Content
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a table of contents with no substantive content in the main body. It lacks any concrete, actionable guidance—no code examples, no specific commands, no decision frameworks, no checklists—despite covering a complex domain that demands them. The instructions are generic platitudes that could apply to any skill, and the content wastes tokens on role descriptions and capability listings that provide no operational value to Claude.
Suggestions
Replace the vague 'Instructions' bullets with a concrete workflow, e.g., a step-by-step architecture review process: 1) Identify workload requirements, 2) Select appropriate services using a decision matrix, 3) Draft IaC with specific Terraform/CDK patterns, 4) Validate with cost estimation commands, 5) Security review checklist.
Add at least one executable code example in the main body (e.g., a Terraform module skeleton for a common pattern like a VPC setup, or a specific AWS CLI command for cost analysis) to make the skill immediately actionable.
Remove the 'Purpose' and 'Capabilities' sections that merely describe what the skill is—Claude doesn't need to be told its own role. Use that space for a quick-reference decision tree or cheat sheet (e.g., 'Serverless vs. containers: use serverless when X, containers when Y').
Add brief 1-line descriptions to each sub-skill link so Claude can determine which to consult without opening all nine files (e.g., 'Cost Optimization & FinOps — Reserved instance analysis, right-sizing, tagging strategies, budget alerts').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with unnecessary meta-descriptions ('You are a cloud architect...', 'Purpose', 'Capabilities') that explain Claude's role rather than providing actionable instructions. The 'Use this skill when' and 'Do not use this skill when' sections are generic and add no real value. Much of the content describes what the skill is rather than what to do. | 1 / 3 |
Actionability | There are no concrete commands, code examples, executable steps, or specific guidance. Instructions like 'Clarify goals, constraints, and required inputs' and 'Apply relevant best practices' are entirely vague. No specific cloud commands, Terraform snippets, architecture decision frameworks, or checklists are provided in the main skill body. | 1 / 3 |
Workflow Clarity | There is no clear multi-step workflow, no sequencing of tasks, and no validation checkpoints. The four bullet points under 'Instructions' are generic platitudes ('Apply relevant best practices and validate outcomes') rather than a structured process. For a skill covering complex operations like infrastructure deployment and migration, this is critically insufficient. | 1 / 3 |
Progressive Disclosure | The skill does reference sub-skills and a resources file with one-level-deep links, which is a reasonable structure. However, no bundle files were provided to verify these references exist, the main content is too thin to serve as a useful overview, and the nine sub-skill links are just titles with no summary of what each contains, making navigation difficult. | 2 / 3 |
Total | 5 / 12 Passed |