aws-cost-optimizer

Comprehensive AWS cost analysis and optimization recommendations using AWS CLI and Cost Explorer

Quality

37%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-aws-cost-optimizer/SKILL.md

Quality

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a clear domain (AWS cost optimization) and mentions specific tools (AWS CLI, Cost Explorer), which helps with distinctiveness. However, it lacks a 'Use when...' clause entirely, the capabilities listed are high-level rather than concrete, and it misses common user trigger terms like 'billing', 'cloud spending', or 'save money'.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about AWS billing, cloud spending, cost reduction, or wants to optimize their AWS infrastructure costs.'

List specific concrete actions such as 'Analyzes spending trends, identifies unused resources, recommends reserved instance purchases, reviews rightsizing opportunities, and generates cost breakdowns by service.'

Include natural trigger term variations users might say: 'AWS bill', 'cloud costs', 'save money on AWS', 'spending too much on AWS', 'cost breakdown'.

Dimension	Reasoning	Score
Specificity	Names the domain (AWS cost) and some actions ('cost analysis and optimization recommendations'), but doesn't list multiple specific concrete actions like identifying unused resources, rightsizing instances, or analyzing reserved instance coverage.	2 / 3
Completeness	Describes what it does (AWS cost analysis and optimization) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also only moderately detailed, warranting a 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'AWS', 'cost', 'Cost Explorer', and 'AWS CLI', but misses common user variations like 'cloud spending', 'billing', 'save money on AWS', 'cost reduction', or 'cloud costs'.	2 / 3
Distinctiveness Conflict Risk	The AWS cost focus with specific tools (AWS CLI, Cost Explorer) provides some distinctiveness, but could overlap with general AWS management skills or cloud infrastructure skills without clearer boundaries.	2 / 3
	Total	7 / 12 Passed

Implementation

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides genuinely useful, executable AWS CLI commands for cost analysis and optimization, which is its strongest aspect. However, it is significantly bloated with sections that don't add value for Claude (example prompts, Kiro CLI integration, verbose capability descriptions, external resource links). The workflow lacks critical validation checkpoints for destructive operations, and the monolithic structure would benefit greatly from splitting into focused reference files.

Suggestions

Remove or drastically reduce sections like 'When to Use This Skill', 'Core Capabilities' (redundant with the commands), 'Example Prompts', 'Integration with Kiro CLI', and 'Additional Resources' — these waste tokens on things Claude already knows or doesn't need.

Add explicit validation steps in the workflow before destructive actions, e.g., 'List volumes to delete → confirm with user → use --dry-run → execute deletion → verify volumes are gone'.

Split the content into focused files: keep SKILL.md as a concise overview with quick-start commands, and move detailed CLI references, the checklist, and best practices into separate bundle files like CLI_REFERENCE.md and CHECKLIST.md.

Remove the 'Best Practices' and 'Limitations' boilerplate sections — Claude already knows to test in non-production and ask for clarification when inputs are missing.

Dimension	Reasoning	Score
Conciseness	The skill is very verbose with significant padding. Sections like 'When to Use This Skill', 'Example Prompts', 'Best Practices', 'Additional Resources', and 'Integration with Kiro CLI' add little value for Claude. The 'Core Capabilities' section is a descriptive overview that restates what the commands below already demonstrate. The checklist, while useful for humans, is largely redundant given the workflow section. Many concepts explained (like what idle EC2 instances are) are things Claude already knows.	1 / 3
Actionability	The AWS CLI commands are concrete, executable, and copy-paste ready with proper flags, JMESPath queries, and output formatting. Commands cover cost analysis, unused resource detection, and rightsizing with real parameters and date calculations.	3 / 3
Workflow Clarity	The 4-step optimization workflow provides a logical sequence but lacks explicit validation checkpoints. For destructive operations like deleting EBS volumes or snapshots, there's no validate-then-act feedback loop — just a general 'verify resources are truly unused' note in Best Practices. The safety notes mention risk levels but don't integrate verification steps into the workflow itself.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with no bundle files to reference. Everything is inline — the checklist, example prompts, best practices, CLI commands, and workflow could be split into separate files. External links to AWS docs don't count as progressive disclosure within the skill bundle. The 'Additional Resources' section links externally but there's no internal structure.	1 / 3
	Total	7 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: boisenoise/skills-collections
Commit: 8ac11ab

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.