CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

terraform-skill

Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code architecture decisions

89

1.45x
Quality

87%

Does it follow best practices?

Impact

99%

1.45x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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-engineered skill body: an overview that stays actionable via tables, matrices, and executable HCL/commands, while pushing depth into six real, correctly-anchored reference files. Main improvement room is trimming the small amount of repeated or already-known material and making failure-handling loops explicit in the CI/CD and test workflows.

DimensionReasoningScore

Conciseness

The body is dense with tables and executable snippets and largely avoids padding, but the singleton-'this' naming convention is explained twice, and basics like the roles of main.tf/variables.tf/outputs.tf are things Claude already knows.

4 / 5

Actionability

Guidance is copy-paste ready throughout: complete HCL blocks (NAT gateway with count, tags, depends_on, lifecycle; variable with validation and nullable), runnable commands ('trivy config .', 'terraform init -upgrade'), and decision matrices (testing approach, count vs for_each, version pinning by component) that cover the common cases.

5 / 5

Workflow Clarity

Multi-step workflows are clearly sequenced with validation checkpoints — CI/CD stages Validate → Test → Plan → Apply with production approvals, and the version-update workflow ending in 'Review and test: terraform plan' — though explicit failure/retry feedback loops (e.g., what to do when a test or plan fails) are not spelled out.

4 / 5

Progressive Disclosure

Verified against the actual bundle: all six referenced files exist in references/ and every cited anchor (code-patterns.md#block-ordering--structure, quick-reference.md#testing-approach-selection, quick-reference.md#terraform-vs-opentofu-comparison, code-patterns.md#count-vs-for_each-deep-dive, etc.) resolves. References are one level deep, consistently signaled with descriptive blurbs, and indexed in a 'Detailed Guides' section.

5 / 5

Total

18

/

20

Passed

Description

83%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.

A strong description: concrete, tool-anchored actions and an explicit, specific 'Use when' trigger covering a well-defined Terraform/OpenTofu IaC niche. The only weakness is that the 'what' is implied through the activity list rather than stated alongside a distinct capability statement.

DimensionReasoningScore

Specificity

Enumerates many concrete actions with specific tools — 'creating modules', 'writing tests (native test framework, Terratest)', 'implementing security scanning (trivy, checkov)', 'debugging state issues' — giving comprehensive, non-generic coverage.

5 / 5

Completeness

The 'Use when working with Terraform or OpenTofu...' clause explicitly and concretely answers 'when', and the enumerated activities convey 'what', but the description never states what the skill provides as a separate clause — the what is woven into the trigger list.

4 / 5

Trigger Term Quality

Strong natural keywords ('Terraform', 'OpenTofu', 'Terratest', 'CI/CD', 'state', 'trivy', 'checkov', 'infrastructure-as-code') that users would actually say, though common variations like 'HCL', '.tf', or 'backend' are absent.

4 / 5

Distinctiveness Conflict Risk

A clear infrastructure-as-code niche anchored by named tools (Terratest, trivy, checkov, native test framework) makes it highly distinguishable with minimal risk of triggering for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (517 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

agentscope-ai/QwenPaw

Path

plugins/bundle/cloudpaw/skills/terraform-skill/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.