Name: cost-projection
Rating: 66.4 (1 reviews)
Author: Cloudzero

cost-projection

Project the monthly cost of an infrastructure definition (Terraform, CDK, CloudFormation, SAM) using CloudZero spend data. Reads IaC files, enumerates resources, and produces a line-item cost breakdown.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/cost-analyst/skills/cost-projection/SKILL.md

Quality

Content

77%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.

A thorough, highly actionable 7-phase workflow with clear sequencing and validation checkpoints, slightly held back by inline time-sensitive pricing detail and references to bundle files that are absent from the provided bundle. Tightening the pricing material and shipping the referenced files would raise the two weakest dimensions.

Suggestions

Ship the seven referenced files under references/ (or remove the references) so the body's navigation points to real bundle files; verify each ${CLAUDE_PLUGIN_ROOT}/references/*.md path resolves.

Move the Strategy 3 estimation-formula table with specific dollar figures into a reference file (e.g. pricing-reference.md) marked as time-sensitive, keeping only the strategy ordering and confidence levels inline.

Tighten Phase 1 auto-discover by collapsing the five explanatory steps into a concise checklist with the find/grep commands, dropping prose that restates what Claude can infer.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and domain-specific, but the inline estimation-formula table embeds time-sensitive dollar figures (e.g. "$0.04048", "~$30/mo") that the rubric flags as a conciseness penalty when not isolated in a deprecated/reference section, and some Phase 1 scaffolding ("Some projects define infrastructure inline...") restates context Claude can infer.	2 / 3
Actionability	It supplies copy-paste-ready shell commands (find/grep), concrete WebSearch/WebFetch examples, parameterized CloudZero tool call specs given as explicit parameter lists, and a full report template — concrete and executable rather than abstract.	3 / 3
Workflow Clarity	A clearly sequenced 7-phase workflow with per-phase goals and explicit checkpoints: "stop" when nothing is found, confirming dimension values via get_dimension_values, existing-vs-new classification, confidence levels, and a fallback when CloudZero queries fail; the operations are read-only analysis so the destructive-batch feedback-loop cap does not apply.	3 / 3
Progressive Disclosure	The body signals one-level-deep references and a See Also section, but the referenced files (service-mapping.md, dimensions-reference.md, best-practices.md, cost-projection-output-examples.md, cloudzero-tools-reference.md, cost-types-reference.md, error-handling.md) are not present in the bundle's references/ directory, and the time-sensitive pricing table is inline content that should live in a reference file; not a 1 because the SKILL.md is well-structured with clearly signaled references rather than a monolithic wall.	2 / 3
	Total	10 / 12 Passed

Description

82%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 specific, third-person description with strong trigger terms and a clear niche, but it states only what the skill does without an explicit when-to-use clause. Adding trigger guidance would lift the weakest dimension.

Suggestions

Append an explicit trigger clause, e.g. "Use when estimating or projecting the monthly cost of Terraform, CDK, CloudFormation, or SAM infrastructure, or when the user asks how much a stack will cost to run."

Add common user phrasings like "estimate", "price", or "budget" alongside "project" to broaden natural trigger coverage.

Consider noting the CloudZero MCP prerequisite in the description so the skill is not invoked in environments lacking it.

Dimension	Reasoning	Score
Specificity	"Project the monthly cost... Reads IaC files, enumerates resources, and produces a line-item cost breakdown" lists multiple concrete actions (project, read, enumerate, produce) tied to a specific domain, matching the multi-action anchor rather than the single-action score-2 example.	3 / 3
Completeness	It clearly answers WHAT the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 2 even though the what-side is strong.	2 / 3
Trigger Term Quality	Names the exact terms a user would say — "Terraform, CDK, CloudFormation, SAM", "monthly cost", "CloudZero spend data", "IaC files" — giving good natural-language coverage rather than internal jargon.	3 / 3
Distinctiveness Conflict Risk	The CloudZero + multi-IaC cost-projection niche is distinctive and unlikely to trigger for unrelated skills; the binding to "CloudZero spend data" sharply reduces conflict risk.	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-projection/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.