# 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.

- Skill: `microsoft/azure-advisor-cost-optimization` (Agent Skill, multi-file: 11 files)
- Install (CLI): `npx get-skill add microsoft/azure-advisor-cost-optimization`
- Raw SKILL.md: https://api.skillmd.com/api/skills/microsoft/azure-advisor-cost-optimization/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- License: MIT
- Author: Microsoft (https://skillmd.com/u/microsoft), verified publisher
- Updated: 2026-11-11
- Page: https://skillmd.com/skills/microsoft/azure-advisor-cost-optimization

---


# Azure Advisor Cost Optimization

Use existing Advisor tools only with `category=Cost` and `sub-category=IdleResources`.
Never substitute billing, inventory or runtime KQL. Preserve selected scope, type and tenant;
pass supplied identities unchanged.

## Shared rules

Use only returned structured retail savings; MCP owns calculations. Never annualize,
reconstruct amounts from dates, or fall back to legacy annualSavingsAmount/savingsAmount
or raw pricing. Cost is accumulated Advisor cost, not monthly spend or yearly savings.
Completed reports use Realized savings.
Every monetary answer or proposal visibly shows Currency and `Pricing basis: <basis>`
from the calculated measure or its documented source. Missing amounts are Unavailable,
not zero; numeric zero stays zero. Preserve a known basis even when amounts are missing.
Potential savings depend on validating and deleting eligible resources. Estimates do not
establish inactivity or safe deletion and never authorize remediation.

## Workflow

Before each flow, read its matching references below, including when using supplied results.
Before scoped calls, read [Scope resolution](references/scope-resolution.md).
Reuse already loaded references.
If a required file is unavailable, report it and stop the affected flow.

Use the matching scenario guidance; [Reference index](references/README.md).

## Quick reference

| Flow | Required reference |
|---|---|
| Discovery and type expansion | [Workflow](references/workflow.md) |
| Counts, savings field mapping and pricing-source interpretation | [Output and savings](references/output-and-savings.md) |
| Tables and selected resources | [Table format](references/table-format.md) |
| Completed/historical reports | [Lifecycle](references/lifecycle.md) |
| State changes | [State updates](references/state-updates.md) |
| Selection/remediation handoff | [Selection](references/selection-and-handoff.md) |
| Explicit prevalidation/safety checks | [Selection](references/selection-and-handoff.md#read-only-prevalidation) |
| Filters/errors | [Tools and recovery](references/tools-and-recovery.md) |
| Routing examples | [Examples](references/examples.md) |

## Response guidance

Use shared headings and column order across models, with documented scope/lifecycle variations.
Visibly show results/proposals before dependent questions; reasoning, tool output or text
inside `ask_user` does not count. Ask directly for missing input.

