Name: custom-dimension-analysis
Rating: 64.8 (1 reviews)
Author: Cloudzero

custom-dimension-analysis

Use when analyzing costs by organization-specific dimensions like teams, products, business units, or applications for showback, chargeback, or business-aligned cost reporting

Quality

78%

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/custom-dimension-analysis/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.

The body is highly actionable with concrete API calls and a strong math-in-code guardrail, but it is overlong and monolithic: a large placeholder output-template section and generic tips pad the token budget, and the cited reference files are absent from the bundle.

Suggestions

Move the 230-line "Output Format" placeholder templates and the "Common Custom Dimension Patterns" / "Tips" sections into a separate reference file, keeping SKILL.md as a lean overview that links out.

Add the missing referenced files to the bundle (best-practices.md, cloudzero-tools-reference.md, error-handling.md, dimensions-reference.md, cost-types-reference.md) or remove the citations so signaled references resolve to real content.

Tighten conciseness by replacing generic advice ("Tell a story", "Make it actionable") with concrete guidance, and add an explicit validate→fix→retry note for steps where API calls can return empty or partial data.

Dimension	Reasoning	Score
Conciseness	The actionable core (API calls, the math-in-code rule) is lean and avoids explaining concepts Claude already knows, but the ~564-line body is padded with a 230-line placeholder "Output Format" template section plus generic "Tips" and "Best Practices" lists that could be tightened or moved to references.	2 / 3
Actionability	It provides concrete, executable tool calls with real parameters (e.g. `get_cost_data(group_by=["User:Defined:Team"], cost_type="real_cost", limit=50)`) and a complete copy-paste-ready Python snippet for unallocated-cost math, matching the anchor for fully executable guidance.	3 / 3
Workflow Clarity	The nine steps are clearly sequenced with a concrete API call per step and a global "All Math In Code" guardrail, but validation checkpoints are implicit rather than per-step and there is no validate→fix→retry feedback loop for the API queries.	2 / 3
Progressive Disclosure	The five referenced `${CLAUDE_PLUGIN_ROOT}/references/*.md` files are clearly signaled in a "See Also" section and are one level deep, but none of them exist in the actual bundle and the SKILL.md itself is monolithic — output templates, patterns, and tips that should be split out are all inline.	2 / 3
	Total	9 / 12 Passed

Description

92%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 well-crafted: it uses third person, leads with an explicit "Use when" trigger, and names concrete dimensions and reporting use-cases. Its only real weakness is some overlap risk with adjacent cost-analysis skills in the same plugin family.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete dimension types ("teams, products, business units, or applications") and concrete reporting purposes ("showback, chargeback, or business-aligned cost reporting"), matching the anchor for listing multiple specific concrete actions rather than naming only a domain and some actions.	3 / 3
Completeness	It opens with an explicit "Use when analyzing..." clause that states both what the skill does and when to invoke it, satisfying the anchor requiring clear answers to both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	It surfaces natural terms a user would actually say — "teams", "products", "business units", "applications", "showback", "chargeback" — giving good coverage comparable to the anchor's varied-term example, though it omits common phrasings like "costs by team" or "break down" that the body's "When to Use" section captures.	3 / 3
Distinctiveness Conflict Risk	The "organization-specific dimensions" / showback-chargeback niche is reasonably specific, but "analyzing costs by dimensions" overlaps with sibling CloudZero cost-analysis skills in the same plugin family, so it could still trigger for a related skill rather than having a fully conflict-free niche.	2 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (572 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Cloudzero/cloudzero-claude-marketplace
Path: plugins/cost-analyst/skills/custom-dimension-analysis/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.