terraform-style-guide
Generate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.
80
70%
Does it follow best practices?
Impact
97%
1.19xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./terraform/code-generation/skills/terraform-style-guide/SKILL.mdQuality
Discovery
75%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 is well-structured with a clear 'Use when...' clause and targets a distinct domain. Its main weakness is a lack of specific concrete actions beyond 'generate code' and limited trigger term coverage for common user phrasings around infrastructure-as-code workflows.
Suggestions
Add more specific concrete actions, e.g., 'create resource blocks, define variables and outputs, configure providers, structure modules'.
Expand trigger terms to include common variations like '.tf files', 'infrastructure as code', 'IaC', 'terraform modules', 'terraform providers'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Terraform HCL) and mentions style conventions and best practices, but doesn't list specific concrete actions like 'create modules, define variables, configure providers, write resource blocks'. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate Terraform HCL code following HashiCorp's style conventions and best practices) and 'when' (Use when writing, reviewing, or generating Terraform configurations) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes good terms like 'Terraform', 'HCL', and 'Terraform configurations', but misses common variations users might say such as '.tf files', 'infrastructure as code', 'IaC', 'terraform modules', 'terraform plan', or 'HashiCorp'. | 2 / 3 |
Distinctiveness Conflict Risk | Terraform HCL is a clear niche with distinct triggers; unlikely to conflict with other skills since it specifically targets Terraform configurations and HashiCorp conventions. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%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, actionable Terraform style guide with excellent concrete examples and good/bad comparisons that Claude can directly apply. Its main weaknesses are moderate verbosity (some sections cover knowledge Claude already has, and the version pinning block is duplicated) and a lack of explicit validation feedback loops in the workflow. The content would benefit from trimming redundant sections and linking out to supplementary files for detailed reference material.
Suggestions
Remove the duplicated version pinning code block and the version constraint operators table, as these are well-known Terraform concepts Claude already understands.
Add an explicit feedback loop to the code generation strategy: after generating code, run `terraform fmt` and `terraform validate`, fix any issues, and re-validate before considering the task complete.
Move detailed sections like Provider Configuration, Dynamic Resource Creation, and Version Control into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and code examples, but includes some content Claude already knows (version constraint operators, basic provider configuration patterns) and could be tightened. The version pinning section repeats the terraform block shown earlier. | 2 / 3 |
Actionability | Provides fully executable HCL code examples throughout, with concrete good/bad comparisons, specific file organization, and copy-paste ready patterns. Every section includes real, runnable code rather than pseudocode. | 3 / 3 |
Workflow Clarity | The code generation strategy provides a clear sequence, and the validation tools section mentions fmt/validate, but there's no explicit feedback loop (validate -> fix -> retry) for the generation workflow. The checklist is helpful but the connection between generation steps and validation checkpoints is implicit rather than explicit. | 2 / 3 |
Progressive Disclosure | References SECURITY.md appropriately for security details, but the main file is quite long (~200 lines of detailed content) with sections like version constraint operators and provider configuration that could be split into reference files. The structure is well-organized with clear headers but could benefit from more aggressive splitting. | 2 / 3 |
Total | 9 / 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
- hashicorp/agent-skills
- Commit
b129bb5
- 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.