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

66%

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

63%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 content is highly actionable with concrete, well-parameterized tool calls and a clear multi-step workflow, but it is lengthy and repeats optimization guidance across several sections while inlining content that would benefit from being split into reference files.

Suggestions

De-duplicate the service-specific optimization guidance that currently appears in Step 8, Output section 8, and the Service-Specific Analysis Guides — keep one canonical version and reference it.

Move the 11-section output template and the service-specific analysis guides into a dedicated reference file and link to them from SKILL.md to cut the body length substantially.

Trim the 'Tips for Effective Analysis' and 'Skill-Specific Best Practices' sections, which restate guidance already implied by the workflow and output format.

Dimension	Reasoning	Score
Conciseness	The ~560-line body is mostly efficient in its API code blocks, but optimization guidance is duplicated across Step 8, Output section 8, and the Service-Specific Analysis Guides, and the large placeholder output template plus 'Tips'/'Advanced Techniques' sections restate points Claude already knows.	3 / 5
Actionability	Concrete, copy-pasteable get_cost_data/get_available_dimensions/get_dimension_values calls with explicit filter, group_by, and limit parameters throughout, plus an executable Python savings-rate snippet; held below 5 only because calls use [service_name] placeholders and several steps are conditional discovery ('if available').	4 / 5
Workflow Clarity	A clear 9-step sequence from service identification through cost-type comparison with per-step intent, and the skill is read-only so the destructive/batch validation cap does not apply; minor gap is the absence of explicit validation checkpoints or error-recovery loops, though these are not critical for read-only API calls.	4 / 5
Progressive Disclosure	Five one-level-deep external references are clearly signaled in a See Also section, but no local bundle files exist and large blocks that could be split out (the 11-section output template, service-specific analysis guides, advanced techniques) are inlined in the ~560-line SKILL.md.	3 / 5
	Total	14 / 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.

The description is clear, third-person, and explicitly pairs a 'what' with a 'Use when' trigger while naming concrete services. It is solid but not exemplary: action coverage and trigger-phrase variety are good rather than comprehensive.

Suggestions

Add 2-3 more concrete actions (e.g., 'attribute costs by account, region, and tag') to lift specificity toward comprehensive coverage.

Expand the when clause with natural trigger phrasings users actually say (e.g., 'Use when the user asks to deep dive into EC2 spending or wants to know why a service is expensive').

Include synonyms and variations (e.g., 'cost breakdown', 'spend analysis', 'optimize [service] costs') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('a specific cloud service's costs') and two concrete actions ('detailed breakdown', 'find optimization opportunities'), but coverage of actions is not comprehensive — only ~2 named actions rather than several.	3 / 5
Completeness	Explicitly answers both what ('detailed breakdown of a specific cloud service's costs') and when ('Use when you need a detailed breakdown...'), but the when clause names the scenario once rather than offering multiple concrete trigger phrases.	4 / 5
Trigger Term Quality	Concrete service names a user would naturally say ('EC2, RDS, S3, Lambda, etc.') give good keyword coverage, though common natural phrasings like 'why is X so expensive' or 'deep dive' live in the body rather than the description.	4 / 5
Distinctiveness Conflict Risk	Scoped to a single specific service's costs with named services, giving a clear niche distinct from general org-level cost analysis; minor overlap risk with closely related cost-analysis skills keeps it just below 5.	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 (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: 62c27f3

Reviewed: 1 day 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.