CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloud-finops

Use for any cloud cost question on AWS, Azure or Google Cloud - a bill that jumped or one service that spiked (NAT gateway, egress, storage), cost anomaly alert thresholds, untagged or unallocated spend and tag cleanup for showback or chargeback, Savings Plans, Reserved Instances or committed use discounts (utilization, coverage, unused commitment, effective savings rate, whether to buy more), or whether cost per order or per customer got worse. Reads a FOCUS billing export with stdlib scripts.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, executable read-only analysis skill: real commands with flags, typed exit codes as checkpoints, refusal guards, and a verified one-level reference bundle. The only deductions are a time-sensitive verification date in the overview and the absence of a written error-recovery loop for the documented exit codes.

Suggestions

Move the 'Definitions verified 2026-11-17' date and FOCUS v1.4 version out of the overview (or into a versioning/deprecations note) so the body is not time-sensitive.

Add one line of error-recovery guidance for exit code 3 (e.g., 'exit 3: re-check the export is FOCUS 1.x CSV with required columns, then re-run') to close the workflow feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and command-first with no padding ('python scripts/allocation_check.py --input focus.csv --required-tags team,env,cost-center'), but the time-sensitive line '**Definitions verified 2026-11-17** against FOCUS v1.4' and a short framing sentence about what FOCUS is keep it below the leanest anchor.

4 / 5

Actionability

Every workflow step is a copy-paste executable command with concrete flags, the scripts table documents typed exit codes (0/2/3) and '--help, --sample and --output json', and a real 14-day sample CSV ships in assets. Coverage spans all three common cases (allocation, commitments, anomalies).

5 / 5

Workflow Clarity

The three steps are clearly sequenced with per-step explanation of what each reports, and validation checkpoints are explicit (exit codes '0 at target · 2 findings · 3 bad input', 'Under 14 days it refuses'). It falls between anchors because no explicit error-recovery loop (e.g., what to do on exit 3) is written out.

4 / 5

Progressive Disclosure

The body is a concise overview pointing to one-level-deep, well-signaled references; all five referenced bundle files (3 references .md, example CSV, review template) and all four scripts exist on disk and each is described in one line. This matches the clear-overview anchor exactly.

5 / 5

Total

18

/

20

Passed

Description

96%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 strong description: explicit 'Use for' trigger guidance, comprehensive concrete capabilities, and cross-provider synonym coverage. The only weakness is the broad 'any cloud cost question' framing, which slightly raises conflict risk against adjacent cost and architecture skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'a bill that jumped or one service that spiked (NAT gateway, egress, storage)', 'untagged or unallocated spend and tag cleanup for showback or chargeback', 'utilization, coverage, unused commitment, effective savings rate, whether to buy more', 'cost per order or per customer' — plus the mechanism ('Reads a FOCUS billing export with stdlib scripts'). Coverage spans allocation, commitments, anomalies and unit economics with no gaps, so it fits the comprehensive anchor rather than the minor-gaps anchor.

5 / 5

Completeness

It explicitly answers 'when' with 'Use for any cloud cost question on AWS, Azure or Google Cloud' followed by concrete trigger scenarios, and 'what' with 'Reads a FOCUS billing export with stdlib scripts'. The 'when' clause is explicit and maximally specific, matching the anchor requiring both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrasings are covered comprehensively with synonyms: 'bill that jumped', 'spike', 'untagged', 'Savings Plans, Reserved Instances or committed use discounts' (the three provider-specific names for the same thing), 'effective savings rate', 'cost per order'. It includes both lay terms and the jargon a FinOps practitioner would actually say.

5 / 5

Distinctiveness Conflict Risk

The niche (cloud billing-export analysis: tags, commitments, anomalies, unit cost) is clearly distinct, but the opening claim 'any cloud cost question on AWS, Azure or Google Cloud' is broad and could overlap with cost-optimization or architecture skills. It is mostly distinct with minor overlap risk rather than minimal, so it sits one notch below the clear-niche anchor.

4 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

alirezarezvani/claude-skills

Path

engineering/cloud-finops/skills/cloud-finops/SKILL.md

Reviewed

Table of Contents

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.