terraform-policy

Write, test, or convert Terraform Policy files (.policy.hcl, .policytest.hcl, Sentinel→tfpolicy). Triggers: policy.hcl, policytest, convert sentinel, tfpolicy, write a policy.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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-organized routing skill that is token-lean and routes cleanly to verified sub-skill references with version-aware branching. The main gaps are an unreferenced bundle file (verified-syntax.md) and validation steps that are mentioned but not wired as explicit feedback-loop checkpoints.

Suggestions

Link references/verified-syntax.md from the body (e.g., in the Routing table or a Syntax reference section) so all bundle files are navigable.

Add an explicit validation checkpoint to the authoring flow, e.g. "After writing .policy.hcl, run tfpolicy validate and fix errors before proceeding", to strengthen the feedback loop.

Surface a one-line test-loop reminder (tfpolicy test against .policytest.hcl) in the routing guidance so verification is sequenced rather than implied.

Dimension	Reasoning	Score
Conciseness	The body is lean: USE FOR / DO NOT USE FOR lists, a routing table, and a concise version-branching block with no padding or explanation of concepts Claude already knows, matching the lean-and-efficient anchor.	5 / 5
Actionability	Concrete version-conditional rules ("include a top-level policy { required_providers { ... } } block") and executable bash install commands are present, but the bulk of authoring detail is delegated to references, leaving minor gaps in inline executable guidance.	4 / 5
Workflow Clarity	A clear sequence exists (check CLI version → branch on 0.1.x vs 0.2.0+ → route to sub-skill) with most checkpoints present, though validation via tfpolicy validate/policytest is referenced rather than sequenced as an explicit feedback loop.	4 / 5
Progressive Disclosure	The overview points to real one-level-deep references (tfpolicy-author.md, tfpolicy-test.md) with a routing table, but references/verified-syntax.md exists in the bundle without being linked from the body, a minor navigation gap.	4 / 5
	Total	17 / 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, third-person description that names concrete actions, file extensions, and explicit trigger phrases, cleanly answering both what and when. Minor synonym coverage gaps in the trigger list keep trigger quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	"Write, test, or convert Terraform Policy files (.policy.hcl, .policytest.hcl, Sentinel→tfpolicy)" lists multiple concrete actions (write, test, convert) tied to specific file formats, matching the comprehensive-coverage anchor.	5 / 5
Completeness	It states the "what" (write/test/convert Terraform Policy files) and an explicit "when" via the concrete Triggers clause, matching the anchor that clearly answers both with trigger phrases.	5 / 5
Trigger Term Quality	The explicit "Triggers: policy.hcl, policytest, convert sentinel, tfpolicy, write a policy" covers file extensions and natural phrases, but a few common synonyms (e.g. "Sentinel migration", "policy test") are absent, sitting just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply scoped to Terraform Policy file types and Sentinel conversion, with distinct triggers that minimize overlap with sibling skills like terraform-test or terraform-style-guide.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: hashicorp/agent-skills
Path: plugins/terraform/skills/terraform-policy/SKILL.md
Commit: 3268468

Reviewed: 5 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.