terraform-skill

Use when working with Terraform or OpenTofu - 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

1.45x

Quality

82%

Does it follow best practices?

Impact

99%

1.45x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

64%Scale 1-3

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

This is a comprehensive Terraform skill with strong actionability through concrete HCL examples and useful decision matrices. Its main weaknesses are moderate verbosity (some content Claude already knows, like basic file naming and elementary security advice) and workflow clarity that lacks explicit validation checkpoints and error recovery loops. The progressive disclosure structure is well-designed in theory but the main file is heavy and bundle files couldn't be verified.

Suggestions

Trim content Claude already knows: remove basic file naming conventions (main.tf, variables.tf), elementary security advice ('don't store secrets in variables'), and the testing pyramid ASCII art to reduce token usage.

Add explicit validation checkpoints and error recovery loops to the CI/CD workflow and version update workflow sections — e.g., 'If plan shows unexpected changes: review diff → fix → re-plan before proceeding to apply'.

Move the detailed Count vs For_Each, Locals for Dependency Management, and Modern Terraform Features sections to reference files, keeping only summary tables and links in the main SKILL.md to better embody progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is generally well-organized but includes some content Claude already knows (e.g., basic naming conventions, standard file naming like main.tf/variables.tf/outputs.tf, basic security advice like 'don't store secrets in variables'). The module hierarchy table and testing pyramid ASCII art add bulk. However, most content provides genuine value through specific patterns and decision matrices.	2 / 3
Actionability	The skill provides concrete, executable HCL code examples throughout — resource block ordering, count vs for_each patterns, variable validation blocks, version constraints, try()/optional() usage, and specific CLI commands (trivy, checkov, terraform init -upgrade). Examples are copy-paste ready and cover real-world scenarios like VPC dependency management.	3 / 3
Workflow Clarity	CI/CD workflow stages are listed (validate → test → plan → apply) but lack explicit validation checkpoints and error recovery steps. The testing decision matrix is helpful but the actual workflow for running tests, handling failures, and iterating is not clearly sequenced with feedback loops. The version update workflow is a simple 3-step list without validation gates.	2 / 3
Progressive Disclosure	The skill references multiple detailed guides (testing-frameworks.md, module-patterns.md, ci-cd-workflows.md, security-compliance.md, quick-reference.md, code-patterns.md) with clear navigation links and descriptions. However, no bundle files were provided, so we cannot verify these references exist. The main file itself is quite long (~400 lines) and includes substantial inline content that could arguably be pushed to reference files, blurring the overview/detail boundary.	2 / 3
	Total	9 / 12 Passed

Description

100%Scale 1-3

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

This is a strong skill description that clearly communicates both what the skill does and when to use it. It provides excellent trigger term coverage with specific tool names and natural practitioner language. The only minor note is that it leads with 'Use when' without a preceding declarative statement of what the skill is, but the enumerated actions within the 'Use when' clause effectively serve that purpose.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: creating modules, writing tests (with named frameworks), setting up CI/CD pipelines, reviewing configurations, debugging state issues, implementing security scanning (with named tools), and making architecture decisions.	3 / 3
Completeness	The description opens with an explicit 'Use when' clause that doubles as both the 'when' and 'what' — it clearly states when Claude should select this skill and enumerates the specific tasks it covers. Both dimensions are well addressed.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'Terraform', 'OpenTofu', 'modules', 'tests', 'Terratest', 'CI/CD', 'state issues', 'trivy', 'checkov', 'infrastructure-as-code'. These are terms practitioners naturally use when seeking help.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche targeting Terraform/OpenTofu specifically, naming specific tools (trivy, checkov, Terratest) and domain-specific concepts (state issues, native test framework). Unlikely to conflict with general coding or other IaC skills.	3 / 3
	Total	12 / 12 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (517 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: antonbabenko/terraform-skill
Path: SKILL.md
Commit: 5a68694

Reviewed: 16 days ago

Table of Contents

Discovery Implementation Validation

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.