Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expertise in evaluating Azure subscription findings from azure-inspector and mapping them to SCF controls.
.claude/skills/grcengclub-azure-inspector-expert/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 44% | 0% |
Use this skill when interpreting azure-inspector findings or explaining Azure control gaps.
Entra ID
| SCF | Check | Typical outcome | |---|---|---| | IAC-01.1 | MFA posture needs Graph/authentication-method verification | inconclusive when Azure CLI cannot prove coverage | | IAC-04 | Enabled Conditional Access policies exist | high fail if none found |
Storage accounts
| SCF | Check | Severity | |---|---|---| | CRY-05 | Blob/file encryption enabled | high if disabled | | DCH-01.2 | Blob public access disabled | critical if allowed | | CRY-06 | Minimum TLS version is TLS 1.2 or later | medium |
Key Vault
| SCF | Check | Severity | |---|---|---| | BCD-11 | Soft delete and purge protection | high/medium | | IAC-07.2 | Azure RBAC authorization preferred over access policies | medium |
Monitor + Defender for Cloud
| SCF | Check | Severity | |---|---|---| | MON-02 | Subscription Activity Log diagnostic export configured | high | | MON-01.2 | Defender for Cloud Standard plan enabled | high |
inconclusive as an evidence gap, not a pass. Entra MFA coverage often needs Microsoft Graph permissions beyond basic Azure Reader.not_applicable document as a scope signal, not a security defect. Example: no Key Vaults found.allowBlobPublicAccess=true is a high-risk configuration even when no container is currently public because it permits future public ACLs.az login is valid but the principal lacks subscription Reader.Policy.Read.All.allowBlobPublicAccess=false, enforce TLS 1.2+, and keep service encryption enabled.v0.1.0 does not inspect network security groups, Azure Policy assignments, VM disk encryption, AKS, SQL, Sentinel analytics, or Defender recommendations. Mark those as future connector coverage unless separate evidence is supplied.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | fail→pass | 9,569 | 4,873 | -49% | 1 | 1 | 0% | 1,398 | 1,416 | +1% | 0 | 0 | — |
case-01 | fail→pass | 18,914 | 23,679 | +25% | 1 | 1 | 0% | 2,735 | 2,694 | -1% | 0 | 0 | — |
case-02 | fail→pass | 21,314 | 15,715 | -26% | 1 | 1 | 0% | 3,515 | 3,220 | -8% | 0 | 0 | — |
case-03 | fail→pass | 12,097 | 12,105 | +0% | 1 | 1 | 0% | 2,040 | 2,812 | +38% | 0 | 0 | — |
case-04 | fail→pass | 10,914 | 10,399 | -5% | 1 | 1 | 0% | 1,577 | 2,269 | +44% | 0 | 0 | — |
case-05 | fail→pass | 7,338 | 7,966 | +9% | 1 | 1 | 0% | 1,073 | 1,968 | +83% | 0 | 0 | — |
case-06 | fail→pass | 7,848 | 5,397 | -31% | 1 | 1 | 0% | 1,254 | 1,499 | +20% | 0 | 0 | — |
case-07 | fail→pass | 10,167 | 5,311 | -48% | 1 | 1 | 0% | 1,675 | 1,586 | -5% | 0 | 0 | — |
case-08 | fail→pass | 16,851 | 6,023 | -64% | 1 | 1 | 0% | 818 | 1,639 | +100% | 0 | 0 | — |
case-09 | fail→pass | 12,060 | 3,321 | -72% | 1 | 1 | 0% | 2,065 | 1,134 | -45% | 0 | 0 | — |
case-10 | fail→pass | 10,616 | 3,189 | -70% | 1 | 1 | 0% | 1,533 | 1,171 | -24% | 0 | 0 | — |
case-11 | fail→pass | 10,434 | 2,500 | -76% | 1 | 1 | 0% | 1,707 | 1,127 | -34% | 0 | 0 | — |
case-12 | pass→pass | 11,091 | 6,905 | -38% | 1 | 1 | 0% | 1,920 | 1,828 | -5% | 0 | 0 | — |
case-14 | fail→pass | 11,776 | 2,959 | -75% | 1 | 1 | 0% | 1,758 | 1,110 | -37% | 0 | 0 | — |
case-15 | pass→pass | 7,145 | 4,825 | -32% | 1 | 1 | 0% | 1,191 | 1,377 | +16% | 0 | 0 | — |
case-16 | fail→fail | 16,449 | 7,634 | -54% | 1 | 1 | 0% | 2,489 | 1,897 | -24% | 0 | 0 | — |
case-17 | pass→pass | 16,947 | 10,971 | -35% | 1 | 1 | 0% | 2,628 | 2,424 | -8% | 0 | 0 | — |
case-18 | pass→pass | 14,667 | 8,742 | -40% | 1 | 1 | 0% | 2,418 | 2,148 | -11% | 0 | 0 | — |
case-19 | pass→pass | 13,652 | 10,425 | -24% | 1 | 1 | 0% | 2,469 | 2,388 | -3% | 0 | 0 | — |
case-20 | fail→pass | 14,902 | 4,805 | -68% | 1 | 1 | 0% | 2,034 | 1,412 | -31% | 0 | 0 | — |
case-21 | fail→pass | 14,886 | 5,599 | -62% | 1 | 1 | 0% | 2,218 | 1,533 | -31% | 0 | 0 | — |
case-22 | fail→pass | 11,313 | 6,366 | -44% | 1 | 1 | 0% | 1,588 | 1,585 | -0% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +73 percentage points is the difference between those two pass rates over the 21 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.