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

—

Does it follow best practices?

Impact

99%

1.45x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

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

Strong, actionable reference material with excellent progressive disclosure and copy-ready code. The main gaps are token efficiency (inline deep-dives that could live in the reference files) and missing explicit validation feedback loops around the destructive apply step.

Suggestions

Trim or relocate the count-vs-for_each, locals dependency-management, and modern-features deep-dives into code-patterns.md so the main file stays a lean overview, removing redundant 'Why this matters' prose.

Add an explicit validation checkpoint before the 'Apply' CI/CD stage — e.g. 'Only proceed to apply when `terraform plan` is reviewed and clean; if errors, fix and re-plan' — to give a validate→fix→retry feedback loop for the destructive operation.

Drop the explanatory testing-pyramid ASCII art or move it to testing-frameworks.md, keeping the decision matrix which already conveys the same cost trade-off more concisely.

Dimension	Reasoning	Score
Conciseness	Largely actionable tables and code, but ~508 lines with explanatory prose ('Why this matters', the testing pyramid ASCII art) and deep-dive inline content (count-vs-for_each, locals dependency management, modern-features quick examples) that partly duplicates the reference guides and could be tightened or moved out.	2 / 3
Actionability	Provides fully executable HCL blocks (resource ordering, count/for_each, locals) and concrete commands ('trivy config .', 'checkov -d .', 'terraform init -upgrade') that are copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	Multi-step sequences exist (CI/CD Validate→Test→Plan→Apply, 'Before generating test code' steps, version update workflow), but the destructive 'apply' stage lacks an explicit validate→fix→retry feedback loop and checkpoints are implicit, capping it at 2 per the destructive-operations guideline.	2 / 3
Progressive Disclosure	A dedicated 'Detailed Guides' section plus in-context citations point to six real one-level-deep reference files (code-patterns, testing-frameworks, module-patterns, ci-cd-workflows, security-compliance, quick-reference), all confirmed present and well-signaled with section anchors.	3 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is exemplary: third-person/trigger form, an explicit 'Use when' clause, and a comprehensive list of concrete capabilities with natural trigger terms. It cleanly answers both what and when with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, ... implementing security scanning (trivy, checkov)' — matching the score-3 anchor that lists several specific actions.	3 / 3
Completeness	Opens with an explicit 'Use when working with Terraform or OpenTofu - ...' trigger and pairs it with a concrete what-list of actions, clearly answering both what the skill does and when to use it.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'Terraform or OpenTofu', 'modules', 'CI/CD pipelines', 'Terratest', 'trivy', 'checkov', 'state issues' — giving good coverage of common variations rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to Terraform/OpenTofu infrastructure-as-code with niche-specific triggers (state issues, trivy/checkov scanning, module patterns), making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 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	15 / 16 Passed

Repository: provectus/awos-recruitment
Commit: 4596913

Reviewed: 4 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.