generating-infrastructure-as-code

Execute use when generating infrastructure as code configurations. Trigger with phrases like "create Terraform config", "generate CloudFormation template", "write Pulumi code", or "IaC for AWS/GCP/Azure". Produces production-ready code for Terraform, CloudFormation, Pulumi, ARM templates, and CDK across multiple cloud providers.

Quality

67%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/devops/infrastructure-as-code-generator/skills/generating-infrastructure-as-code/SKILL.md

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 its domain (infrastructure as code), lists specific tools and platforms it supports, and provides explicit trigger phrases for when it should be selected. The description is concise yet comprehensive, covering both the 'what' and 'when' effectively. The only minor issue is the awkward phrasing 'Execute use when' at the beginning, which seems like a grammatical error but doesn't significantly impact functionality.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and tools: generating Terraform configs, CloudFormation templates, Pulumi code, ARM templates, and CDK across multiple cloud providers. Also specifies 'production-ready code' as an output quality.	3 / 3
Completeness	Clearly answers both 'what' (produces production-ready IaC code for multiple tools and cloud providers) and 'when' (explicit trigger phrases like 'create Terraform config', 'generate CloudFormation template', etc.). Has explicit trigger guidance.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms: 'create Terraform config', 'generate CloudFormation template', 'write Pulumi code', 'IaC for AWS/GCP/Azure', plus tool names like Terraform, CloudFormation, Pulumi, ARM templates, CDK. These are terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche in infrastructure as code. The specific tool names (Terraform, CloudFormation, Pulumi, ARM, CDK) and cloud provider references make it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

35%

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

This skill provides a reasonable high-level framework for IaC generation but critically lacks executable code examples—its most significant weakness for a code-generation skill. The workflow is sequenced but missing validation feedback loops important for infrastructure operations. The content tries to cover too many tools and providers in a single file without concrete examples for any of them, resulting in abstract guidance that wouldn't meaningfully improve Claude's IaC output.

Suggestions

Add concrete, executable code examples for at least the primary IaC tools (e.g., a complete Terraform VPC module, a CloudFormation S3 template) showing the expected output format and structure.

Add explicit validation feedback loops: after generating code, validate → review errors → fix → re-validate before presenting to the user, especially given IaC can create costly or destructive infrastructure.

Split tool-specific guidance into separate referenced files (e.g., TERRAFORM.md, CLOUDFORMATION.md, PULUMI.md) with detailed patterns and examples for each, keeping SKILL.md as a concise overview.

Replace the 'Examples' section (which just lists prompts) with actual input→output examples showing a request and the corresponding generated IaC code.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary padding (e.g., the Overview section largely restates the description, the Prerequisites list includes things Claude would know to check, and the Examples section describes prompts rather than providing executable output). However, it's not egregiously verbose—most sections carry useful information.	2 / 3
Actionability	Despite covering a code-generation skill, the content contains zero executable code examples, no concrete Terraform/CloudFormation/Pulumi snippets, and no copy-paste-ready templates. The instructions are entirely abstract procedural descriptions ('Define input variables with types...') rather than showing actual HCL, YAML, or TypeScript code.	1 / 3
Workflow Clarity	The 10-step workflow provides a reasonable sequence, and step 10 mentions validation. However, there's no explicit feedback loop (validate → fix → re-validate), no checkpoint gates between steps, and the validation step is only at the end rather than integrated throughout the process. For IaC generation which can produce destructive infrastructure changes, this is insufficient.	2 / 3
Progressive Disclosure	The content is organized into clear sections (Instructions, Output, Error Handling, Examples, Resources), which is decent structure. However, for a skill covering 5 different IaC tools across 3 cloud providers, all content is inline in a single file with no references to separate detailed guides per tool or provider. The Resources section only links to external documentation rather than bundled reference files.	2 / 3
	Total	7 / 12 Passed

Validation

81%

Warnings & errors only

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

Validation — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 4801da6

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.