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.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 267
01 前言 Front Matter
- name
- azure-advisor-cost-optimization
- license
- MIT
- metadata
- { "author": "Microsoft", "version": "1.0.11" }
- description
- 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.
02 资源文件 10
- 参考文档references/examples.md3.7 KB
- 参考文档references/lifecycle.md4.1 KB
- 参考文档references/output-and-savings.md3.2 KB
- 参考文档references/README.md1000 B
- 参考文档references/scope-resolution.md3.4 KB
- 参考文档references/selection-and-handoff.md8.6 KB
- 参考文档references/state-updates.md5.0 KB
- 参考文档references/table-format.md11.5 KB
- 参考文档references/tools-and-recovery.md6.3 KB
- 参考文档references/workflow.md3.4 KB
03 SKILL.md 正文
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. Reuse already loaded references. If a required file is unavailable, report it and stop the affected flow.
Use the matching scenario guidance; Reference index.
Quick reference
| Flow | Required reference |
|---|---|
| Discovery and type expansion | Workflow |
| Counts, savings field mapping and pricing-source interpretation | Output and savings |
| Tables and selected resources | Table format |
| Completed/historical reports | Lifecycle |
| State changes | State updates |
| Selection/remediation handoff | Selection |
| Explicit prevalidation/safety checks | Selection |
| Filters/errors | Tools and recovery |
| Routing examples | Examples |
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.
04 同仓库更多 Skills
python-appservice-deploy
Deploy Python (Flask/Django/FastAPI) code to Azure App Service Linux. WHEN: "Flask App Service", "Django App Service", "FastAPI App Service", "deploy Python to App Service". DO NOT USE FOR: Container Apps, Functions, non-Python, Terraform/Bicep/IaC, full infra — use azure-prepare.
preset
Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).
customize
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
capacity
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
deploy-model
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).