Write and run Terraform tests (.tftest.hcl). USE FOR: test files, run blocks, assertions, mock providers, plan-mode unit tests, apply-mode integration tests, test troubleshooting. WHEN: create test, write test, terraform test, .tftest.hcl, mock provider, test module, validate infrastructure, test assertion. DO NOT USE FOR: Bicep code, architecture decisions, deployment.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is an excellent skill description that hits all the key criteria. It provides specific capabilities, comprehensive trigger terms, explicit when/when-not guidance, and clear boundaries that distinguish it from related infrastructure skills. The structured USE FOR / WHEN / DO NOT USE FOR format makes it easy for Claude to quickly determine relevance.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and artifacts: 'test files, run blocks, assertions, mock providers, plan-mode unit tests, apply-mode integration tests, test troubleshooting.' These are precise, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (write and run Terraform tests with specific capabilities listed under USE FOR) and 'when' (explicit WHEN clause with trigger terms). Also includes a DO NOT USE FOR clause to further clarify boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'create test', 'write test', 'terraform test', '.tftest.hcl', 'mock provider', 'test module', 'validate infrastructure', 'test assertion'. These match how users naturally phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: Terraform test files specifically (.tftest.hcl). The DO NOT USE FOR clause explicitly excludes Bicep, architecture decisions, and deployment, reducing conflict risk with related infrastructure skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that excels at conciseness and progressive disclosure, using tables and terse descriptions effectively while pointing to detailed reference files. Its main weaknesses are the lack of an inline executable example (the canonical example is entirely deferred) and the absence of an explicit step-by-step workflow with validation checkpoints for writing and running tests. Adding a minimal but complete inline test example and a clearer workflow sequence would elevate this skill significantly.
Suggestions
Include a minimal but complete inline .tftest.hcl example (e.g., a simple plan-mode test with one run block and one assert) rather than deferring the canonical example entirely to a reference file.
Add an explicit step-by-step workflow for creating and running a test, such as: 1. Create .tftest.hcl file → 2. Write run blocks with assertions → 3. Run `terraform test` → 4. Interpret output → 5. Fix failures and re-run.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It uses tables for quick reference, avoids explaining basic Terraform concepts, and delegates detailed examples to reference files. Every section earns its place without unnecessary padding. | 3 / 3 |
Actionability | The skill provides concrete CLI commands and assert syntax, but the canonical example is deferred to a reference file rather than shown inline. The main file lacks a complete, copy-paste-ready test file example, which would significantly improve actionability. | 2 / 3 |
Workflow Clarity | The file structure and running tests sections provide some workflow guidance, but there's no explicit step-by-step workflow for creating a test (e.g., create file → write run blocks → validate → run → interpret results). There are no validation checkpoints or error recovery feedback loops for the test-writing process. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled, one-level-deep references to four specific reference files. The reference index table at the bottom provides easy navigation, and content is appropriately split between overview and detailed materials. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
ec7b8ff
Table of Contents
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.