cost-comparison

Use when comparing costs between time periods, environments, accounts, regions, or teams to understand spending differences and identify inefficiencies

Quality

88%

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

Quality

Content

77%Weight 40%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 content is highly actionable with concrete API examples, formulas, and a clear sequenced workflow, but it is verbose and monolithic — much of the output-template and scenario material should live in one-level-deep reference files. No bundle files were present locally to verify referenced paths.

Suggestions

Move the nine-section Output Format template and the five Common Comparison Scenarios into a referenced file (e.g., references/output-templates.md) and keep SKILL.md as a lean overview with one-level-deep pointers.

Consolidate the overlapping 'Skill-Specific Best Practices', 'Tips for Effective Comparison', and 'Advanced Techniques' sections into a single concise list to remove redundancy.

Add an explicit validation checkpoint early in the workflow (e.g., 'verify both comparison groups returned complete data for equal-length periods before computing differences') to catch empty/partial queries before metrics are derived.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but it is padded with redundant advice sections ('Skill-Specific Best Practices', 'Tips for Effective Comparison', 'Advanced Techniques' overlap heavily) and verbose placeholder tables ($X,XXX / +XX%) that could be tightened.	2 / 3
Actionability	It supplies concrete get_cost_data(...) calls with real filter/group_by parameters, explicit formulas for difference/percentage/ratio, and specific variance thresholds (>50%, 20-50%, <20%), giving copy-paste-ready guidance.	3 / 3
Workflow Clarity	The seven-step procedure is clearly numbered and sequenced (Identify type → Query → Calculate → Identify differences → Drill down → Normalize → Patterns), with the 'All Math In Code' critical rule acting as an explicit guardrail; operations are read-only so destructive-batch validation caps do not apply.	3 / 3
Progressive Disclosure	External references are well-signaled in a 'See Also' section and inline (best-practices.md, cloudzero-tools-reference.md, error-handling.md, dimensions-reference.md, cost-types-reference.md), but the SKILL.md itself is a ~440-line monolith with the 9-section output template, five scenarios, and advanced techniques inlined rather than split into referenced files.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%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 is concise, uses third-person/trigger voice, and explicitly covers both capability and invocation conditions with concrete comparison dimensions. It is a strong, low-conflict trigger description.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete comparison scopes — 'time periods, environments, accounts, regions, or teams' — alongside explicit outcomes ('understand spending differences and identify inefficiencies'), matching the anchor for listing several specific concrete actions rather than vague language.	3 / 3
Completeness	It opens with an explicit 'Use when comparing costs...' trigger and states what the skill does (compare costs across named dimensions to surface differences and inefficiencies), clearly answering both what and when.	3 / 3
Trigger Term Quality	Phrases like 'comparing costs', 'time periods', 'environments', 'accounts', 'regions', and 'teams' are natural terms users would say when requesting a comparison, giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The scope is narrowly framed around cross-dimensional cost comparison, with distinct triggers ('comparing costs between ... environments, accounts, regions, or teams') that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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: Cloudzero/cloudzero-claude-marketplace
Path: plugins/cost-analyst/skills/cost-comparison/SKILL.md
Commit: b9c7c16

Reviewed: 13 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.