CtrlK
BlogDocsLog inGet started
Tessl Logo

building-terraform-modules

Execute this skill empowers AI assistant to build reusable terraform modules based on user specifications. it leverages the terraform-module-builder plugin to generate production-ready, well-documented terraform module code, incorporating best practices for sec... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

36

Quality

33%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/devops/terraform-module-builder/skills/building-terraform-modules/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

This skill provides a well-structured overview of building Terraform modules with clear steps and useful error handling, but falls short on actionability due to the complete absence of concrete HCL code examples. The workflow is sequential but lacks explicit validation feedback loops, and the content includes some unnecessary padding (prerequisites Claude already knows, vague natural-language examples instead of code). Adding executable HCL snippets and validation checkpoints would significantly improve this skill.

Suggestions

Add at least one complete, executable HCL code example (e.g., a minimal variables.tf with a validation block, or a versions.tf template) to make the skill copy-paste actionable.

Add an explicit feedback loop at step 10: 'If terraform validate fails, review errors, fix the relevant file, and re-run validation before proceeding to terraform plan.'

Remove or condense the prerequisites section—items like 'Familiarity with HCL syntax' and 'Understanding of the infrastructure resources' are unnecessary for Claude.

Replace the natural-language examples with concrete input/output pairs showing a user request and the resulting module file structure or key HCL snippets.

DimensionReasoningScore

Conciseness

The prerequisites section includes unnecessary items like 'Understanding of the infrastructure resources' and 'Familiarity with HCL syntax' which Claude already knows. The examples section lists natural language prompts rather than code examples, adding tokens without much value. The overview also restates things that are implicit from the instructions.

2 / 3

Actionability

The instructions provide a clear sequence of steps with specific file names and commands (terraform init, terraform validate, terraform-docs), but lack any concrete code examples—no HCL snippets for variables.tf, main.tf, or versions.tf. For a skill about generating Terraform modules, at least one executable HCL template or snippet would significantly improve actionability.

2 / 3

Workflow Clarity

The 10-step workflow is clearly sequenced and step 10 includes validation (terraform validate and terraform plan), but there's no explicit feedback loop for error recovery—no 'if validation fails, fix and re-validate' checkpoint. For a module-building workflow that involves multiple interdependent files, missing validation feedback loops cap this at 2.

2 / 3

Progressive Disclosure

The content is reasonably organized with clear sections (Overview, Prerequisites, Instructions, Output, Error Handling, Examples, Resources), but everything is inline in a single file with no bundle files for detailed reference material. The error handling table and examples could be split into separate files, and the Resources section links externally but doesn't reference any local supporting documents.

2 / 3

Total

8

/

12

Passed

Description

17%

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 description suffers from a truncated capability statement, first/third person voice inconsistency ('empowers AI assistant'), and critically, a completely generic placeholder 'Use when' clause that provides no real trigger guidance. The Terraform module domain is identifiable but the description fails to provide actionable selection criteria for Claude to choose this skill appropriately.

Suggestions

Replace the generic 'Use when appropriate context detected' with specific triggers like 'Use when the user asks to create a Terraform module, scaffold infrastructure as code, or mentions HCL, .tf files, or reusable cloud infrastructure components.'

Complete the truncated description and list concrete actions such as 'generates module structure with variables.tf, outputs.tf, main.tf, includes input validation, security best practices, and README documentation.'

Remove 'Execute this skill empowers AI assistant' phrasing and use third person active voice like 'Builds reusable Terraform modules based on user specifications.'

DimensionReasoningScore

Specificity

It names the domain (Terraform modules) and mentions some actions ('build reusable terraform modules', 'generate production-ready, well-documented terraform module code'), but the description is truncated and padded with vague language like 'incorporating best practices for sec...' which is incomplete.

2 / 3

Completeness

While the 'what' is partially addressed (building Terraform modules), the 'when' clause is completely generic placeholder text ('Use when appropriate context detected') that provides zero actionable trigger guidance. This should cap completeness at 1 since the when clause is effectively missing.

1 / 3

Trigger Term Quality

The trigger guidance is entirely generic boilerplate ('Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.') with no actual natural keywords a user would say. Terms like 'terraform module', 'infrastructure as code', 'IaC', or 'HCL' are not explicitly listed as triggers.

1 / 3

Distinctiveness Conflict Risk

The mention of 'terraform modules' and 'terraform-module-builder plugin' provides some distinctiveness within the infrastructure-as-code domain, but the generic trigger language and truncated description weaken its ability to clearly distinguish itself from other IaC or cloud provisioning skills.

2 / 3

Total

6

/

12

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.