azure-compute

Recommend Azure VM sizes, VM Scale Sets (VMSS), and configurations based on workload requirements, performance needs, and budget constraints. No Azure account required — uses public documentation and the Azure Retail Prices API. WHEN: recommend VM size, which VM should I use, choose Azure VM, VM for web/database/ML/batch/HPC, GPU VM, compare VM sizes, cheapest VM, best VM for workload, VM pricing, cost estimate, burstable/compute/memory/storage optimized VM, confidential computing, VM trade-offs, VM families, VMSS, scale set recommendation, autoscale VMs, load balanced VMs, VMSS vs VM, scale out, horizontal scaling, flexible orchestration.

Install with Tessl CLI

npx tessl i github:microsoft/github-copilot-for-azure --skill azure-compute

What are skills?

1.32x

Review — 92%

Does it follow best practices?

Evaluation — 89%

↑ 1.32x

Agent success when using this skill

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

93%

42%

Containerized REST API — Azure Compute Architecture Recommendation

VMSS configuration and autoscale recommendation

Criteria

Without context

With context

VMSS recommended

100%

Flexible orchestration

100%

Orchestration immutability warning

100%

VMSS docs fetched

100%

Autoscale docs fetched

100%

Autoscale strategy specified

100%

Load balancer type named

100%

Min/max instance pricing

100%

VMSS no extra charge

100%

Production min ≥ 2 instances

100%

VM family web_fetch

Retail Prices API used

25%

100%

No az CLI for pricing

100%

2-3 options presented

100%

Without context: $0.3379 · 2m 8s · 11 turns · 14 in / 7,177 out tokens

With context: $0.6579 · 2m 22s · 26 turns · 2,590 in / 7,792 out tokens

89%

Azure VM Selection for Production Database Server

VM family selection with live pricing API query

Criteria

Without context

With context

E-series selected

100%

VM family docs fetched

66%

Retail Prices API used

100%

curl or Invoke-RestMethod

100%

Linux vs Windows OS filter

100%

87%

isPrimaryMeterRegion filter

eastus default region

100%

Monthly estimate formula

100%

ARM SKU names provided

100%

2-3 options with trade-offs

100%

Why family fits explained

100%

priceType Consumption filter

100%

Reservation next step

50%

100%

Without context: $0.2918 · 1m 33s · 14 turns · 21 in / 5,594 out tokens

With context: $0.6902 · 2m 22s · 27 turns · 2,598 in / 7,962 out tokens

85%

15%

GPU Compute Cost Analysis for ML Training Workloads

GPU VM pricing with Spot and reservation comparison

Criteria

Without context

With context

NC or ND series selected

100%

GPU family docs fetched

100%

Spot VM docs fetched

Retail Prices API used

100%

Spot meterName filter

36%

100%

Reservation pricing queried

100%

Monthly estimate formula

100%

curl or Invoke-RestMethod

100%

2-3 GPU options compared

100%

Trade-offs explained

100%

Azure Pricing Calculator mentioned

Spot eviction risk mentioned

100%

Without context: $1.0103 · 4m 12s · 30 turns · 36 in / 15,124 out tokens

With context: $0.9834 · 3m 44s · 31 turns · 1,787 in / 12,645 out tokens

Evaluated: 2 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Containerized REST API — Azure Compute Architecture Recommendation Azure VM Selection for Production Database Server GPU Compute Cost Analysis for ML Training Workloads

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.