CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

terraform-conventions

Provides Terraform module, testing, CI/CD, security and AWS stack-layout guidance layered with Provectus conventions (exact version pinning, required tags, ephemeral secrets). Use when working with Terraform - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code architecture decisions. OpenTofu is largely compatible; verify feature floors. Does not cover application code, Kubernetes manifests, or CloudFormation/CDK.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill with excellent progressive disclosure (verified links, one level deep) and clearly sequenced workflows with real validation gates. Its one weakness is conciseness: several body sections restate standard Terraform knowledge and duplicate content already in the reference files.

Suggestions

Replace the inline count vs for_each decision table and GOOD/BAD examples with a two-line summary pointing to Code Patterns: Count vs For_Each (code-patterns.md#count-vs-for_each-deep-dive), which already contains the same patterns.

Compress the Naming Conventions, Variable Block Ordering, and Module Development sections to their non-obvious Provectus-specific rules only, and delegate the standard Terraform conventions (which Claude already knows) to module-patterns.md and quick-reference.md.

Trim the Modern Terraform Features table to the few versions that gate the skill's own guidance (testing 1.6+, mocking 1.7+, write-only args 1.11+) and reference code-patterns.md for the rest.

DimensionReasoningScore

Conciseness

The Provectus Conventions section is dense and earns every token, but the middle of the body restates standard Terraform knowledge Claude already has and duplicates the reference files: the count vs for_each decision table and GOOD/BAD examples appear again in code-patterns.md, block ordering in code-patterns.md, and naming/file-organization conventions in quick-reference.md's Common Patterns. Mostly efficient but with real tightening opportunities — not 4, since the duplication is more than minor; not 2, since there is no padded prose and the opinionated conventions genuinely add non-obvious rules.

3 / 5

Actionability

Fully executable throughout: exact constraint syntax ('required_version = "= X.Y.Z"'), concrete locals.tf and merge(local.required_tags, ...) HCL, copy-paste plan -out apply commands, named MCP tools with an HTTP-API fallback URL, and exact CLI commands ('trivy config .', 'checkov -d .'). Code examples are complete and runnable.

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints: the apply workflow is plan -out → 'terraform show plan.tfplan' → 'Wait for explicit approval' → apply the saved plan (a validation gate on a destructive operation), module version resolution has an MCP-first path with a defined fallback loop, cost review is 'Plan → cost review → build', and security scans must 'pass before a plan'. A pre-commit checklist is referenced, matching the top anchor's sequence-plus-validation-plus-checklist profile.

5 / 5

Progressive Disclosure

All seven in-body reference links resolve to real files in the bundle, the anchors used (e.g., aws-stack-layout.md#security-baseline, code-patterns.md#count-vs-for_each-deep-dive, quick-reference.md#troubleshooting-guide) match actual headings, and references are one level deep (they link only back to SKILL.md, never onward to further files). A closing References section summarizes each file, making navigation easy — matching the top anchor.

5 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete capabilities, an explicit multi-scenario 'Use when' trigger clause, named tools, and clear exclusions. The only minor gap is a couple of missing natural synonyms (HCL, .tf).

DimensionReasoningScore

Specificity

The description enumerates many concrete actions with tool specifics: 'creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code architecture decisions' — comprehensive coverage across the skill's scope, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers both questions: 'what' is stated first ('Provides Terraform module, testing, CI/CD, security and AWS stack-layout guidance layered with Provectus conventions (exact version pinning, required tags, ephemeral secrets)') and 'when' follows with a concrete 'Use when working with Terraform - ...' clause listing eight trigger scenarios, plus explicit exclusions — a clear match for the top anchor.

5 / 5

Trigger Term Quality

Good keyword coverage includes natural terms users would say: 'Terraform', 'Terratest', 'CI/CD pipelines', 'trivy', 'checkov', 'infrastructure-as-code', 'OpenTofu', 'state'. A few natural synonyms are missing (e.g., 'HCL', '.tf files'), which places it at 'good coverage; a few natural terms missing' rather than the comprehensive-synonym anchor at 5.

4 / 5

Distinctiveness Conflict Risk

The Terraform/IaC niche is distinct with tool-specific triggers (Terratest, trivy, checkov) and the closing boundary 'Does not cover application code, Kubernetes manifests, or CloudFormation/CDK' explicitly fences off adjacent skills, giving minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

provectus/awos-recruitment

Path

registry/skills/terraform-conventions/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.