ { "id": "IAM-001", "category": "authentication", "severity": "critical", "cvss_score": 9.1, "title": "MFA not enforced for admin role", "nist_reference": "SP 800-63B Section 4.2 (AAL2)", "remediation": "Enable MFA requirement for all admin accounts" } ], "nist_aal_compliance": { "target_level": "AAL2", "current_level": "AAL1", "compliant": false, "gaps": ["MFA not enforced"] }, "summary": {"critical_count": 1, "overall_risk": "critical"} }
Token budgets:
Safety:
Auditability:
Determinism:
NIST Standards:
IAM Best Practices:
Privileged Access:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,638 | 12,732 | -13% | 1 | 1 | 0% | 3,311 | 4,988 | +51% | 0 | 0 | — |
case-02 | fail→pass | 16,648 | 14,125 | -15% | 1 | 1 | 0% | 3,306 | 4,897 | +48% | 0 | 0 | — |
case-03 | fail→pass | 12,799 | 10,593 | -17% | 1 | 1 | 0% | 2,821 | 4,461 | +58% | 0 | 0 | — |
case-04 | fail→fail | 19,024 | 25,552 | +34% | 1 | 1 | 0% | 4,006 | 7,369 | +84% | 0 | 0 | — |
case-05 | fail→fail | 7,472 | 16,837 | +125% | 1 | 1 | 0% | 1,362 | 5,758 | +323% | 0 | 0 | — |
case-06 | fail→fail | 10,235 | 12,013 | +17% | 1 | 1 | 0% | 2,020 | 4,522 | +124% | 0 | 0 | — |
case-07 | fail→fail | 17,119 | 20,637 | +21% | 1 | 1 | 0% | 3,348 | 6,397 | +91% | 0 | 0 | — |
case-08 | fail→pass | 10,135 | 9,858 | -3% | 1 | 1 | 0% | 2,288 | 4,374 | +91% | 0 | 0 | — |
case-09 | fail→pass | 9,805 | 8,115 | -17% | 1 | 1 | 0% | 2,229 | 4,085 | +83% | 0 | 0 | — |
case-10 | pass→pass | 8,860 | 10,907 | +23% | 1 | 1 | 0% | 2,049 | 4,147 | +102% | 0 | 0 | — |
case-11 | pass→pass | 6,485 | 7,565 | +17% | 1 | 1 | 0% | 1,406 | 3,824 | +172% | 0 | 0 | — |
case-12 | fail→pass | 8,574 | 10,217 | +19% | 1 | 1 | 0% | 1,755 | 4,367 | +149% | 0 | 0 | — |
case-13 | fail→pass | 9,439 | 7,967 | -16% | 1 | 1 | 0% | 1,876 | 3,817 | +103% | 0 | 0 | — |
case-14 | fail→pass | 13,465 | 14,369 | +7% | 1 | 1 | 0% | 1,695 | 3,854 | +127% | 0 | 0 | — |
case-15 | fail→pass | 13,031 | 5,985 | -54% | 1 | 1 | 0% | 2,543 | 3,350 | +32% | 0 | 0 | — |
case-16 | fail→pass | 11,429 | 7,495 | -34% | 1 | 1 | 0% | 2,126 | 3,871 | +82% | 0 | 0 | — |
case-17 | fail→pass | 5,662 | 6,254 | +10% | 1 | 1 | 0% | 1,233 | 3,364 | +173% | 0 | 0 | — |
case-18 | pass→pass | 9,718 | 10,847 | +12% | 1 | 1 | 0% | 2,221 | 4,745 | +114% | 0 | 0 | — |
case-19 | fail→pass | 7,095 | 7,815 | +10% | 1 | 1 | 0% | 1,309 | 3,603 | +175% | 0 | 0 | — |
case-20 | fail→pass | 10,038 | 11,630 | +16% | 1 | 1 | 0% | 1,960 | 4,381 | +124% | 0 | 0 | — |
case-21 | fail→fail | 16,559 | 11,256 | -32% | 1 | 1 | 0% | 3,671 | 4,335 | +18% | 0 | 0 | — |
case-22 | pass→pass | 15,091 | 12,910 | -14% | 1 | 1 | 0% | 1,191 | 3,524 | +196% | 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 +59 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.