Content
36%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a high-level framework for cloud cost optimization but lacks the concrete, actionable guidance needed to be effective. The instructions read more like a checklist of goals than executable steps, with no specific commands, tool references, code examples, or validation checkpoints. The structure is reasonable but the content is too abstract to drive reliable execution.
Suggestions
Add concrete, executable examples for each instruction step—e.g., specific AWS CLI commands like `aws ce get-cost-and-usage`, Azure Cost Management queries, or GCP billing export queries to collect cost data.
Integrate explicit validation checkpoints into the workflow, such as 'Verify staging performance metrics match baseline before applying changes to production' with specific metrics to check.
Provide at least one complete worked example showing the full flow from cost data collection through recommendation to implementation, with specific numbers and resource types.
Either provide the referenced `resources/implementation-playbook.md` bundle file or inline the most critical tooling and analysis steps directly in the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill repeats the description in the body ('You are a cloud cost optimization expert...'), includes a 'Context' section that restates what Claude can infer, and has 'Use this skill when' / 'Do not use this skill when' sections that add moderate padding. The instructions themselves are reasonably lean but the surrounding material could be tightened. | 3 / 5 |
Actionability | The instructions are high-level bullet points ('Collect cost data', 'Identify waste') with no concrete commands, code snippets, CLI examples, or specific tool invocations. There are no executable steps—only abstract direction that Claude would need to interpret and flesh out entirely on its own. | 2 / 5 |
Workflow Clarity | There is a rough sequence (collect → identify → propose → implement), but steps are vaguely defined with no validation checkpoints, no explicit feedback loops, and no concrete verification steps. The safety section mentions staging validation but doesn't integrate it into the workflow sequence. For operations involving resource deletion/resizing, this lack of validation should cap the score. | 2 / 5 |
Progressive Disclosure | The skill references `resources/implementation-playbook.md` for detailed workflows, which is a reasonable one-level-deep reference. However, no bundle files are provided, so the reference is unverifiable. The main file's structure is adequate with clear sections, but the inline content is thin while the referenced file doesn't exist. | 3 / 5 |
Total | 10 / 20 Passed |