aws-cost-cleanup

Automated cleanup of unused AWS resources to reduce costs

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The content is highly actionable with a clear, well-checkpointed workflow, but it is over-long for a SKILL.md and lacks any progressive-disclosure structure: everything lives inline with no referenced detail files.

Suggestions

Split the full scripts (Lambda handler, cost calculator, individual cleanup scripts) into files under scripts/ and reference them from a concise overview to improve progressive disclosure and conciseness.

Trim the inline examples to the essential pattern and link out to the rest, reducing the ~310-line body toward a lean overview.

Verify any referenced bundle paths actually exist once files are split, since currently no references/, scripts/, or assets/ directories are present.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining basic concepts Claude already knows, but at ~310 lines it inlines several full scripts (Lambda handler, cost calculator) that could be tightened or moved out, so it is mostly efficient rather than lean.	2 / 3
Actionability	Provides multiple fully executable, copy-paste-ready artifacts — real aws CLI commands, a boto3 savings calculator, a Lambda handler, and a lifecycle-policy JSON — giving concrete, specific guidance.	3 / 3
Workflow Clarity	Sequences a four-phase workflow (Discovery → Validation → Execution → Verification) with an explicit dry-run-first feedback loop and a safety checklist, satisfying the validation/checkpoint requirement for destructive batch operations.	3 / 3
Progressive Disclosure	No bundle files exist and all content — including full multi-script implementations — is inline in a single monolithic SKILL.md; sections are well organized, but content that should be separate is not split into clearly signaled one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 clear and accurate but generic: it states the goal without listing concrete actions or an explicit usage trigger, so it stops short of being sharply specific or fully complete.

Suggestions

Add a concise 'Use when...' clause naming trigger scenarios (e.g., 'Use when auditing AWS accounts for waste or when the user mentions unattached volumes, old snapshots, or unused IPs').

Enumerate the concrete cleanup targets in the description (e.g., unattached EBS volumes, old snapshots, unused Elastic IPs) to lift specificity from 2 to 3.

Add natural keyword variations users would actually say ('AWS waste', 'reduce my AWS bill', 'EBS snapshots') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ('unused AWS resources') and a broad action ('cleanup...to reduce costs'), but does not enumerate the specific cleanup actions (volumes, snapshots, EIPs) needed for a 3.	2 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' trigger in the description; the When-to-use guidance lives only in the body, which caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant natural terms ('unused AWS resources', 'reduce costs') but omits common variations a user would say ('EBS', 'snapshots', 'Elastic IPs', 'waste', 'billing').	2 / 3
Distinctiveness Conflict Risk	'Unused AWS resources' is a recognizable niche, but the description is broad enough to overlap with other AWS or cost-management skills rather than carving a clearly distinct trigger.	2 / 3
	Total	8 / 12 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
Commit: f36337d

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.