aws-cost-cleanup

Automated cleanup of unused AWS resources to reduce costs

Quality

32%

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-cleanup/SKILL.md

Quality

Content

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 cleanup scripts and a reasonable safety framework, but it is far too verbose for a skill file. Content that should be split into separate referenced files (Lambda code, lifecycle policies, cost calculator) is all inlined, creating a monolithic document. Several sections (Example Prompts, Kiro CLI Integration, Additional Resources, Limitations boilerplate) add little actionable value and waste tokens.

Suggestions

Reduce the SKILL.md to a concise overview (~80 lines) with the cleanup targets list, one representative script example, the safety checklist, and the workflow steps—move all other scripts and code into separate bundle files (e.g., scripts/cleanup-ebs.sh, scripts/calculate-savings.py, lambda/cleanup.py)

Remove the 'Example Prompts', 'Kiro CLI Integration', 'Additional Resources', and generic 'Limitations' sections entirely—these don't help Claude execute the task

Make validation steps in the workflow concrete: add specific AWS CLI commands to verify resource dependencies (e.g., checking if a snapshot is referenced by an AMI before deletion, checking if an EIP has DNS records)

Consolidate 'Best Practices' and 'Risk Mitigation' into the Safety Checklist to eliminate redundancy

Dimension	Reasoning	Score
Conciseness	The skill is excessively verbose at ~250+ lines. It includes unnecessary sections like 'Example Prompts', 'Kiro CLI Integration', 'Additional Resources', 'When to Use This Skill', and 'Limitations' boilerplate that add little value. The 'Best Practices' and 'Risk Mitigation' sections overlap significantly. Claude already knows AWS CLI syntax and boto3 patterns—much of this could be condensed dramatically.	1 / 3
Actionability	The skill provides fully executable bash scripts and Python code that are copy-paste ready. The AWS CLI commands are specific with proper query filters, and the Lambda function, lifecycle policy JSON, and cost calculator are all concrete and complete.	3 / 3
Workflow Clarity	The 4-phase cleanup workflow is clearly sequenced and the safety checklist is good, but the validation steps within the workflow are vague ('Verify resources are truly unused', 'Check for dependencies') without concrete commands or checks. For destructive batch operations like deleting volumes and snapshots, the feedback loops are implicit rather than explicit in the scripts themselves.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with no bundle files to offload content to. The S3 lifecycle policy, Lambda function, cost calculator, multi-account scripts, and monitoring setup could all be separate referenced files. Everything is inlined in one massive document, making it hard to navigate and consuming excessive context window.	1 / 3
	Total	7 / 12 Passed

Description

22%

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 is too vague and high-level, reading more like a tagline than a functional skill description. It lacks specific actions, resource types, and explicit trigger guidance ('Use when...'), making it difficult for Claude to confidently select this skill over others in a large skill library.

Suggestions

List specific concrete actions and resource types, e.g., 'Identifies and removes unused EC2 instances, unattached EBS volumes, stale snapshots, idle load balancers, and orphaned Elastic IPs.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about reducing AWS costs, cleaning up unused cloud resources, finding idle instances, or optimizing AWS spend.'

Include common keyword variations users might say, such as 'cost optimization', 'cloud waste', 'idle resources', 'AWS bill reduction', specific service names like 'EC2', 'S3', 'RDS'.

Dimension	Reasoning	Score
Specificity	The description says 'cleanup of unused AWS resources' which is vague — it doesn't specify what types of resources (EC2 instances, EBS volumes, snapshots, etc.) or what concrete actions are performed (terminate, delete, deregister, etc.).	1 / 3
Completeness	It provides a vague 'what' (cleanup unused AWS resources) but has no explicit 'when' clause or trigger guidance. The absence of a 'Use when...' clause caps this at 2 per the rubric, and the 'what' is also weak, so it scores a 1.	1 / 3
Trigger Term Quality	It includes 'AWS', 'unused', 'cleanup', and 'costs' which are somewhat natural terms a user might say, but it's missing specific resource types (e.g., EC2, S3, EBS, snapshots, idle instances) and common variations like 'cost optimization' or 'cloud waste'.	2 / 3
Distinctiveness Conflict Risk	The AWS cost/cleanup focus provides some distinctiveness, but 'unused AWS resources' is broad enough to potentially overlap with AWS infrastructure management, cost analysis, or cloud optimization skills.	2 / 3
	Total	6 / 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: 47e0c5a

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.