azure-expert — Claude Code skill: what it does, how to install
azure-expert is a Claude Code skill for Microsoft Azure architecture, Azure Functions code, Cosmos DB queries, and Azure CLI commands.
Apache-2.0 180 installs ★ 45 updated 2026-10-12
npx skills add personamanagmentlayer/pcl --skill azure-expert -a claude-codeWhat azure-expert does
This skill equips coding assistants with blueprints and practices for Microsoft Azure services, covering ARM templates, App Services, Cosmos DB, and serverless Azure Functions. It explicitly permits running terminal commands under Bash(az:*) alongside basic file edits.
The skill provides Python implementations for HTTP and queue triggers, Cosmos DB client queries with partition keys, and deployment templates. It also flags architectural pitfalls like hardcoded credentials, single-region deployments, and unmanaged identities.
Running terminal deployment steps directly requires an authentic Azure CLI (az) setup on the host system.
What it helps with
- scaffold Python functions for Azure Functions HTTP and queue triggers
- generate az CLI commands to deploy web apps and storage accounts
- query Cosmos DB containers with partition key parameters
- draft ARM deployment templates for App Service hosting plans
Example prompts for the agent
- Create a Python QueueTrigger function for Azure Functions handling AzureWebJobsStorage
- Draft an az CLI command to deploy an Ubuntu virtual machine with SSH keys
- Show a Cosmos DB query filtered by userId using the Python client
How to install azure-expert
1Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill azure-expert -a claude-code2Manually: put the files in place
~/.claude/skills/azure-expert/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/azure-expert/
1Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill azure-expert -a codex2Manually: put the files in place
.agents/skills/azure-expert/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill azure-expert -a cursor2Manually: put the files in place
.cursor/skills/azure-expert/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install personamanagmentlayer/pcl stdlib/cloud/azure-expert2Manually: put the files in place
.github/skills/azure-expert/SKILL.md1Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill azure-expert -a gemini-cli2Platform CLI
gemini skills install https://github.com/personamanagmentlayer/pcl --path stdlib/cloud/azure-expertManually: put the files in place
.devin/skills/azure-expert/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add personamanagmentlayer/pcl --skill azure-expert -a opencodeClaude.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-expert
How to install azure-expert in Claude Code?
Run npx skills add personamanagmentlayer/pcl --skill azure-expert -a claude-code in your terminal to save the definition into ~/.claude/skills/azure-expert/SKILL.md.
What does azure-expert do?
It guides the agent on Azure cloud architecture, ARM templates, Azure Functions code generation, and executing az terminal commands.
Which tools are permitted by this skill?
The configuration grants access to Read, Write, Edit, and shell commands matching Bash(az:*).
Source text
SKILL.md · Apache-2.0
---
name: azure-expert
version: 1.1.0
description: >-
Expert-level Microsoft Azure cloud platform, services, and architecture. Use when the
user mentions cloud, Microsoft platforms, Azure Functions, or Cosmos DB.
category: cloud
tags: [azure, cloud, microsoft, azure-functions, cosmos-db]
allowed-tools:
- Read
- Write
- Edit
- Bash(az:*)
---
# Microsoft Azure Expert
Expert guidance for Microsoft Azure cloud platform, services, and cloud-native architecture.
## Core Concepts
- Azure Resource Manager (ARM)
- Virtual Machines and App Services
- Azure Functions (serverless)
- Azure Storage (Blob, Queue, Table)
- Azure SQL Database
- Cosmos DB
- Azure Kubernetes Service (AKS)
- Azure Active Directory
## Azure CLI
```bash
# Login
az login
# Create resource group
az group create --name myResourceGroup --location eastus
# Create VM
az vm create \
--resource-group myResourceGroup \
--name myVM \
--image UbuntuLTS \
--admin-username azureuser \
--generate-ssh-keys
# Create App Service
az webapp create \
--resource-group myResourceGroup \
--plan myAppServicePlan \
--name myWebApp \
--runtime "NODE|14-lts"
# Create storage account
az storage account create \
--name mystorageaccount \
--resource-group myResourceGroup \
--location eastus \
--sku Standard_LRS
```
## Azure Functions
```python
import azure.functions as func
import logging
app = func.FunctionApp()
@app.function_name(name="HttpTrigger")
@app.route(route="hello")
def main(req: func.HttpRequest) -> func.HttpResponse:
logging.info('Python HTTP trigger function processed a request.')
name = req.params.get('name')
if not name:
try:
req_body = req.get_json()
name = req_body.get('name')
except ValueError:
pass
if name:
return func.HttpResponse(f"Hello, {name}!")
else:
return func.HttpResponse(
"Please pass a name",
status_code=400
)
@app.function_name(name="QueueTrigger")
@app.queue_trigger(arg_name="msg", queue_name="myqueue",
connection="AzureWebJobsStorage")
def queue_trigger(msg: func.QueueMessage):
logging.info(f'Python queue trigger function processed: {msg.get_body().decode("utf-8")}')
```
## Cosmos DB
```python
from azure.cosmos import CosmosClient, PartitionKey
endpoint = "https://myaccount.documents.azure.com:443/"
key = "YOUR_KEY"
client = CosmosClient(endpoint, key)
database = client.create_database_if_not_exists(id="myDatabase")
container = database.create_container_if_not_exists(
id="myContainer",
partition_key=PartitionKey(path="/userId")
)
# Create item
item = {
"id": "1",
"userId": "user123",
"name": "John Doe"
}
container.create_item(body=item)
# Query items
query = "SELECT * FROM c WHERE c.userId = @userId"
items = container.query_items(
query=query,
parameters=[{"name": "@userId", "value": "user123"}],
enable_cross_partition_query=True
)
for item in items:
print(item)
```
## ARM Templates
```json
{
"$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
"contentVersion": "1.0.0.0",
"resources": [
{
"type": "Microsoft.Web/sites",
"apiVersion": "2021-02-01",
"name": "[parameters('webAppName')]",
"location": "[parameters('location')]",
"properties": {
"serverFarmId": "[resourceId('Microsoft.Web/serverfarms', parameters('appServicePlanName'))]"
}
}
]
}
```
## Best Practices
- Use managed identities
- Implement Azure Key Vault
- Tag resources properly
- Use ARM templates or Bicep
- Monitor with Azure Monitor
- Implement auto-scaling
- Use availability zones
## Anti-Patterns
❌ Hardcoded credentials
❌ No resource tagging
❌ Single region deployment
❌ No backup strategy
❌ Ignoring cost optimization
❌ Not using managed services
## Resources
- Azure Documentation: https://docs.microsoft.com/azure/
- Azure CLI: https://docs.microsoft.com/cli/azure/
© personamanagmentlayer · Apache-2.0 · personamanagmentlayer/pcl