cost-comparison

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

Quality

72%

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 ./plugins/cost-analyst/skills/cost-comparison/SKILL.md

Quality

Content

63%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.

A well-structured, actionable procedure with concrete API patterns, thresholds, and worked scenarios that make the comparison workflow easy to follow. Its weaknesses are verbosity (duplicated best-practices sections, heavy placeholder output templates) and inlining ~200 lines of output-format and scenario detail that belongs in a separate reference file.

Suggestions

Move the 9-subsection output format and the five 'Common Comparison Scenarios' walkthroughs into a reference file (e.g., references/comparison-output.md), keeping only the executive-summary template inline in SKILL.md.

Merge 'Skill-Specific Best Practices' and 'Tips for Effective Comparison' into one section — they cover the same guidance (normalization, root causes, fairness) twice.

Add one example Python script that computes differences/percentages from two get_cost_data results, since the Critical Rule mandates code-based math but no such script is shown.

Dimension	Reasoning	Score
Conciseness	The body is domain-specific rather than padded with concepts Claude already knows, but the 9-subsection output format is dense placeholder tables, and 'Skill-Specific Best Practices' and 'Tips for Effective Comparison' largely duplicate each other; both could be tightened.	3 / 5
Actionability	Concrete get_cost_data() calls with real parameters, formulas, variance thresholds (>50% / 20-50% / <20%), benchmark ratios, and unit-economics examples make the guidance mostly executable. Minor gap: the Critical Rule mandates Python computation yet no example script is provided and Step 3 formulas are bare pseudocode.	4 / 5
Workflow Clarity	A clear 7-step sequence (identify comparison type, query, calculate, categorize, drill down, normalize, find patterns) with concrete thresholds and a prerequisite that sequences loading the org-context skill first. Minor validation gaps: no explicit checkpoints confirming both comparison queries returned comparable data before computing differences.	4 / 5
Progressive Disclosure	Five plugin-level references are clearly signaled one level deep in 'See Also' and in-text, but none exist in this bundle's directories, and roughly 200 lines of output-format templates and scenario walkthroughs are inlined in SKILL.md where they could be split into a reference file.	3 / 5
	Total	14 / 20 Passed

Description

70%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.

A solid trigger-focused description with an explicit and well-enumerated 'Use when' clause and natural keywords across all comparison dimensions. Its main weakness is the under-specified 'what' — it never states the concrete outputs the skill produces (difference calculations, efficiency benchmarks, normalized comparisons).

Suggestions

State 2-3 concrete capabilities in the description, e.g., 'Calculates absolute and percentage differences, benchmarks efficiency across groups, and normalizes for scale' before the 'Use when' clause.

Add common trigger synonyms users say — 'vs', 'versus', 'benchmark', 'month-over-month' — to broaden natural-language matching.

Clarify what distinguishes this skill from sibling cost skills (e.g., trend analysis) for time-period comparisons to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	The description names the domain ('comparing costs between time periods, environments, accounts, regions, or teams') and 1-2 actions ('understand spending differences', 'identify inefficiencies'), but lists no concrete outputs like calculating percentage differences, benchmarking, or normalizing for scale.	3 / 5
Completeness	An explicit 'Use when...' clause with enumerated trigger dimensions clearly answers 'when', and 'comparing costs... to understand spending differences and identify inefficiencies' answers 'what', though the 'what' is thin on concrete capabilities.	4 / 5
Trigger Term Quality	Natural keywords like 'compare', 'costs', 'environments', 'accounts', 'regions', 'teams', and 'spending differences' cover the common phrasings users would say, but synonyms such as 'vs', 'versus', 'difference', 'benchmark', and 'month-over-month' are missing from the description.	4 / 5
Distinctiveness Conflict Risk	The enumerated comparison dimensions carve a distinct cost-comparison niche, but time-period comparisons ('this month vs last month') overlap with sibling trend-analysis skills and the description does not state what distinguishes this skill from them.	4 / 5
	Total	15 / 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: Cloudzero/cloudzero-claude-marketplace
Path: plugins/cost-analyst/skills/cost-comparison/SKILL.md
Commit: f539a8b

Reviewed: 12 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.