Name: cost-spike-investigation
Rating: 63.2 (1 reviews)
Author: Cloudzero

cost-spike-investigation

Use when a cost spike or unexpected increase has already been identified and you need to find which service, account, or resource is responsible

Quality

75%

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-spike-investigation/SKILL.md

Quality

Content

65%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.

Highly actionable with concrete API calls and a clear step sequence, but weakened by redundant explanatory content and missing validation checkpoints plus absent bundle reference files.

Suggestions

Add explicit validation/verification checkpoints (e.g., confirm baseline and spike periods are equal length, sanity-check that summed group_by costs reconcile to the top-level total) between steps.

Trim 'Common Spike Patterns' and 'Skill-Specific Best Practices' to essentials or move them into a reference file, since they restate knowledge Claude already has.

Provide the referenced references/*.md files (best-practices, cloudzero-tools-reference, error-handling, dimensions-reference, cost-types-reference) so the See Also links resolve to real bundle content.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete query blocks, but sections like 'Common Spike Patterns' and best-practice prose restate concepts Claude already knows and could be trimmed.	2 / 3
Actionability	Provides concrete, copy-paste-ready get_cost_data / get_dimension_values / get_available_dimensions calls with real parameters plus a defined output report structure, matching the executable-code anchor.	3 / 3
Workflow Clarity	A clear seven-step sequence is present with comparison logic and an all-math-in-code guardrail, but there are no explicit validation or verify-then-proceed checkpoints.	2 / 3
Progressive Disclosure	Sections are well labeled with one-level-deep See Also references, but the referenced references/*.md files are not present in the bundle and some inline content (output format, spike patterns) could be externalized.	2 / 3
	Total	9 / 12 Passed

Description

85%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.

A strong description with an explicit trigger clause, concrete goal, and distinct niche; the only weakness is narrow trigger-term coverage that misses common user phrasings.

Dimension	Reasoning	Score
Specificity	States a concrete trigger ('cost spike or unexpected increase has already been identified') and a concrete goal with named dimensions ('find which service, account, or resource is responsible'), matching the multiple-specific-actions anchor.	3 / 3
Completeness	An explicit 'Use when...' clause states both what (attribute the spike to a service/account/resource) and when (a spike has already been identified), clearly answering both what and when.	3 / 3
Trigger Term Quality	Includes natural terms ('cost spike', 'unexpected increase') but lacks common variations like 'bill too high', 'spending anomaly', or 'why did costs go up', so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	Scoped narrowly to post-identification root-cause attribution of cloud cost spikes, a distinct niche with triggers unlikely to fire for general cost-analysis skills.	3 / 3
	Total	11 / 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-spike-investigation/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.