aws-cost-cleanup

Automated cleanup of unused AWS resources to reduce costs

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-aws-cost-cleanup/SKILL.md

Quality

Content

56%Weight 40%Scale 1-5

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

The body is strong on executable, concrete AWS CLI/boto3 guidance and has a sensible phased workflow with dry-run and validation emphasis. Its weaknesses are verbosity from redundant safety/practice sections and a monolithic structure that inlines scripts which belong in bundle files.

Suggestions

Move the named scripts (cleanup-unused-ebs.sh, cleanup-old-snapshots.sh, release-unused-eips.sh, calculate-savings.py, the Lambda handler) into a scripts/ directory and reference them from SKILL.md to cut the body's length substantially.

Merge the overlapping 'Safety Checklist', 'Best Practices', 'Risk Mitigation', and 'Always:' sections into one consolidated safety block, and drop the redundant 'When to Use This Skill' section and 'Kiro CLI Integration' filler.

Add concrete validation commands to each workflow phase (e.g. how to verify a resource is unused before deletion) and a fix/retry loop for failed deletions to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~300-line body has several padded or duplicated sections: 'When to Use This Skill' merely repeats the frontmatter description, and 'Safety Checklist', 'Best Practices', 'Risk Mitigation', and 'Always:' blocks restate the same cautionary advice three times over. The 'Kiro CLI Integration' section adds little skill-specific value, and a full Lambda function is inlined. This matches anchor 2 (several unnecessary/padded sections) more than 3's 'some unnecessary explanation', since the padding is repeated across multiple sections rather than incidental.	2 / 5
Actionability	Concrete, executable code dominates: dry-run bash scripts for EBS volumes, snapshots, and Elastic IPs; a boto3 savings calculator; an S3 lifecycle policy; and CloudWatch alarm commands. It falls short of 5 because listed cleanup targets (unused AMIs, orphaned ENIs, NAT Gateways, ELBs) have no scripts, and the Organizations loop assumes preconfigured named profiles without explaining how.	4 / 5
Workflow Clarity	The four-phase workflow (Discovery → Validation → dry-run Execution → Verification) is clearly sequenced with explicit validation checkpoints and a safety checklist, so the destructive-operation cap at 3 does not apply. However, phases are high-level bullets without the underlying commands or fix/retry feedback loops, keeping it at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	The body is well-sectioned with clear headers, but it is monolithic: scripts explicitly named as files ('cleanup-unused-ebs.sh', 'calculate-savings.py', the Lambda handler) are fully inlined rather than placed in a scripts/ directory, and there are no one-level-deep internal references at all. This matches anchor 3 ('content that should be separate is inline') — structure is good, so it is above anchor 2's 'minimal structure'.	3 / 5
	Total	13 / 20 Passed

Description

48%Weight 40%Scale 1-5

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 names a clear, distinct niche but is thin: one generic verb ('cleanup'), no concrete resource types, and no trigger guidance for when to invoke the skill. It reads more like a title than a capability description with triggers.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user wants to reduce AWS costs, clean up unused resources, or lower their AWS bill.'

List the concrete resource types covered (unattached EBS volumes, old snapshots, unused Elastic IPs, incomplete S3 multipart uploads) so the 'what' is specific and comprehensive.

Include natural synonyms users would say — 'AWS bill', 'cost savings', 'unused EC2/EBS/S3 resources' — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Automated cleanup of unused AWS resources to reduce costs" names the domain (AWS, unused resources) but offers only the generic action "cleanup" with no concrete resource types or operations. It matches anchor 2 ('names the domain but actions are minimal or generic') rather than 3, which requires 1-2 concrete actions like 'deletes unattached EBS volumes and old snapshots'.	2 / 5
Completeness	The 'what' is stated (automated cleanup of unused AWS resources to reduce costs) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because the 'when' is entirely absent rather than just imprecise.	3 / 5
Trigger Term Quality	Terms like "AWS", "cleanup", "unused resources", and "costs" are natural keywords, but common user phrasings such as "reduce my AWS bill", "EBS volumes", "snapshots", or "Elastic IPs" are absent. This lands at anchor 3 (relevant keywords but missing common variations), below 4 which requires only a few missing natural terms.	3 / 5
Distinctiveness Conflict Risk	"AWS" + "unused resources" + "cleanup" carves a fairly distinct niche with minimal conflict risk against non-AWS or non-cleanup skills. It falls short of 5 only because it could overlap slightly with broader AWS cost-optimization or governance skills.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-aws-cost-cleanup/SKILL.md
Commit: 690de8f

Reviewed: 7 hours 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.