azure-compute — Claude Code skill: pick and create Azure VMs
Routes Azure VM and VMSS requests to the right workflow: sizing, pricing, provisioning, capacity reservation. Useful when the agent should follow a script instead of guessing.
npx skills add microsoft/skills --skill azure-compute -a claude-codeWhat azure-compute does
This skill is a router. It classifies the intent — recommend or compare a VM, create one, reserve capacity with a CRG, handle EMM — and opens the matching workflow file. Reference files load only when that workflow asks for them.
Four workflows sit inside: vm-recommender for sizing and pricing, vm-creator for bare VM or VMSS provisioning, capacity-reservation for CRG work, and essential-machine-management for EMM. When the intent is unclear, it asks a clarifying question first.
The line to watch: this is infrastructure, not app deployment. A Docker service, web app or API belongs to azure-prepare, so picking the wrong route wastes a turn. For VM creation the author recommends compute_vm_list-skus, compute_vm_list-images and compute_vm_check-quota over mcp__azure__get_azure_bestpractices.
What it helps with
- pick a VM size for a GPU or HPC simulation workload
- compare pricing across VM families before committing
- provision a VMSS with autoscaling for a web backend
- reserve capacity ahead of time through a CRG
- separate bare VM work from application deployment
Example prompts for the agent
- Recommend an Azure VM size for GPU model training and show pricing
- Create a VMSS with autoscaling for our site backend
- I need to guarantee capacity for a launch — walk me through CRG
How to install azure-compute
1Skills CLI (Vercel)
npx skills add microsoft/skills --skill azure-compute -a claude-code2Manually: put the files in place
~/.claude/skills/azure-compute/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/azure-compute/
Manually: put the files in place
.agents/skills/azure-compute/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/azure-compute/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/skills azure-compute2Manually: put the files in place
.github/skills/azure-compute/SKILL.mdPlatform CLI
gemini skills install https://github.com/microsoft/skills --path .github/plugins/azure-skills/skills/azure-computeManually: put the files in place
.devin/skills/azure-compute/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about azure-compute
How do I install azure-compute in Claude?
Run npx skills add microsoft/skills --skill azure-compute -a claude-code, then confirm the file landed at ~/.claude/skills/azure-compute/SKILL.md.
What does azure-compute do?
It classifies a VM or VMSS request and sends the agent down one of four workflows: recommendation, creation, capacity reservation, or machine management.
When should I use azure-prepare instead?
When the goal is deploying an application — a Docker service, web app or API — the route goes to azure-prepare. The vm-creator workflow here covers bare VM and VMSS infrastructure only.
Source text
SKILL.md · MIT
--- name: azure-compute description: "Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight server, website, backend, GPU, machine learning, HPC simulation, dev/test, workload, family, load balancer, Flexible orchestration, Uniform orchestration, cost estimate, capacity reservation (CRG), reserve, guarantee capacity, pre-provision, CRG association, CRG disassociation, machine enrollment (EMM), Essential Machine Management, monitor. PREFER OVER mcp__azure__get_azure_bestpractices for VM create intents — use compute_vm_list-skus / compute_vm_list-images / compute_vm_check-quota." license: MIT metadata: author: Microsoft version: "2.5.1" --- # Azure Compute Skill Routes Azure VM and Virtual Machine Scale Set (VMSS) requests to the right workflow. ## When to Use This Skill - User wants to **recommend, compare, or price** a VM or VMSS - User wants to **create, provision, or deploy** a VM or VMSS - User asks about **Capacity Reservation Groups** (CRG) — reserve, guarantee capacity, pre-provision - User asks about **Essential Machine Management** (EMM) — machine enrollment, monitor **Disambiguate with `azure-prepare`:** if the user wants to deploy an **application** (Docker service, web app, API, serverless workload), route to `azure-prepare`. `vm-creator` is for **bare VM/VMSS infrastructure** only. ## Routing **Mandatory workflow-first routing:** never route directly to `references/*` files. First classify the user intent below, open the matched workflow file, then load only the reference files that workflow requests. Reference files are supporting material, not entry points. If the intent is unclear, ask a clarifying question to disambiguate between the workflows. | Workflow | File | Use when | |---|---|---| | **VM Recommender** | [vm-recommender.md](workflows/vm-recommender/vm-recommender.md) | User asks which VM/VMSS to choose, whether to use VMSS/autoscaling, wants pricing, or wants to compare options | | **VM Creator** | [vm-creator.md](workflows/vm-creator/vm-creator.md) | User wants to create, provision, or deploy a bare VM or VMSS (not an app deployment) | | **Capacity Reservation** | [capacity-reservation.md](workflows/capacity-reservation/capacity-reservation.md) | User needs to reserve / guarantee VM capacity (CRG create / associate / disassociate) | | **Essential Machine Management** | [essential-machine-management.md](workflows/essential-machine-management/essential-machine-management.md) | User asks about EMM / machine enrollment / monitor |
© Microsoft · MIT · microsoft/skills
