CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-advisor-cost-optimization

Analyze Azure Advisor Cost/IdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: "find unused Azure resources", "what resources am I paying for but no longer using", "idle-resource savings", "historical idle-resource savings", "are these idle resources safe to delete". Generic Cost, other subcategories, and cross-category requests use azure-advisor.

Quality

87%

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

The canonical home for this skill is azure-advisor-cost-optimization in microsoft/GitHub-Copilot-for-Azure

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.

An exemplary orchestration-style SKILL.md body: token-efficient domain rules, concrete parameter and formatting constraints, and a clean one-level-deep reference structure with a flow-to-file routing table. The only weaknesses are that per-flow executable detail and step-level validation checkpoints are delegated to references rather than stated inline.

DimensionReasoningScore

Conciseness

The body is ~46 lines of dense, domain-specific imperative rules ("Never annualize, reconstruct amounts from dates", "Missing amounts are Unavailable, not zero") with no padding and no explanation of concepts Claude already knows. Every token earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

Concrete constraints are present ("category=Cost and sub-category=IdleResources", "Pricing basis: <basis>", "If a required file is unavailable, report it and stop the affected flow") giving mostly executable guidance for an instruction-only skill. It stops short of 5 because the actual execution details for each flow are deferred to references rather than specified inline, leaving minor gaps.

4 / 5

Workflow Clarity

A clear sequence is present (read matching references before each flow, read scope-resolution before scoped calls, apply scenario guidance) with an explicit failure checkpoint ("report it and stop the affected flow") and a visible-results gate ("Visibly show results/proposals before dependent questions"). The destructive-operation cap does not apply because the skill is explicitly read-only with deletion-safety prevalidation built in as a core flow, but per-flow step detail lives in references, leaving minor validation gaps versus the anchor for 5.

4 / 5

Progressive Disclosure

The body is a lean overview with a Quick reference table mapping each flow to a specific file; all ten referenced files exist in references/, the anchor link (#read-only-prevalidation) resolves to a real heading, and references are one level deep (siblings plus a README index pointing back to SKILL.md). This matches the anchor for clear overview with well-signaled one-level-deep references.

5 / 5

Total

18

/

20

Passed

Description

82%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 with explicit dual-action capability statement, literal user-voice trigger phrases, and explicit routing boundaries against a sibling skill. The main gap is breadth of concrete capability coverage (only two actions named) and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

"Analyze Azure Advisor Cost/IdleResources findings and prevalidate deletion safety, including Service Groups" names the domain and exactly two concrete actions, matching the anchor for 1-2 actions that is not comprehensive. It does not reach 4 because the description does not enumerate additional specific actions (e.g., savings reporting, table formatting, lifecycle reports) that the body shows the skill performs.

3 / 5

Completeness

It explicitly answers both what ("Analyze Azure Advisor Cost/IdleResources findings and prevalidate deletion safety") and when (a literal WHEN: clause with concrete trigger phrases), matching the anchor for clearly and explicitly answering both. The routing boundary to azure-advisor further strengthens the when-guidance rather than weakening it.

5 / 5

Trigger Term Quality

The WHEN clause quotes five natural user utterances ("find unused Azure resources", "what resources am I paying for but no longer using", "idle-resource savings", "historical idle-resource savings", "are these idle resources safe to delete") giving good keyword coverage across discovery, savings, and safety intents. It falls short of 5 because common variations like "reduce Azure spend", "Azure waste", or "clean up unused resources" are absent.

4 / 5

Distinctiveness Conflict Risk

The niche is tightly scoped to Azure Advisor Cost/IdleResources findings, and the closing sentence ("Generic Cost, other subcategories, and cross-category requests use azure-advisor") explicitly disambiguates against the sibling skill. Clear niche with distinct triggers and minimal conflict risk, matching the anchor for 5.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

microsoft/azure-skills

Path

.github/plugins/azure-advisor/skills/azure-advisor-cost-optimization/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.