CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

terraform-generator

Generate Terraform modules, configure providers, define variables and outputs, set up remote state backends, and write production-ready HCL (.tf files) following current standards. Use when creating new Terraform resources, building Terraform projects, writing infrastructure as code (IaC), scaffolding AWS/Azure/GCP cloud infrastructure, working with terraform plan/apply workflows, or structuring multi-environment configurations.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

62%Weight 40%Scale 1-5

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

A well-structured, highly actionable generation workflow with an exemplary validate-and-fix loop, but the body is noticeably verbose: rules are stated two to three times each, basic HCL examples duplicate the reference files, and three of its cited bundle paths (modern_features.md, aws-web-app/, multi-env/) do not exist.

Suggestions

State each rule once: merge the 'Lifecycle Rules on Critical Resources', 'S3 Lifecycle Best Practices', and 'Data Sources for Dynamic Values' sections into their corresponding Anti-Patterns entries (or vice versa), and delete the 'Notes' section that repeats earlier guidance verbatim.

Remove the basic HCL syntax examples from Step 3 (variable validation blocks, outputs, dynamic blocks, locals) — Claude already knows standard Terraform syntax and references/terraform_best_practices.md already covers these — keeping only the skill's opinionated rules (pinning policy, prevent_destroy list, CKV checks).

Fix the dangling bundle references: either create references/modern_features.md (cited three times, including a callout promising a 'full feature matrix') and the assets/aws-web-app/ and assets/multi-env/ templates, or remove them from the Step 2.5 table, the References section, and the assets list.

DimensionReasoningScore

Conciseness

The body (~600 lines) contains several padded/redundant sections: the prevent_destroy rule is stated three times ("Lifecycle Rules When Appropriate", "Lifecycle Rules on Critical Resources", "NEVER leave critical stateful resources without prevent_destroy"), the S3 abort-incomplete-multipart-upload rule twice, the AMI data-source rule twice, and an entirely redundant "Notes" section that repeats earlier guidance ("Always run devops-skills:terraform-validator after generation", "Web search is essential for custom providers/modules"). Step 3 also inlines ~80 lines of basic HCL syntax Claude already knows (variable declarations with validation blocks, outputs, dynamic blocks, locals) that duplicates references/terraform_best_practices.md. This matches anchor 2 ('several unnecessary explanations or padded sections') better than anchor 3, since the waste spans multiple sections rather than being isolated tightenings.

2 / 5

Actionability

Guidance is highly executable: copy-paste HCL snippets, exact bash commands ("terraform fmt -check", "terraform init", "terraform validate"), concrete WebSearch query formats ("datadog terraform provider v3.30 monitor resource documentation"), pinned provider versions, and Checkov failure IDs paired with fixes ("CKV_AWS_24 | SSH open to 0.0.0.0/0 | Restrict to specific CIDR"). However, Step 2.5's table and the Version Awareness callout instruct reading "references/modern_features.md", which does not exist in the bundle — an instruction that fails when followed — keeping this below anchor 5's 'fully executable' bar.

4 / 5

Workflow Clarity

The five-step workflow is explicitly ordered ("Work through these steps in order. Do not skip any step.") with a dedicated validation step, an explicit fix-and-revalidate feedback loop ("Do NOT proceed to Step 5 until all checks pass"), a common-failures table with fixes, and a manual fallback command path. This matches anchor 5: clear sequence, explicit validation, feedback loops for error recovery.

5 / 5

Progressive Disclosure

Reference signaling is genuinely good — a "When to consult each reference" table and one-level-deep paths — but the actual bundle undermines it: "references/modern_features.md" is cited three times (Step 2.5 table, Version Awareness callout, References section) yet is absent from references/, and the assets section lists "aws-web-app/" and "multi-env/" which do not exist in assets/. Additionally, Step 3 inlines basic best-practice examples that duplicate the 768-line references/terraform_best_practices.md. This lands between anchor 3 ('content that should be separate is inline', broken navigation) and anchor 4 ('minor organization gaps') — the missing cited files are more than a minor gap since following the navigation fails, so anchor 3 is the better fit.

3 / 5

Total

14

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An excellent description: concrete capabilities, explicit use-when triggers with synonyms and file extensions, and a clear niche. The only weakness is the 'terraform plan/apply workflows' trigger, which slightly over-claims relative to the body's scope (generation only, never apply).

DimensionReasoningScore

Specificity

The description lists five distinct concrete actions — "Generate Terraform modules, configure providers, define variables and outputs, set up remote state backends, and write production-ready HCL (.tf files)" — comprehensively covering the skill's domain, matching anchor 5 ('multiple specific concrete actions; comprehensive coverage'). It is not anchor 4 because there are no minor coverage gaps: generation, providers, variables/outputs, state backends, and file format are all named.

5 / 5

Completeness

It explicitly answers both questions: the first sentence gives the 'what' (generate modules, configure providers, define variables/outputs, set up remote state backends, write production-ready HCL) and the second gives an explicit 'when' ("Use when creating new Terraform resources, building Terraform projects, writing infrastructure as code (IaC), scaffolding AWS/Azure/GCP...") with concrete trigger phrases, exactly matching anchor 5.

5 / 5

Trigger Term Quality

Natural trigger coverage includes synonyms and file extensions: "Terraform", "infrastructure as code (IaC)", ".tf files", "scaffolding AWS/Azure/GCP cloud infrastructure", "creating new Terraform resources", "building Terraform projects", "terraform plan/apply workflows", "multi-environment configurations". This matches anchor 5 ('comprehensive coverage of natural terms including synonyms and file extensions'); the phrasing mirrors what a user would actually say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

The Terraform/HCL generation niche is clear with distinct triggers, but "working with terraform plan/apply workflows" invites requests the body explicitly excludes ("Running terraform apply or changing live infrastructure: this skill only writes configuration") and creates minor overlap with the referenced terraform-validator skill — fitting anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than anchor 5's minimal conflict risk.

4 / 5

Total

19

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (599 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

pantheon-org/tekhne

Path

skills/infrastructure/terraform/generator/SKILL.md

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.