Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Maps infrastructure code (Terraform, Kubernetes, CloudFormation) to compliance controls (ISO 27001, SOC 2, NIST 800-53). Analyzes IaC files and generates compliance evidence mappings showing which controls are satisfied.
.claude/skills/grcengclub-code-to-control-mapper/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 210% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -69% | 0% |
Maps infrastructure-as-code (IaC) files to specific compliance framework controls. Translates technical implementations into audit-ready compliance evidence.
Map a Terraform file to SOC 2:
bashnode plugins/grc-engineer/scripts/map-control.js main.tf SOC2
Map Kubernetes manifests to ISO 27001:
bashnode plugins/grc-engineer/scripts/map-control.js k8s/deployment.yaml ISO27001
Map CloudFormation template to NIST 800-53:
bashnode plugins/grc-engineer/scripts/map-control.js template.yaml NIST80053
Generates markdown reports with:
markdown# Compliance Mapping Report ## SOC 2 - CC6.1: Logical and Physical Access Controls **Status:** ✅ Satisfied **Evidence:** - `main.tf:45` - `aws_db_instance` with `storage_encrypted = true` - `main.tf:52` - IAM role with least privilege policy **Mapping:** Data at rest encryption via AWS KMS satisfies encryption requirements.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 6,494 | 15,254 | +135% | 1 | 1 | 0% | 1,000 | 3,098 | +210% | 0 | 0 | — |
case-01 | fail→pass | 9,594 | 23,598 | +146% | 1 | 1 | 0% | 1,469 | 2,411 | +64% | 0 | 0 | — |
case-03 | fail→fail | 10,437 | 18,047 | +73% | 1 | 1 | 0% | 1,651 | 3,559 | +116% | 0 | 0 | — |
case-04 | fail→pass | 9,873 | 2,512 | -75% | 1 | 1 | 0% | 1,480 | 903 | -39% | 0 | 0 | — |
case-05 | fail→pass | 18,892 | 7,394 | -61% | 1 | 1 | 0% | 3,202 | 1,715 | -46% | 0 | 0 | — |
case-06 | fail→pass | 17,536 | 3,153 | -82% | 1 | 1 | 0% | 3,113 | 973 | -69% | 0 | 0 | — |
case-07 | fail→pass | 8,976 | 1,905 | -79% | 1 | 1 | 0% | 1,314 | 789 | -40% | 0 | 0 | — |
case-08 | fail→pass | 11,052 | 2,414 | -78% | 1 | 1 | 0% | 1,771 | 930 | -47% | 0 | 0 | — |
case-09 | fail→pass | 9,593 | 2,238 | -77% | 1 | 1 | 0% | 1,430 | 829 | -42% | 0 | 0 | — |
case-10 | fail→pass | 7,675 | 2,532 | -67% | 1 | 1 | 0% | 1,193 | 942 | -21% | 0 | 0 | — |
case-11 | fail→pass | 13,731 | 1,857 | -86% | 1 | 1 | 0% | 1,987 | 777 | -61% | 0 | 0 | — |
case-12 | pass→pass | 10,001 | 3,050 | -70% | 1 | 1 | 0% | 1,503 | 949 | -37% | 0 | 0 | — |
case-13 | pass→pass | 8,974 | 5,092 | -43% | 1 | 1 | 0% | 1,335 | 1,288 | -4% | 0 | 0 | — |
case-14 | fail→pass | 11,068 | 1,346 | -88% | 1 | 1 | 0% | 1,554 | 708 | -54% | 0 | 0 | — |
case-15 | fail→pass | 19,029 | 11,565 | -39% | 1 | 1 | 0% | 3,045 | 2,410 | -21% | 0 | 0 | — |
case-16 | fail→pass | 8,860 | 1,840 | -79% | 1 | 1 | 0% | 1,387 | 807 | -42% | 0 | 0 | — |
case-17 | fail→pass | 9,724 | 2,809 | -71% | 1 | 1 | 0% | 1,616 | 982 | -39% | 0 | 0 | — |
case-18 | fail→pass | 13,100 | 1,827 | -86% | 1 | 1 | 0% | 1,917 | 813 | -58% | 0 | 0 | — |
case-19 | fail→pass | 10,853 | 2,022 | -81% | 1 | 1 | 0% | 1,685 | 801 | -52% | 0 | 0 | — |
case-20 | pass→pass | 11,126 | 12,293 | +10% | 1 | 1 | 0% | 1,795 | 2,424 | +35% | 0 | 0 | — |
case-21 | fail→pass | 12,385 | 10,001 | -19% | 1 | 1 | 0% | 2,186 | 2,084 | -5% | 0 | 0 | — |
case-22 | fail→pass | 8,862 | 8,414 | -5% | 1 | 1 | 0% | 725 | 1,175 | +62% | 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 +82 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.