service-cost-deep-dive

Use when you need a detailed breakdown of a specific cloud service's costs — EC2, RDS, S3, Lambda, etc. — to understand usage patterns and find optimization opportunities

Quality

77%

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/service-cost-deep-dive/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.

Highly actionable with concrete API examples and a clear step sequence, but weakened by redundancy across service-specific sections, a verbose placeholder output template, and a monolithic body that should offload detail to the reference files it already cites.

Suggestions

Consolidate the three repeated service-specific sections (Step 8, Output Format section 8, and Service-Specific Analysis Guides) into a single reference file to remove redundancy.

Move the large placeholder output template into a separate output-format reference, keeping SKILL.md as a lean overview that links to it.

Add explicit validation checkpoints to the workflow, e.g. 'Confirm the service FQDID resolved to exactly one match before continuing' and 'If a query returns no rows, verify the filter values and retry'.

Dimension	Reasoning	Score
Conciseness	Mostly actionable with no basic-concept padding, but ~550 lines with service-specific guidance repeated in three places (Step 8, Output Format section 8, and Service-Specific Analysis Guides) and a large placeholder output template ('$X,XXX', 'XX%', '[Details]') that could be tightened.	2 / 3
Actionability	Provides many concrete, copy-paste-ready API calls with specific parameters (filters, group_by, limit, granularity, cost_type) plus an executable Python savings-rate snippet; the only placeholders are the variable service name, which is justified.	3 / 3
Workflow Clarity	A clear 9-step numbered sequence with conditional 'if available' discovery logic, but no explicit validation checkpoints or error-recovery feedback loops (e.g., confirming the FQDID matched, handling empty results) for a complex multi-step process.	2 / 3
Progressive Disclosure	References are well-signaled and one-level-deep in a 'See Also' section, but no bundle files exist locally and the body itself is a monolith — the ~170-line output template and service-specific guides are inline content that should be split into reference files.	2 / 3
	Total	9 / 12 Passed

Description

90%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 strong description with an explicit 'Use when' trigger, named service triggers, and a clear niche. Its only weakness is that the action verbs lean slightly goal-oriented rather than enumerating concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain ('detailed breakdown of a specific cloud service's costs') and a few actions ('understand usage patterns', 'find optimization opportunities'), but these skew toward goals rather than the concrete multi-action listing of a 3 like 'extract, fill, merge'.	2 / 3
Completeness	Opens with an explicit 'Use when you need a detailed breakdown...' trigger and states what it does (break down service costs to understand usage and find optimization opportunities), clearly answering both what and when.	3 / 3
Trigger Term Quality	Includes natural terms users would actually say — named services 'EC2, RDS, S3, Lambda, etc.' plus 'costs', 'breakdown', 'optimization opportunities' — giving good coverage beyond a single generic phrase.	3 / 3
Distinctiveness Conflict Risk	The 'specific cloud service' framing with named services carves a clear niche (service-level cost deep dives) that is unlikely to fire for unrelated skills.	3 / 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 (561 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/service-cost-deep-dive/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.