cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
55
61%
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/cloud-infrastructure/skills/cost-optimization/SKILL.mdQuality
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 defines its scope across four major cloud providers, lists specific optimization techniques, and includes an explicit 'Use when' clause with natural trigger terms. It uses proper third-person voice and is concise without being vague. The description would effectively differentiate itself from general cloud management or DevOps skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: resource rightsizing, tagging strategies, reserved instances, and spending analysis across named cloud providers (AWS, Azure, GCP, OCI). | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize cloud costs through rightsizing, tagging, reserved instances, spending analysis) and 'when' (explicit 'Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'cloud costs', 'AWS', 'Azure', 'GCP', 'rightsizing', 'reserved instances', 'cloud expenses', 'infrastructure costs', 'cost governance'. These cover common variations of how users discuss cloud cost optimization. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in cloud cost optimization. The specific mention of cloud providers, cost-specific strategies like rightsizing and reserved instances, and cost governance makes it unlikely to conflict with general cloud infrastructure or DevOps skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a cloud cost optimization wiki page than an actionable skill for Claude. It is excessively verbose, repeating well-known cloud concepts, and lacks a clear workflow for how Claude should actually approach a cost optimization task. The few Terraform examples are a strength, but they're buried in a sea of generic bullet points that Claude already knows.
Suggestions
Add a clear step-by-step workflow (e.g., 1. Discover current spend → 2. Identify waste → 3. Implement changes → 4. Validate savings) with explicit validation checkpoints at each stage.
Remove generic descriptions of cloud concepts (what reserved instances are, what spot instances are) and focus only on specific decision criteria, thresholds, and executable code/commands Claude wouldn't already know.
Split provider-specific details into separate reference files (e.g., aws-cost-optimization.md, azure-cost-optimization.md) and keep SKILL.md as a concise overview with navigation links.
Add concrete examples of cost analysis commands (e.g., AWS CLI commands to find unused resources, queries for cost explorer) rather than just listing tool names.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines, with much content Claude already knows (what reserved instances are, what spot instances are, basic cloud concepts). Bullet-point lists like 'Use managed services', 'Implement caching' are generic advice that add no novel information. The checklist at the end largely repeats earlier content. | 1 / 3 |
Actionability | There are some executable Terraform code blocks (S3 lifecycle, budget alerts, autoscaling) which are concrete and copy-paste ready. However, much of the content is descriptive bullet points and plain-text tables rather than actionable commands or code. The Azure, GCP, and OCI sections are entirely abstract guidance with no executable examples. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow or sequenced process for performing cost optimization. The content is organized as a reference catalog of options rather than a guided process. There are no validation checkpoints, feedback loops, or decision points to guide Claude through an actual cost optimization engagement. | 1 / 3 |
Progressive Disclosure | The content has section headers providing some structure, and there is one reference to 'references/tagging-standards.md'. However, the bulk of the content is a monolithic wall of information that could benefit from splitting into provider-specific reference files. The referenced bundle file doesn't exist, and most content that should be in separate files is inline. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- wshobson/agents
- Commit
112197c
- 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.