refactor-module
Transform monolithic Terraform configurations into reusable, maintainable modules following HashiCorp's module design principles and community best practices.
Install with Tessl CLI
npx tessl i github:hashicorp/agent-skills --skill refactor-module80
Quality
41%
Does it follow best practices?
Impact
84%
1.05xAverage score across 10 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./terraform/module-generation/skills/refactor-module/SKILL.mdQuality
Discovery
40%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 establishes a clear niche around Terraform module creation and is unlikely to conflict with other skills. However, it lacks explicit trigger guidance ('Use when...') which is critical for skill selection, and could benefit from more specific concrete actions and natural user terminology.
Suggestions
Add a 'Use when...' clause with trigger terms like 'refactor Terraform', 'create Terraform module', 'split infrastructure code', 'modularize .tf files'
Include more specific actions such as 'extract resources into modules', 'define input variables and outputs', 'create module directory structure'
Add common user terminology variations like 'IaC', 'infrastructure as code', '.tf files', 'terraform refactoring'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Terraform) and the general action (transform monolithic configurations into modules), but lacks specific concrete actions like 'extract resources', 'create input variables', 'define outputs', or 'structure directories'. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing explicit trigger guidance caps this at 2, but the 'when' is entirely absent, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes 'Terraform', 'modules', and 'monolithic' which are relevant, but misses common user terms like 'refactor', 'split', 'modularize', '.tf files', 'infrastructure code', or 'IaC'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Terraform', 'monolithic configurations', 'reusable modules', and 'HashiCorp' creates a clear niche that is unlikely to conflict with other skills - this is distinctly about Terraform module refactoring. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent, actionable Terraform code examples with realistic before/after transformations and concrete migration commands. However, it severely violates token efficiency by including extensive inline content that should be split into reference files, explaining concepts Claude already understands, and lacking clear validation checkpoints in the workflow despite state migration being a destructive operation.
Suggestions
Extract the 'Before/After: Modular Structure' code examples, 'Module Documentation' template, and 'Refactoring Patterns' into separate reference files (e.g., EXAMPLES.md, DOCUMENTATION_TEMPLATE.md, PATTERNS.md) and link to them from a concise overview
Remove the 'Capability Statement', 'Prerequisites', and 'Input Parameters' table sections - these explain what Claude can infer from the examples
Add explicit validation gates in the workflow: 'Run terraform plan after each state mv command - proceed only if plan shows no changes' rather than just mentioning it in Common Pitfalls
Consolidate the state migration section to show only the modern 'moved' block approach with a brief note about pre-1.1 alternatives, rather than showing both in full detail
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines with significant redundancy. Explains basic concepts Claude knows (what modules are, what encapsulation means), includes lengthy markdown tables for parameters, and repeats similar patterns multiple times. The 'Capability Statement' and 'Prerequisites' sections add little value. | 1 / 3 |
Actionability | Provides fully executable, copy-paste ready HCL code throughout. The before/after transformation examples are complete and realistic, state migration commands are specific, and the testing section references concrete file structures and patterns. | 3 / 3 |
Workflow Clarity | Steps are listed (Analysis → Design → Transform → Migrate → Document → Test) but validation checkpoints are weak. The state migration section mentions 'test in non-production first' but lacks explicit verify-before-proceed gates. No clear feedback loop for catching refactoring errors before they impact state. | 2 / 3 |
Progressive Disclosure | Monolithic wall of content with everything inline. The 400+ line document includes full module documentation templates, complete before/after code examples, testing guidance, and patterns that should be in separate reference files. Only links to external skills at the end rather than organizing content hierarchically. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (539 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
license_field | 'license' field is missing | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 12 / 16 Passed | |
- 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.