Name: cost-comparison
Rating: 59.2 (1 reviews)
Author: Cloudzero

cost-comparison

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

Quality

69%

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

71%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 content is highly actionable with executable API examples and concrete formulas inside a clearly sequenced workflow, but it is noticeably verbose due to redundant scenario/advanced/tips sections and does not fully leverage progressive disclosure since the referenced files are absent from the bundle and much detailed material is inlined.

Suggestions

Move the Common Comparison Scenarios, Advanced Techniques, and detailed output-format templates into separate reference files linked from the body to cut redundancy and shrink SKILL.md toward a lean overview.

Add an explicit validation checkpoint (e.g., confirm both comparison groups returned comparable dimensions and no group is empty) before computing differences in Step 3.

Ensure the referenced references/*.md files (best-practices, cloudzero-tools-reference, error-handling, dimensions-reference, cost-types-reference) actually ship in the bundle, or inline only what is essential and drop dead references.

Dimension	Reasoning	Score
Conciseness	The ~440-line body is mostly efficient and avoids explaining concepts Claude already knows, but the Common Comparison Scenarios, Advanced Techniques, Best Practices, and Tips sections substantially restate ideas already covered in the 7-step workflow and output format, creating noticeable redundancy.	3 / 5
Actionability	It provides copy-paste-ready get_cost_data(...) calls with real filters and group_by parameters, concrete formulas for absolute/percentage differences and ratios, and specific variance thresholds (>50%, 20-50%, <20%), fully covering the common comparison cases.	5 / 5
Workflow Clarity	A clear 7-step sequence (identify, query, calculate, categorize, drill down, normalize, find patterns) is paired with the strong 'All Math In Code' guardrail, but there is no explicit validation checkpoint confirming comparable data before computing differences; because the operations are read-only rather than destructive, this stays at 4 rather than the batch-cap of 3.	4 / 5
Progressive Disclosure	Section headers and a 'See Also' block with one-level-deep references exist, but a large volume of content that belongs in separate files (five scenarios, advanced techniques, detailed output templates) is inlined, and the referenced references/*.md files are not present in the bundle to verify.	3 / 5
	Total	15 / 20 Passed

Description

67%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 is specific and clearly answers both what the skill does and when to use it, with a well-scoped comparison niche. Its main weakness is that natural user-facing trigger terms live in the body rather than the description, and the concrete actions are implied rather than enumerated.

Suggestions

Add the natural trigger phrases users say ('compare', 'vs', 'versus', 'difference', 'benchmark') directly into the description so it triggers reliably without relying on the body's When-to-Use list.

State the concrete actions the skill performs (e.g., 'compute absolute and percentage differences, normalize for scale, and drill into drivers') rather than only naming the comparison targets.

Tighten the what/when split so the capabilities read as a distinct action list before the 'Use when' clause.

Dimension	Reasoning	Score
Specificity	The description enumerates several concrete comparison dimensions ('time periods, environments, accounts, regions, or teams') and two outcomes ('understand spending differences and identify inefficiencies'), but lists comparison targets rather than the concrete computational actions performed, leaving minor coverage gaps.	4 / 5
Completeness	Both 'what' (side-by-side cost comparisons to identify variations/inefficiencies) and an explicit 'Use when' clause with concrete trigger contexts are present, but the 'what' is not separated as a crisp list of concrete actions so it does not fully reach the level-5 anchor.	4 / 5
Trigger Term Quality	It contains some relevant keywords ('comparing costs', 'spending differences', 'inefficiencies') but omits the natural trigger terms a user would say (compare, vs, versus, difference, benchmark) that only appear in the body's 'When to Use' section, not in the description itself.	3 / 5
Distinctiveness Conflict Risk	The cost-comparison/benchmarking niche is clearly distinct, but because it sits within a family of related cloud-cost skills (it explicitly builds on understand-cloudzero-organization) there is minor overlap risk with closely related skills.	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: 62c27f3

Reviewed: 1 day 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.