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".
38
37%
Does it follow best practices?
Impact
—
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 padded with vague buzzwords ('comprehensive guidance and automation') and lacks concrete, specific actions that would help Claude distinguish this skill from others. While it includes some trigger phrases, the overall lack of specificity about what the skill actually does (e.g., which cloud providers, what types of analysis, what optimization actions) significantly weakens its utility for skill selection.
Suggestions
Replace vague language like 'comprehensive guidance and automation' with specific concrete actions, e.g., 'Analyzes AWS/Azure/GCP billing data, identifies unused resources, recommends reserved instance purchases, and generates cost reduction reports.'
Expand trigger terms to include common user phrases and cloud-specific keywords like 'AWS bill', 'cloud spending', 'reserved instances', 'right-sizing', 'billing report', 'cost explorer'.
Strengthen the 'when' clause with explicit contextual triggers, e.g., 'Use when the user asks about cloud infrastructure costs, wants to review billing data, or needs recommendations for reducing cloud spend.'
| 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 it 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 so vague that the completeness is undermined, and the 'when' is formulaic rather than contextually rich. | 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/Azure/GCP costs', 'cost report', 'budget', or specific cloud provider terms. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'cloud cost optimization' provides some niche focus, but the description is generic enough that it could overlap with general financial analysis skills, budgeting tools, or any cost-related skill. No specific cloud platforms or tooling are mentioned to sharpen distinctiveness. | 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 covers a broad and important topic but lacks the concrete, executable guidance that would make it truly useful. The instructions read more like a high-level checklist or consulting framework than actionable steps Claude can execute—there are no actual CLI commands with proper arguments, no code snippets, no Terraform examples, and no sample API calls. The error handling table is a strength, but the overall skill would benefit significantly from executable code examples and validation checkpoints.
Suggestions
Add concrete, executable CLI commands for each step (e.g., full `aws ce get-cost-and-usage` command with proper `--time-period`, `--granularity`, and `--metrics` flags, and equivalent `gcloud`/`az` commands).
Include at least one complete, copy-paste-ready script for a common task like detecting idle EC2 instances or generating an S3 lifecycle policy JSON.
Add explicit validation checkpoints in the workflow, especially before generating IaC changes (step 8) and before executing cleanup scripts—integrate the dry-run step directly into the numbered workflow.
Split provider-specific guidance (AWS, GCP, Azure) into separate referenced files to improve progressive disclosure and reduce the monolithic nature of the current content.
| 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 describes tasks in natural language rather than providing executable examples. However, the error handling table and instructions are fairly efficient. | 2 / 3 |
Actionability | Despite listing 10 steps, the skill provides no executable code, no concrete CLI commands with full syntax, no actual Terraform snippets, and no real scripts. Instructions like 'Pull current cost data' and 'Recommend rightsizing' are descriptive rather than actionable. The examples section lists prompts rather than input/output pairs with concrete code. | 1 / 3 |
Workflow Clarity | The 10 steps provide a clear sequence, and the error handling table adds some recovery guidance. However, there are no explicit validation checkpoints between steps—particularly critical before step 8 (generating IaC changes) and before executing cleanup scripts. The dry-run mention in Output is good but not integrated into the workflow itself. | 2 / 3 |
Progressive Disclosure | The content is well-sectioned with clear headers (Prerequisites, Instructions, Output, Error Handling, Examples, Resources). However, for a skill this broad (covering AWS, GCP, and Azure across multiple optimization strategies), the content would benefit from splitting provider-specific details into separate files. As a standalone file with no bundle, it's a monolithic treatment of a complex topic. | 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
6e9558f
- 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.