cost-optimization
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
74
61%
Does it follow best practices?
Impact
98%
1.28xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/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 well-crafted skill description that follows best practices closely. It uses third person voice, lists specific concrete capabilities, includes an explicit 'Use when' clause with natural trigger terms, and occupies a clearly defined niche. The description is concise yet comprehensive, covering both the actions performed and the scenarios that should trigger its selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'resource rightsizing', 'tagging strategies', 'reserved instances', and 'spending analysis'. These are distinct, well-defined cloud cost optimization activities. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize cloud costs through rightsizing, tagging, reserved instances, spending analysis) and 'when' (explicit 'Use when' clause covering reducing expenses, analyzing costs, implementing governance policies). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'cloud costs', 'rightsizing', 'reserved instances', 'spending analysis', 'cloud expenses', 'infrastructure costs', 'cost governance'. These cover common variations of how users discuss cloud cost optimization. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche around cloud cost optimization with specific triggers like 'rightsizing', 'reserved instances', 'tagging strategies', and 'cost governance' that are 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 knowledge base article than an actionable skill for Claude. It is heavily padded with general cloud knowledge that Claude already possesses, lacks a clear workflow or decision process, and doesn't define when or how to apply specific optimizations. The Terraform examples add some value but are buried in verbose advisory content.
Suggestions
Remove general cloud knowledge (pricing model descriptions, what spot instances are, etc.) and focus only on specific decision criteria, thresholds, and executable patterns Claude wouldn't already know.
Add a clear workflow: e.g., 1) Analyze current costs with specific commands/queries, 2) Identify optimization targets using specific metrics/thresholds, 3) Implement changes, 4) Validate savings — with explicit validation checkpoints.
Split cloud-specific details (AWS, Azure, GCP) into separate reference files and keep SKILL.md as a concise overview with decision logic for which optimizations to apply when.
Add concrete decision thresholds (e.g., 'If CPU utilization < 20% for 14 days, recommend downsizing') rather than generic advice like 'right-size instances based on utilization'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose and largely consists of information Claude already knows—cloud pricing models, general cost optimization strategies, and basic cloud service descriptions. Much of the content reads like a cloud cost optimization blog post rather than actionable instructions that add novel knowledge. The bullet-point lists of general advice (e.g., 'Use managed services', 'Implement caching') are things Claude can generate on its own. | 1 / 3 |
Actionability | There are some concrete Terraform code examples (S3 lifecycle, budget alerts, auto-scaling, tagging) that are executable and copy-paste ready. However, much of the content is vague bullet points and informational tables rather than specific instructions. The skill mixes actionable code with large amounts of descriptive/advisory content that doesn't tell Claude exactly what to do. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow or sequenced process. The content is organized as a reference catalog of cost optimization options rather than a guided process. The checklist at the end is helpful but lacks sequencing, validation steps, or feedback loops. For a skill involving potentially destructive changes (rightsizing, deleting resources), the absence of any verification or rollback steps is a significant gap. | 1 / 3 |
Progressive Disclosure | The skill references external files (references/tagging-standards.md, assets/cost-analysis-template.xlsx) and related skills, which is good structure. However, the main file is a monolithic wall of content (~250 lines) that could benefit significantly from splitting detailed cloud-specific sections into separate reference files. No bundle files are provided to support the references. | 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
- Dicklesworthstone/pi_agent_rust
- Commit
99da384
- 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.