Name: cost-projection
Rating: 60.8 (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

76%

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

67%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.

A well-structured, highly actionable seven-phase workflow with strong sequencing, fallbacks, and a stop condition. Main deductions are for inline time-sensitive pricing data, some duplicated guidance, and heavy inline detail that belongs in the (currently absent) reference files.

Suggestions

Move the fallback pricing formula table and dated figures out of SKILL.md into a reference file (e.g. pricing-estimates.md) so stale numbers don't occupy context, keeping only the lookup strategy and confidence levels inline.

Extract the full Phase 7 report template and per-framework parsing details into the output-examples and parsing reference files, leaving SKILL.md a lean overview of the seven phases.

Add explicit validation checkpoints between phases (e.g. confirm the resource inventory is non-empty and every CZ:Service dimension value resolved before querying) to strengthen the workflow's error-recovery loops.

Dimension	Reasoning	Score
Conciseness	Mostly procedural and appropriately assumes IaC knowledge, but it inlines time-sensitive pricing figures ('$0.04048' Fargate, '~$33/mo' NAT Gateway, '$0.20/million invocations', a '2024' search example) that the rubric penalizes outside a deprecated section, and repeats cost assumptions in both Phase 5 notes and the report template. Could be tightened per anchor 3 rather than trimmed-minor-gaps anchor 4.	3 / 5
Actionability	Highly concrete throughout — copy-paste find/grep commands, explicit WebSearch/WebFetch query strings, exact get_cost_data parameters (group_by, granularity, cost_type, 30-day range), a numeric estimation formula table, and a full report template. Minor gaps keep it at 4: MCP tool-call syntax is delegated to a reference and instructions like 'trace the stack definitions' are underspecified.	4 / 5
Workflow Clarity	Seven clearly sequenced phases each with an explicit Goal, a hard stop condition ('If absolutely nothing infrastructure-related is found → ... stop'), fallback behavior ('If CloudZero queries fail, still provide configuration-based estimates'), and user-escalation for unresolved variables. Not 5 because there are no explicit validate-then-proceed checkpoints or retry loops, though the read-only nature of the analysis means the destructive-cap does not apply.	4 / 5
Progressive Disclosure	References are one level deep and well signaled — cited in-phase ('Read the service mapping reference') plus a See Also index with one-line descriptions. However, no bundle files exist in this skill's directory (references/, scripts/, assets/ are absent), and reference-weight content such as per-framework parsing details, the pricing table, and the full output template is inlined in a ~440-line body that could be split out.	4 / 5
	Total	15 / 20 Passed

Description

75%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 specific, well-voiced description with strong action coverage and distinct triggers, undermined only by the complete absence of an explicit 'when to use' clause and some missing natural synonyms ('estimate', 'pricing'). Adding a Use-when clause would likely lift completeness and trigger quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks what infrastructure will cost, wants a cost estimate before deploying, or is comparing architecture options by price.'

Include natural user phrasings and synonyms such as 'estimate', 'pricing', 'budget', and 'how much' in the trigger language.

Mention 'before deploying' or 'design review' contexts so the pre-deployment use case is discoverable from the description alone.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Project the monthly cost', 'Reads IaC files, enumerates resources, and produces a line-item cost breakdown' — with named inputs (Terraform, CDK, CloudFormation, SAM), data source (CloudZero spend data), and output format (line-item breakdown). Uses third person throughout; no padding or buzzwords.	5 / 5
Completeness	Clearly answers 'what' (project monthly cost of IaC via CloudZero) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Good natural keyword coverage — 'monthly cost', 'Terraform', 'CDK', 'CloudFormation', 'SAM', 'spend', 'cost breakdown' — but misses common user synonyms like 'estimate', 'pricing', 'how much', or 'budget'. Fits anchor 4 (good coverage, a few natural terms missing) rather than 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche — IaC cost projection with four named frameworks and a specific data platform — with distinct trigger terms; minimal conflict risk with other skills.	5 / 5
	Total	17 / 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-projection/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.