terraform-engineer
Use when implementing infrastructure as code with Terraform across AWS, Azure, or GCP. Invoke for module development (create reusable modules, manage module versioning), state management (migrate backends, import existing resources, resolve state conflicts), provider configuration, multi-environment workflows, and infrastructure testing.
72
88%
Does it follow best practices?
Impact
—
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 a strong skill description that clearly identifies the tool (Terraform), the domain (infrastructure as code), and lists specific concrete actions organized by category. It includes explicit trigger guidance with 'Use when' and 'Invoke for' clauses, and uses natural keywords that users would employ when requesting Terraform help. The description is well-structured, concise, and distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: module development, module versioning, state management (with sub-actions like migrate backends, import existing resources, resolve state conflicts), provider configuration, multi-environment workflows, and infrastructure testing. | 3 / 3 |
Completeness | Clearly answers both 'what' (module development, state management, provider configuration, multi-environment workflows, infrastructure testing) and 'when' with an explicit 'Use when implementing infrastructure as code with Terraform' and 'Invoke for...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Terraform', 'infrastructure as code', 'AWS', 'Azure', 'GCP', 'module', 'state management', 'import existing resources', 'backend', 'multi-environment'. These cover common variations of how users would describe Terraform-related tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Terraform specifically, with distinct triggers like 'Terraform', 'state management', 'module versioning', and cloud provider names in the IaC context. Unlikely to conflict with general cloud or coding skills due to the Terraform-specific terminology. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-structured Terraform skill with strong actionability through executable code examples and clear workflow sequencing with validation checkpoints and error recovery loops. The main weaknesses are minor verbosity (persona description, some obvious constraints) and the fact that the referenced bundle files don't exist, undermining the progressive disclosure strategy. Overall it provides practical, concrete guidance that would effectively direct Claude's Terraform work.
Suggestions
Remove the opening persona sentence and trim the constraints list to only non-obvious items (e.g., Claude already knows not to store secrets in plain text)
Provide the referenced files (references/module-patterns.md, etc.) or remove the reference table if they won't be created, as broken references reduce trust in the skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary framing (e.g., the opening sentence describing the persona's expertise is redundant). The constraints section restates things Claude already knows (e.g., don't store secrets in plain text). However, the code examples and workflow are reasonably tight. | 2 / 3 |
Actionability | Provides fully executable HCL code examples for module structure, remote backend configuration, and provider version pinning. Commands are specific (terraform fmt, terraform validate, tflint, terraform plan -out=tfplan). The error recovery section gives concrete remediation steps with specific commands. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced with explicit validation checkpoints at step 5 and a feedback loop (fix → re-validate → repeat until clean). The error recovery section provides specific remediation paths for different failure types, and explicitly states to return to step 5 after any fix before re-planning. | 3 / 3 |
Progressive Disclosure | The reference table with 'Load When' guidance is well-structured and clearly signaled. However, no bundle files were provided, so the referenced files (references/module-patterns.md, etc.) don't actually exist, making the progressive disclosure aspirational rather than functional. The inline content is reasonably sized but the code examples section could potentially be offloaded. | 2 / 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.
- Repository
- jeffallan/claude-skills
- Commit
e8be415
- 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.