aws-cost-cleanup

Automated cleanup of unused AWS resources to reduce costs

1.02x

Quality

32%

Does it follow best practices?

Impact

88%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/aws-cost-cleanup/SKILL.md

Quality

Content

42%Scale 1-3

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 solid safety checklist, but suffers from significant bloat. Too many sections repeat similar advice, and the entire content is inlined rather than split into focused reference files. The workflow section names the right phases but lacks concrete validation commands, relying on vague instructions like 'verify resources are truly unused' without showing how.

Suggestions

Split the content: keep SKILL.md as a concise overview with the workflow and safety checklist, then move cleanup scripts to SCRIPTS.md, the Lambda/automation code to AUTOMATION.md, and the cost calculator to COST_CALCULATOR.md with clear one-level references.

Remove the 'When to Use This Skill', 'Example Prompts', 'Kiro CLI Integration', and 'Additional Resources' sections entirely—they add no actionable value for Claude.

Add concrete validation commands to the workflow, e.g., 'Check volume attachments: aws ec2 describe-volumes --volume-id $vol --query Volumes[0].Attachments' and 'Check snapshot dependencies: aws ec2 describe-images --filters Name=block-device-mapping.snapshot-id,Values=$snap_id'.

Consolidate 'Best Practices', 'Risk Mitigation', and 'Safety Checklist' into a single concise safety section to eliminate redundancy.

Dimension	Reasoning	Score
Conciseness	The skill is excessively verbose at ~250 lines. It includes unnecessary sections like 'When to Use This Skill', 'Example Prompts', 'Kiro CLI Integration', 'Additional Resources', and 'Best Practices' that are either obvious or not actionable. The 'Risk Mitigation' and 'Best Practices' sections largely repeat the Safety Checklist. Claude doesn't need to be told what EBS volumes or Elastic IPs are.	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 syntax, filters, and output formatting. The Lambda function, lifecycle policy JSON, and cost calculator are all concrete and complete.	3 / 3
Workflow Clarity	The Cleanup Workflow section has a clear 4-phase sequence (Discovery → Validation → Execution → Verification) and the Safety Checklist is good. However, the validation steps are vague ('Check for dependencies', 'Verify resources are truly unused') without concrete commands to actually perform those checks. The feedback loop between dry-run and execution is implicit rather than explicit with specific validation commands.	2 / 3
Progressive Disclosure	This is a monolithic wall of content with no references to external files. The cleanup scripts, Lambda function, cost calculator, S3 lifecycle policy, Organizations integration, and monitoring setup could all be separate referenced files. Everything is inlined, making the skill overwhelming and hard to navigate.	1 / 3
	Total	7 / 12 Passed

Description

22%Scale 1-3

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 useful domain (AWS resource cleanup for cost reduction) but is too vague about specific capabilities and lacks explicit trigger guidance. It reads more like a tagline than a functional skill description, missing concrete actions, resource types, and a 'Use when...' clause.

Suggestions

List specific concrete actions and resource types, e.g., 'Identifies and removes unused EC2 instances, unattached EBS volumes, old 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 AWS cost optimization, cleaning up unused resources, reducing cloud spend, or finding idle/orphaned AWS infrastructure.'

Include common file or tool references users might mention, such as 'AWS CLI', 'Cost Explorer', 'Trusted Advisor', or specific service names to improve trigger term coverage.

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 partially addresses 'what' (cleanup unused AWS resources) but lacks specificity, and there is no 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it down to 1.	1 / 3
Trigger Term Quality	It includes 'AWS', 'unused', 'cleanup', and 'reduce 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) that users would commonly mention.	2 / 3
Distinctiveness Conflict Risk	The AWS cost optimization / unused resource cleanup niche is somewhat specific, but 'AWS resources' is broad enough to potentially overlap with other AWS-related skills (infrastructure management, cost analysis, etc.).	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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/aws-cost-cleanup/SKILL.md
Commit: fbdfd63

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.