optimizing-cloud-costs
Execute use when you need to work with cloud cost optimization. This skill provides cost analysis and optimization with comprehensive guidance and automation. Trigger with phrases like "optimize costs", "analyze spending", or "reduce costs".
48
37%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/devops/cloud-cost-optimizer/skills/optimizing-cloud-costs/SKILL.mdQuality
Discovery
40%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 description is weak overall, relying on vague buzzwords like 'comprehensive guidance and automation' without specifying concrete actions or capabilities. While it includes some useful trigger terms, it lacks specificity about what the skill actually does (e.g., which cloud platforms, what types of analysis, what optimization actions). The description also uses an awkward imperative voice in the opening ('Execute use when...') rather than third person.
Suggestions
Replace vague language with specific concrete actions, e.g., 'Analyzes cloud resource usage across AWS/GCP/Azure, identifies underutilized instances, recommends rightsizing, and generates cost savings reports.'
Expand trigger terms to include common variations like 'cloud billing', 'AWS costs', 'reserved instances', 'cost explorer', 'spending report', 'infrastructure costs'.
Rewrite the opening in third person voice (e.g., 'Provides cloud cost optimization for...') and add a clear 'Use when...' clause describing specific scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'cost analysis and optimization with comprehensive guidance and automation' without listing any concrete actions. There are no specific capabilities mentioned—just abstract claims about what the skill provides. | 1 / 3 |
Completeness | It has a weak 'what' (vague 'cost analysis and optimization') and does include trigger phrases serving as a partial 'when' clause. However, the 'what' is too vague to be truly useful, and the 'when' is limited to just three phrases rather than describing scenarios comprehensively. | 2 / 3 |
Trigger Term Quality | It includes some natural trigger phrases like 'optimize costs', 'analyze spending', and 'reduce costs', which users might say. However, it lacks variations such as 'cloud billing', 'AWS/GCP/Azure costs', 'cost report', 'spending breakdown', or specific cloud platform terms. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'cloud cost optimization' provides some specificity, but the description is broad enough that it could overlap with general financial analysis skills, budgeting tools, or other cloud management skills. It doesn't specify which cloud platforms or what types of cost optimization it handles. | 2 / 3 |
Total | 7 / 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 broad overview of cloud cost optimization across three major providers but lacks the concrete, executable guidance needed to be truly actionable. The instructions read more like a checklist of goals than a step-by-step technical guide—there are no actual scripts, CLI command examples with full arguments, or template configurations. The error handling table is a strength, but the absence of validation checkpoints in a workflow involving resource deletion and infrastructure changes is a notable weakness.
Suggestions
Add concrete, executable code examples for key steps: full AWS CLI commands for cost data retrieval, a Python script for detecting idle resources, and a sample Terraform snippet for rightsizing—not just descriptions of what to do.
Insert explicit validation checkpoints: add dry-run verification before resource cleanup (step 3), a confirmation gate before applying IaC changes (step 8), and a cost comparison check after implementing optimizations.
Remove or condense the Overview paragraph—Claude already understands cloud cost optimization concepts. Jump straight to Prerequisites or a quick-start command.
Consider splitting per-cloud-provider details into separate reference files (e.g., AWS_COSTS.md, GCP_COSTS.md) to keep the main skill focused and enable progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably structured but includes some unnecessary verbosity. The Overview section explains what cloud cost optimization is, which Claude already knows. The Examples section restates things already covered in Instructions. However, it's not egregiously padded. | 2 / 3 |
Actionability | Despite listing 10 steps, the skill provides no executable code, no concrete CLI commands with full syntax, no scripts, and no copy-paste-ready configurations. Instructions like 'Pull current cost data' and 'Recommend rightsizing' are descriptive rather than actionable. The Terraform/IaC changes and cleanup scripts mentioned in Output are never actually provided. | 1 / 3 |
Workflow Clarity | The 10 steps provide a clear sequence, and the error handling table adds useful recovery guidance. However, there are no validation checkpoints between steps—no verification that cost data was pulled correctly, no dry-run before cleanup, no confirmation gates before applying IaC changes. For destructive operations like resource cleanup and infrastructure changes, this is a significant gap. | 2 / 3 |
Progressive Disclosure | The content is organized into clear sections (Prerequisites, Instructions, Output, Error Handling, Examples, Resources), which is good. However, with no bundle files, all content is inline in a single file. The detailed error handling table and multi-cloud coverage could benefit from being split into per-provider reference files. The Resources section provides external links but no internal file references. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%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 | |
- Commit
3a2d27d
- 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.