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.

46

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

77%

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

The body is concise and unusually well-structured, with a clear 10-step workflow ending in an explicit terraform validate/plan checkpoint and a practical error-handling table. Its main weakness is a disconnect from its own bundle: the description advertises a terraform-module-builder plugin with scaffolding and validation scripts, but SKILL.md never points to or invokes those bundled files, so progressive disclosure and actionability suffer.

Suggestions

Reference and actually invoke the bundled scripts in the workflow, e.g. add a step 'Scaffold the module: python scripts/module_scaffolding.py' and 'Run automated checks: python scripts/validation_checks.py' so the advertised plugin capabilities are used rather than described.

Link the bundle's assets/validation_rules.json and scripts/ from a Resources or Bundle section so progressive disclosure is one level deep and clearly signaled (e.g. 'Validation rules: see assets/validation_rules.json').

Include at least one minimal executable HCL snippet (e.g. a variables.tf block with a validation rule) so the actionability guidance is copy-paste ready rather than described.

DimensionReasoningScore

Conciseness

The body is lean and well-organized: the 10-step Instructions, Output list, and Error Handling table each add only what Claude would not already know, with no padding or explanations of basic Terraform concepts.

3 / 3

Actionability

Steps reference concrete commands and files ('terraform init && terraform validate', 'terraform-docs markdown table . > README.md', the standard file set), but there is no actual executable HCL example in the body and the scaffold/validation scripts listed in the bundle are not invoked or shown, leaving guidance partly abstract.

2 / 3

Workflow Clarity

The Instructions form a clearly sequenced 10-step build process ending in an explicit validation checkpoint ('Validate the module with terraform init && terraform validate and test with terraform plan'), and the Error Handling table provides a fix-and-retry feedback loop, satisfying the validation-checkpoint requirement.

3 / 3

Progressive Disclosure

The body is well sectioned, but it never references the bundled assets/scripts (module_scaffolding.py, validation_checks.py, validation_rules.json, module_template/) that the description claims the skill leverages; the bundle files exist but are not navigated to from SKILL.md, so the split is not clearly signaled.

2 / 3

Total

10

/

12

Passed

Description

22%

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 reads as auto-generated boilerplate: it is grammatically broken ('Execute this skill empowers AI assistant...'), truncated mid-sentence ('best practices for sec...'), and uses generic template language ('Use when appropriate context detected') instead of concrete triggers. It communicates a niche (Terraform modules) but fails the rubric's explicit-trigger requirement and contains no real natural trigger phrases.

Suggestions

Rewrite in third person without the broken 'Execute this skill empowers AI assistant' framing and finish the truncated 'sec...' clause (e.g., 'Generates production-ready Terraform modules with variables, outputs, validation, and READMEs for AWS, GCP, and Azure').

Replace the generic 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose' with concrete natural triggers, e.g. 'Use when the user asks to build, scaffold, or generate a reusable Terraform module, or mentions module structure, variables.tf/outputs.tf, or terraform-docs.'

Remove buzzwords ('empowers', 'production-ready', 'best practices') in favor of the specific actions the skill performs, and ensure the description fully answers 'when should Claude use it'.

DimensionReasoningScore

Specificity

The phrase 'empowers AI assistant to build reusable terraform modules based on user specifications' names the domain but lists no concrete actions like 'generate', 'validate', or 'document'; it then devolves into 'incorporating best practices for sec...' which is cut off and vague.

1 / 3

Completeness

It states what the skill does at a high level, but the 'when' guidance is the generic boilerplate 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose' rather than explicit, concrete triggers, which the rubric says caps completeness at 2 and the truncated/templated nature pushes it lower.

1 / 3

Trigger Term Quality

'Trigger with relevant phrases based on skill purpose' is a meta-instruction, not real trigger terms, but 'terraform modules', 'terraform-module-builder', and 'production-ready' do cover some natural phrasing a user might say.

2 / 3

Distinctiveness Conflict Risk

'Terraform modules' is a reasonably specific niche unlikely to collide with unrelated skills, but the templated, generic trigger boilerplate weakens distinctiveness versus a sibling terraform skill.

2 / 3

Total

6

/

12

Passed

Validation

87%

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

Validation14 / 16 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

14

/

16

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.