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

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/custom-dimension-analysis/SKILL.md

Quality

Content

56%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 body delivers strong operational guidance — a well-sequenced 9-step procedure with concrete, copy-paste-ready API calls and a useful critical rule about computing all math in code. It is significantly undermined by token bloat: a ~230-line placeholder output template, duplicated multi-dimensional-analysis content, and three overlapping advisory sections that should be condensed or moved into reference files.

Suggestions

Move the 11-section Output Format template into a references/output-templates.md file and keep only a short skeleton plus one fully worked example inline — this addresses both the conciseness and progressive_disclosure anchors.

Delete or merge the redundant 'Advanced Techniques' multi-dimensional example (it repeats Step 7's group_by call) and consolidate 'Skill-Specific Best Practices', 'Tips for Effective Analysis', and 'Common Custom Dimension Patterns' into one brief section.

Add explicit validation checkpoints to the workflow (e.g., verify the dimension exists in Step 2's values before querying, sanity-check that allocated + unallocated equals total in Step 8) and surface the error-handling reference at the relevant steps rather than only in 'See Also'.

Dimension	Reasoning	Score
Conciseness	The ~570-line body is noticeably verbose: the 'Output Format' section alone spans roughly 230 lines of placeholder tables ('$X,XXX', '[Value A]'), 'Advanced Techniques' repeats Step 7's multi-dimensional analysis, and the Tips/Best Practices/Patterns sections restate the same guidance in three forms. This fits the 2 anchor (several padded sections) better than 3, since the padding is substantial rather than incidental trimming.	2 / 5
Actionability	Guidance is highly concrete with copy-paste-ready tool calls (e.g., get_cost_data(group_by=["User:Defined:Team"], cost_type="real_cost", limit=50)) and a real Python snippet for unallocated-cost math. It stops short of the 5 anchor because the Step 8 Python uses '...' placeholders for inputs and some sections (Step 9, Patterns) give only questions to consider rather than executable commands.	4 / 5
Workflow Clarity	Steps 1-9 are explicitly and coherently sequenced, with a prerequisites section handling the dependency on the org-context skill and intermediate review points ('Review values to understand...'). It misses the 5 anchor because there are no validation or error-recovery checkpoints (empty results, missing dimension, allocation sanity checks are deferred entirely to a referenced error-handling file).	4 / 5
Progressive Disclosure	The body has clear section structure and a 'See Also' list of one-level-deep plugin references (best-practices, tools, error-handling, dimensions, cost-types), but those references are only surfaced at the very end, and a large block of content that clearly belongs in a separate reference file — the ~230-line output-format template — is inlined in SKILL.md. No bundle files (references/, scripts/, assets/) ship with this skill, so all detail must live in this one file. This fits the 3 anchor (structure present, but content that should be separate is inline).	3 / 5
	Total	13 / 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 description with an explicit and well-phrased 'Use when...' trigger clause and good natural keyword coverage for business-aligned cost analysis. Its main weakness is that the capability statement is thin — it says 'analyzing costs' without naming the concrete analyses the skill actually performs.

Suggestions

State concrete capabilities alongside the trigger, e.g., 'Breaks down cloud costs by custom dimensions (teams, products, business units), analyzes trends and service mix per dimension value, and produces showback/chargeback reports. Use when...' — this would raise specificity and completeness.

Add common user phrasings as triggers, such as 'cost per team', 'product P&L', or 'cost allocation', to widen trigger-term coverage to the 5 anchor.

Dimension	Reasoning	Score
Specificity	The description names the domain ('analyzing costs by organization-specific dimensions') with a single concrete action, and 'for showback, chargeback, or business-aligned cost reporting' states purposes rather than actions. It matches the anchor of naming the domain with 1-2 concrete actions but not comprehensive coverage, and does not list several specific actions (breakdowns, trend analysis, service-mix comparison) that would justify a 4.	3 / 5
Completeness	It explicitly answers 'when' with a concrete 'Use when analyzing costs by...' clause listing concrete trigger phrases, and the 'what' ('analyzing costs by organization-specific dimensions') is present but thin and embedded in the when-clause. This fits the 4 anchor (both present, one could be more explicit) rather than 5, which requires a clearly separate, concrete statement of what the skill does.	4 / 5
Trigger Term Quality	Natural terms users would say are well covered: 'teams, products, business units, or applications' plus 'showback, chargeback'. It falls short of the 5 anchor because common variations and synonyms are missing (e.g., 'cost per team', 'cost allocation', 'P&L', 'by [team name]').	4 / 5
Distinctiveness Conflict Risk	'organization-specific dimensions', 'showback', and 'chargeback' establish a clear niche with distinct triggers. Minor overlap risk remains with sibling cloud-cost-analysis skills in the same plugin (the body itself references a general best-practices reference and an org-context skill), so it does not reach the 5 anchor's minimal conflict risk.	4 / 5
	Total	15 / 20 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: 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.