azure-verified-modules

Azure Verified Modules (AVM) requirements and best practices for developing certified Azure Terraform modules. Use when creating or reviewing Azure modules that need AVM certification.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/terraform/skills/azure-verified-modules/SKILL.md

Quality

Content

57%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 thorough, well-organized AVM requirements reference with strong concrete HCL examples and a compliance checklist. Its main weaknesses are the lack of file-based progressive disclosure (everything inlined in one 615-line file), no explicit validate/retry workflow, and some non-essential padding such as the statistics summary.

Suggestions

Split the per-requirement detail into one-level-deep reference files (e.g. references/variables.md, references/outputs.md, references/code-style.md) and keep SKILL.md as an overview with clearly signaled links, to improve progressive disclosure and reduce token load.

Add an explicit develop/review workflow with validation checkpoints (e.g. 'run terraform fmt/validate, then tflint + checkov, fix and re-run until clean, then confirm against the Compliance Checklist') so the testing tools form a feedback loop rather than a bare list.

Remove the Summary Statistics section and the introductory sentence restating purpose, since Claude does not need requirement counts or a restated rationale to apply the rules.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient concrete rules with HCL examples, but the 615-line monolith includes unnecessary padding such as the Summary Statistics section ('Total Requirements: 37', 'MUST: 21') and an introductory sentence Claude does not need. It is not a 4 because that stats block and intro could be trimmed, and not a 2 because the bulk is concrete and unpadded rather than heavily padded.	3 / 5
Actionability	Provides many copy-paste-ready HCL examples, a provider version-constraint table, specific file names (deprecated_variables.tf, .terraform-docs.yml), and severity/requirement-ID tagging. It is not a 5 because several sections (Variable Definition Order, Naming Rules, Branch Protection) give only abstract rules without executable examples, and not a 3 because most guidance is concrete and executable.	4 / 5
Workflow Clarity	Numbered orderings exist for block-internal structure and a Compliance Checklist provides checkpoints, but there is no end-to-end develop/review workflow with an explicit validate-then-fix-then-retry feedback loop. It is not a 4 because validation checkpoints are not sequenced into a workflow, and not a 2 because the checklist and ordered lists supply some structure and checkpoints.	3 / 5
Progressive Disclosure	The body is well-structured with a Table of Contents and clear section headers, but all 615 lines are inlined in SKILL.md with no bundle/reference files to defer to (references/scripts/assets directories are absent). It is not a 4 because content that clearly belongs in separate files (e.g. the 37-requirement spec) is not split out, and not a 2 because the headers and TOC provide real navigable structure rather than minimal structure.	3 / 5
	Total	13 / 20 Passed

Description

78%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, well-structured description that clearly states what the skill covers and when to use it with a concrete 'Use when' trigger. Minor room to add a few more specific capabilities and synonyms/file extensions to lift specificity and trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure Verified Modules', 'Azure Terraform modules') and 1-2 actions ('developing', 'creating or reviewing'), but the actions are generic rather than a comprehensive list of concrete capabilities. It is not a 4 because it does not list several specific actions, and not a 2 because the domain and verbs are concrete, not minimal.	3 / 5
Completeness	Explicitly answers both 'what' ('AVM requirements and best practices for developing certified Azure Terraform modules') and 'when' ('Use when creating or reviewing Azure modules that need AVM certification') with a concrete 'Use when' trigger phrase. The 'Use when' clause is present, so no cap applies; it is not a 4 because the 'when' is specific rather than vague.	5 / 5
Trigger Term Quality	Good natural keyword coverage including 'Azure Verified Modules', 'AVM', 'Terraform modules', and 'creating or reviewing' — terms a user would actually say. It is not a 5 because it lacks synonyms and file extensions (e.g. '.tf', 'certified module'), and not a 3 because the core natural phrases users say are present.	4 / 5
Distinctiveness Conflict Risk	The 'AVM certification' niche is clearly distinct from generic skills, with triggers unlikely to fire for unrelated work. It is not a 5 because a generic Azure/Terraform-module skill could still overlap, and not a 3 because the AVM-certification scope is specific rather than broadly overlapping.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (616 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: hashicorp/agent-skills
Path: plugins/terraform/skills/azure-verified-modules/SKILL.md
Commit: 3268468

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.