Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Execute this skill empowers AI assistant to build reusable terraform modules based on user specifications. it leverages the terraform-module-builder plugin to generate production-ready, well-documented terraform module code, incorporating best practices for sec... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
.claude/skills/jeremylongshore-building-terraform-modules/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 30 |
| gemini-3.1-pro-preview | 100% | 1 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 41% | 0% |
Build reusable, production-ready Terraform modules with proper variable definitions, outputs, validation rules, documentation, and examples. Generate modules following HashiCorp's standard module structure for AWS, GCP, and Azure resources with security best practices, tagging conventions, and lifecycle management.
terraform version)terraform-docs installed for automated documentation generation (optional)main.tf, variables.tf, outputs.tf, versions.tf, locals.tfversions.tf with required_version and required_providers blocks pinned to stable versionsvariables.tf with descriptions, types, defaults, and validation rulesmain.tf using variables for all configurable values; use locals for computed valuesoutputs.tf for resource IDs, ARNs, endpoints, and connection stringsexamples/ directory with at least one complete usage example showing module invocationterraform-docs markdown table . > README.mdterraform init && terraform validate and test with terraform plan using the examplemain.tf, variables.tf, outputs.tf, versions.tf, locals.tfexamples/basic/main.tf with realistic variable valuesREADME.md with inputs, outputs, and usage documentation.terraform-docs.yml configuration for documentation generationterraform test (HCL-based)| Error | Cause | Solution | |-------|-------|---------| | variable validation failed | Input value does not meet validation rule | Check the validation block in variables.tf; adjust the value or the validation regex | | provider not found | Missing or wrong provider source in versions.tf | Add the provider to required_providers with correct source and version constraint | | circular dependency | Resources referencing each other in a loop | Refactor to break the cycle; use depends_on or separate into sub-modules | | output references undeclared resource | Typo in resource name or resource removed | Verify resource names in main.tf match output references exactly | | module source not found | Incorrect module path or registry reference | Verify the source path is relative (e.g., ./modules/vpc) or a valid registry address |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,808 | 20,654 | +16% | 1 | 1 | 0% | 4,083 | 5,712 | +40% | 0 | 0 | — |
case-02 | fail→pass | 23,603 | 26,493 | +12% | 1 | 1 | 0% | 5,151 | 7,042 | +37% | 0 | 0 | — |
case-03 | fail→pass | 16,289 | 19,754 | +21% | 1 | 1 | 0% | 3,285 | 5,399 | +64% | 0 | 0 | — |
case-04 | pass→pass | 19,209 | 23,306 | +21% | 1 | 1 | 0% | 4,005 | 5,887 | +47% | 0 | 0 | — |
case-05 | fail→pass | 15,870 | 19,619 | +24% | 1 | 1 | 0% | 3,395 | 5,336 | +57% | 0 | 0 | — |
case-06 | fail→pass | 9,046 | 3,287 | -64% | 1 | 1 | 0% | 965 | 1,356 | +41% | 0 | 0 | — |
case-07 | pass→pass | 4,991 | 4,935 | -1% | 1 | 1 | 0% | 959 | 1,634 | +70% | 0 | 0 | — |
case-08 | pass→pass | 10,254 | 6,837 | -33% | 1 | 1 | 0% | 1,854 | 2,006 | +8% | 0 | 0 | — |
case-09 | pass→pass | 7,636 | 4,058 | -47% | 1 | 1 | 0% | 1,379 | 1,642 | +19% | 0 | 0 | — |
case-10 | pass→pass | 8,422 | 7,308 | -13% | 1 | 1 | 0% | 1,470 | 2,238 | +52% | 0 | 0 | — |
case-11 | pass→pass | 9,058 | 5,463 | -40% | 1 | 1 | 0% | 1,626 | 1,751 | +8% | 0 | 0 | — |
case-12 | pass→pass | 4,694 | 7,084 | +51% | 1 | 1 | 0% | 920 | 2,142 | +133% | 0 | 0 | — |
case-13 | pass→pass | 7,717 | 6,980 | -10% | 1 | 1 | 0% | 1,329 | 1,951 | +47% | 0 | 0 | — |
case-14 | fail→fail | 10,133 | 4,454 | -56% | 1 | 1 | 0% | 1,696 | 1,699 | +0% | 0 | 0 | — |
case-15 | pass→pass | 10,702 | 10,412 | -3% | 1 | 1 | 0% | 1,912 | 2,734 | +43% | 0 | 0 | — |
case-16 | fail→pass | 10,583 | 14,234 | +34% | 1 | 1 | 0% | 1,889 | 3,248 | +72% | 0 | 0 | — |
case-17 | pass→pass | 13,588 | 12,281 | -10% | 1 | 1 | 0% | 2,430 | 3,097 | +27% | 0 | 0 | — |
case-18 | pass→pass | 3,634 | 3,408 | -6% | 1 | 1 | 0% | 621 | 1,389 | +124% | 0 | 0 | — |
case-19 | pass→pass | 7,516 | 8,446 | +12% | 1 | 1 | 0% | 1,390 | 2,425 | +74% | 0 | 0 | — |
case-20 | pass→pass | 6,856 | 7,485 | +9% | 1 | 1 | 0% | 1,261 | 2,167 | +72% | 0 | 0 | — |
case-21 | pass→pass | 4,136 | 3,503 | -15% | 1 | 1 | 0% | 694 | 1,459 | +110% | 0 | 0 | — |
case-22 | pass→pass | 3,789 | 3,067 | -19% | 1 | 1 | 0% | 633 | 1,402 | +121% | 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 +27 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.