Name: diff-cost-projection
Rating: 61.6 (1 reviews)
Author: Cloudzero

diff-cost-projection

Analyze code diffs for infrastructure cost impact using CloudZero spend data. Detects Terraform, CDK, CloudFormation, SAM, K8s, scaling, and application code changes that affect cloud spending.

Quality

72%

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/diff-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.

The skill is highly actionable with a clear, well-validated multi-phase workflow and concrete commands. Conciseness is moderate due to repetition and inline examples, and progressive disclosure is held back because the referenced bundle files are not present to verify the split.

Suggestions

Move the long inline examples (e.g. the Strategy A/B instance-type walkthrough and the output report template) into the referenced files to shorten the main SKILL.md.

De-duplicate the confidence-level and stop-condition guidance that recurs across phases into a single stated reference.

Ensure the referenced bundle files (cost-impact-taxonomy.md, service-mapping.md, output-examples.md, etc.) actually exist in the references/ directory so progressive disclosure resolves.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and task-focused, but at ~340 lines it repeats guidance (e.g. confidence levels, stop conditions) and embeds several long inline examples that could live in the referenced files, so it could be tightened.	2 / 3
Actionability	Provides concrete, executable git commands, specific CloudZero tool calls with parameters, and copy-paste-ready estimation formulas (e.g. 'hourly_price × 730', '(M/N - 1) × 100%').	3 / 3
Workflow Clarity	Seven phases are clearly sequenced with explicit early-exit/stop checkpoints at each phase (empty diff, all-skip files, no signals) and concrete validation guidance (cache org context, batch queries, handle no-data).	3 / 3
Progressive Disclosure	References are well-signaled via a 'See Also' list and inline ${CLAUDE_PLUGIN_ROOT}/references/*.md paths, but the bundle directories (references/, scripts/, assets/) do not exist in this review bundle, so the referenced files cannot be verified and the structure is not actually split as described.	2 / 3
	Total	10 / 12 Passed

Description

67%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 specific and distinctive, clearly naming concrete capabilities and a narrow niche. Its weakness is the absence of an explicit 'Use when...' trigger clause and natural user-facing trigger phrasing, which limits completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause covering natural user phrasings such as 'estimate the cost impact of my changes' or 'will this branch raise our cloud bill'.

Surface the trigger phrases already present in the body ('What's the cost impact of my changes?', 'Will this branch increase our cloud spend?') into the description so they can be matched at load time.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Analyze code diffs', 'Detects Terraform, CDK, CloudFormation, SAM, K8s, scaling, and application code changes') rather than vague language.	3 / 3
Completeness	It clearly answers what the skill does, but the 'when' is only implied by the domain — there is no explicit 'Use when...' guidance, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant terms like 'cost impact', 'code diffs', and 'cloud spending', but lacks the natural phrases a user would say (e.g. 'estimate cost', 'will this increase spend') and has no 'Use when...' trigger clause.	2 / 3
Distinctiveness Conflict Risk	The CloudZero/infrastructure-cost niche is highly specific with distinct triggers (named IaC tools + spend data), making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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/diff-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.