aws-cost-optimizer

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

Quality

37%

Does it follow best practices?

Impact

Pending

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, which is helpful for differentiation. However, it lacks a 'Use when...' clause, doesn't enumerate specific concrete actions, and misses common user trigger terms like 'billing', 'cloud spending', or 'savings plans'. It reads more like a title than a functional description that helps Claude select the right skill.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about AWS costs, cloud spending, billing analysis, savings plans, reserved instances, or cost reduction strategies.'

List specific concrete actions such as 'Analyzes AWS billing data, identifies unused resources, recommends rightsizing opportunities, evaluates Reserved Instance and Savings Plan coverage, and generates cost breakdowns by service or tag.'

Include natural trigger terms users would say, such as 'AWS bill', 'cloud spending', 'cost reduction', 'savings plans', 'reserved instances', and 'cost breakdown'.

Dimension	Reasoning	Score
Specificity	Names the domain (AWS cost) and some actions ('cost analysis' and 'optimization recommendations'), and mentions specific tools (AWS CLI, Cost Explorer), but doesn't list multiple concrete actions like identifying unused resources, rightsizing instances, or analyzing billing breakdowns.	2 / 3
Completeness	Describes what it does (AWS cost analysis and optimization recommendations) 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 not very detailed, warranting a 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'AWS', 'cost', 'Cost Explorer', and 'AWS CLI' which users might mention, but misses common variations like 'cloud spending', 'billing', 'savings plans', 'reserved instances', 'cost reduction', or 'AWS bill'.	2 / 3
Distinctiveness Conflict Risk	The combination of AWS cost analysis with specific tools (AWS CLI, Cost Explorer) provides some distinctiveness, but 'cost analysis and optimization' is broad enough that it could overlap with general AWS management skills or cloud infrastructure skills.	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 suffers from significant verbosity with sections that describe capabilities rather than instruct (Core Capabilities, Example Prompts, Best Practices), and it lacks proper validation/feedback loops for destructive operations like resource deletion. The monolithic structure with no external file references makes it token-inefficient.

Suggestions

Remove or drastically reduce 'Core Capabilities', 'Example Prompts', 'When to Use This Skill', and 'Best Practices' sections—these describe rather than instruct and waste tokens on things Claude already knows.

Add explicit validation steps before destructive operations: e.g., 'List unattached volumes → verify each is truly unused (check last attach time, tags) → confirm with user → delete with --dry-run first → then delete.'

Split the CLI command reference, checklist, and workflow into separate files (e.g., CLI_REFERENCE.md, CHECKLIST.md) and link from a concise SKILL.md overview.

Remove the 'Integration with Kiro CLI' and 'Additional Resources' sections as they add minimal actionable value.

Dimension	Reasoning	Score
Conciseness	The skill is excessively verbose with sections Claude doesn't need: 'When to Use This Skill', 'Example Prompts', 'Core Capabilities' bullet lists that merely describe what the skill does rather than instruct, 'Best Practices' that are generic advice Claude already knows, and 'Integration with Kiro CLI' that adds little value. The 'Additional Resources' section with URLs is also low-value filler.	1 / 3
Actionability	The AWS CLI commands are concrete, executable, and copy-paste ready with proper flags, JMESPath queries, and date calculations. Commands cover cost analysis, unused resource detection, and rightsizing analysis with specific output formatting.	3 / 3
Workflow Clarity	The 'Optimization Workflow' provides a clear 4-step sequence, and the Safety Notes mention risk levels. However, there are no explicit validation checkpoints or feedback loops for destructive operations like deleting EBS volumes or snapshots—the workflow just says 'Delete unattached EBS volumes' without a verify-then-delete pattern. This should cap the score at 2 per the rubric's feedback loop requirement for destructive changes.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files. Everything is inline—the checklist, example prompts, best practices, CLI commands, and workflow could be split into separate reference files. At ~150+ lines, this would benefit significantly from progressive disclosure.	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: 431bfad

Reviewed: 2 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.