CtrlK
BlogDocsLog inGet started
Tessl Logo

aws-cost-optimizer

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

50

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-aws-cost-optimizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 skill's core strength is its highly executable AWS CLI reference, but it is packaged as a long single file with padded sections and a workflow whose destructive steps lack inline validation. Restructuring into SKILL.md plus reference files and adding verify-before-delete checkpoints would raise quality substantially.

Suggestions

Embed validation checkpoints in the Quick Wins workflow (e.g., "List unattached volumes → confirm with the user which are safe → snapshot/backup → delete → verify removal") instead of relying on a separate Safety Notes section.

Split the command catalog, example prompts, and checklist into reference files (e.g., references/commands.md, references/prompts.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

Remove or shrink the "Integration with Kiro CLI" and "Example Prompts" sections, which add token cost without adding capability Claude cannot infer.

DimensionReasoningScore

Conciseness

The body is mostly efficient — terse bullet lists and command blocks with no basic-concept explanations — but sections like "Example Prompts", "Integration with Kiro CLI", and the generic "Best Practices" list add tokens Claude does not need. This is anchor 3 (mostly efficient with some content that could be tightened) rather than 4, since multiple sections could be trimmed or cut entirely.

3 / 5

Actionability

Concrete, copy-paste-ready AWS CLI commands with working --query filters and date arithmetic cover the common cases (cost breakdowns, unattached volumes, idle instances, rightsizing). Minor gaps keep it at 4 rather than 5: placeholder identifiers (i-xxxxx, mydb), no pagination handling, and the snapshot date-substitution quoting is fragile.

4 / 5

Workflow Clarity

The four-phase Optimization Workflow (Baseline → Quick Wins → Strategic → Monitoring) is clearly sequenced, but the "Quick Wins" phase lists destructive batch actions ("Delete unattached EBS volumes", "Stop/terminate idle EC2 instances", "Delete old snapshots") with no validation checkpoints embedded in the workflow itself — the safety caveats live in a separate section. The destructive-operations rule caps workflow clarity at 3 despite the good sequencing.

3 / 5

Progressive Disclosure

The file has well-organized section headers, but it is a ~190-line monolith with no bundle files: the CLI command catalog, example prompts, and checklist content that would fit naturally in separate reference files are all inlined. Anchor 3 (some structure, but content that should be separate is inline) rather than 4, since there is no file-level separation at all for a skill well over 50 lines.

3 / 5

Total

13

/

20

Passed

Description

53%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 answers "what" concretely but entirely omits "when", capping completeness at 3 and weakening trigger discoverability. It is distinct and mostly free of fluff except for "Comprehensive". Adding a "Use when..." clause with natural user phrasings would lift most dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about AWS spending, cloud costs, reducing their AWS bill, or finding idle/unused AWS resources."

Replace the buzzword "Comprehensive" with 2-3 named capabilities such as "find idle EC2 instances and unattached EBS volumes, analyze Cost Explorer trends, recommend Reserved Instances".

Include natural synonyms users would say ("AWS bill", "cloud spend", "cost savings") to improve trigger term coverage.

DimensionReasoningScore

Specificity

"AWS cost analysis" and "optimization recommendations" name the domain with two moderately concrete actions, but "Comprehensive" is filler and no specific capabilities (e.g., finding idle resources, rightsizing) are enumerated. This matches anchor 3 rather than 4 because the actions remain generic rather than several distinct specific ones.

3 / 5

Completeness

The "what" is clearly stated ("cost analysis and optimization recommendations using AWS CLI and Cost Explorer") but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the "what" is concrete, not vague.

3 / 5

Trigger Term Quality

Relevant keywords like "AWS", "cost", "Cost Explorer", and "AWS CLI" are present, but common natural phrasings users would actually say — "AWS bill", "cloud spend", "reduce spending", "save on AWS costs" — are missing. Not 4 because the keyword set lacks the natural-language variations the anchor requires.

3 / 5

Distinctiveness Conflict Risk

The AWS-specific niche with named tools ("AWS CLI and Cost Explorer") gives clear distinct triggers with only minor overlap risk against general cloud-finops or AWS-administration skills. Not 5 because "cost analysis and optimization" alone could still collide with broader cloud cost skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
boisenoise/skills-collections
Reviewed

Table of Contents

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.