|- Azure Bot Service Management SDK for Python. Use for creating, managing, and configuring Azure Bot Service resources.
npx skills add https://github.com/microsoft/skills --skill azure-mgmt-botservice-py
Manage Azure Bot Service resources including bots, channels, and connections.
pip install azure-mgmt-botservice
pip install azure-identity
AZURE_SUBSCRIPTION_ID=<your-subscription-id> # Required for all auth methods
AZURE_RESOURCE_GROUP=<your-resource-group> # Required for all auth methods
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
> 🔑 Two rules apply to every code sample below:
>
> 1. Prefer DefaultAzureCredential. It works locally (Azure CLI / VS Code / Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account/API keys — they bypass Entra audit and rotation.
> - Local dev: DefaultAzureCredential works as-is.
> - Production: set AZURE_TOKEN_CREDENTIALS=prod (or AZURE_TOKEN_CREDENTIALS=<specific_credential>) to constrain the credential chain to production-safe credentials.
> 2. Wrap every client in a context manager so HTTP transports, sockets, and token caches are released deterministically:
> - Sync: with <Client>(...) as client:
> - Async: async with <Client>(...) as client: and async with DefaultAzureCredential() as credential: (from azure.identity.aio)
>
> Snippets may abbreviate this setup, but production code should always follow both rules.
from azure.identity import DefaultAzureCredential, ManagedIdentityCredential
from azure.mgmt.botservice import AzureBotService
import os
# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential(require_envvar=True)
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()
with AzureBotService(
credential=credential,
subscription_id=os.environ["AZURE_SUBSCRIPTION_ID"]
) as client:
# Use `client` for all subsequent operations (see examples below)
...
from azure.mgmt.botservice import AzureBotService
from azure.mgmt.botservice.models import Bot, BotProperties, Sku
from azure.identity import DefaultAzureCredential
import os
resource_group = os.environ["AZURE_RESOURCE_GROUP"]
bot_name = "my-chat-bot"
credential = DefaultAzureCredential()
with AzureBotService(
credential=credential,
subscription_id=os.environ["AZURE_SUBSCRIPTION_ID"]
) as client:
bot = client.bots.create(
resource_group_name=resource_group,
resource_name=bot_name,
parameters=Bot(
location="global",
sku=Sku(name="F0"), # Free tier
kind="azurebot",
properties=BotProperties(
display_name="My Chat Bot",
description="A conversational AI bot",
endpoint="https://my-bot-app.azurewebsites.net/api/messages",
msa_app_id="<your-app-id>",
msa_app_type="MultiTenant"
)
)
)
print(f"Bot created: {bot.name}")
bot = client.bots.get(
resource_group_name=resource_group,
resource_name=bot_name
)
print(f"Bot: {bot.properties.display_name}")
print(f"Endpoint: {bot.properties.endpoint}")
print(f"SKU: {bot.sku.name}")
bots = client.bots.list_by_resource_group(resource_group_name=resource_group)
for bot in bots:
print(f"Bot: {bot.name} - {bot.properties.display_name}")
all_bots = client.bots.list()
for bot in all_bots:
print(f"Bot: {bot.name} in {bot.id.split('/')[4]}")
bot = client.bots.update(
resource_group_name=resource_group,
resource_name=bot_name,
properties=BotProperties(
display_name="Updated Bot Name",
description="Updated description"
)
)
client.bots.delete(
resource_group_name=resource_group,
resource_name=bot_name
)
from azure.mgmt.botservice.models import (
BotChannel,
MsTeamsChannel,
MsTeamsChannelProperties
)
channel = client.channels.create(
resource_group_name=resource_group,
resource_name=bot_name,
channel_name="MsTeamsChannel",
parameters=BotChannel(
location="global",
properties=MsTeamsChannel(
properties=MsTeamsChannelProperties(
is_enabled=True
)
)
)
)
from azure.mgmt.botservice.models import (
BotChannel,
DirectLineChannel,
DirectLineChannelProperties,
DirectLineSite
)
channel = client.channels.create(
resource_group_name=resource_group,
resource_name=bot_name,
channel_name="DirectLineChannel",
parameters=BotChannel(
location="global",
properties=DirectLineChannel(
properties=DirectLineChannelProperties(
sites=[
DirectLineSite(
site_name="Default Site",
is_enabled=True,
is_v1_enabled=False,
is_v3_enabled=True
)
]
)
)
)
)
from azure.mgmt.botservice.models import (
BotChannel,
WebChatChannel,
WebChatChannelProperties,
WebChatSite
)
channel = client.channels.create(
resource_group_name=resource_group,
resource_name=bot_name,
channel_name="WebChatChannel",
parameters=BotChannel(
location="global",
properties=WebChatChannel(
properties=WebChatChannelProperties(
sites=[
WebChatSite(
site_name="Default Site",
is_enabled=True
)
]
)
)
)
)
channel = client.channels.get(
resource_group_name=resource_group,
resource_name=bot_name,
channel_name="DirectLineChannel"
)
keys = client.channels.list_with_keys(
resource_group_name=resource_group,
resource_name=bot_name,
channel_name="DirectLineChannel"
)
# Access Direct Line keys
if hasattr(keys.properties, 'properties'):
for site in keys.properties.properties.sites:
print(f"Site: {site.site_name}")
print(f"Key: {site.key}")
from azure.mgmt.botservice.models import (
ConnectionSetting,
ConnectionSettingProperties
)
connection = client.bot_connection.create(
resource_group_name=resource_group,
resource_name=bot_name,
connection_name="graph-connection",
parameters=ConnectionSetting(
location="global",
properties=ConnectionSettingProperties(
client_id="<oauth-client-id>",
client_secret="<oauth-client-secret>",
scopes="User.Read",
service_provider_id="<service-provider-id>"
)
)
)
connections = client.bot_connection.list_by_bot_service(
resource_group_name=resource_group,
resource_name=bot_name
)
for conn in connections:
print(f"Connection: {conn.name}")
| Operation | Method |
|-----------|--------|
| client.bots | Bot CRUD operations |
| client.channels | Channel configuration |
| client.bot_connection | OAuth connection settings |
| client.direct_line | Direct Line channel operations |
| client.email | Email channel operations |
| client.operations | Available operations |
| client.host_settings | Host settings operations |
| SKU | Description |
|-----|-------------|
| F0 | Free tier (limited messages) |
| S1 | Standard tier (unlimited messages) |
| Channel | Class | Purpose |
|---------|-------|---------|
| MsTeamsChannel | Microsoft Teams | Teams integration |
| DirectLineChannel | Direct Line | Custom client integration |
| WebChatChannel | Web Chat | Embeddable web widget |
| SlackChannel | Slack | Slack workspace integration |
| FacebookChannel | Facebook | Messenger integration |
| EmailChannel | Email | Email communication |
azure.xxx sync clients with azure.xxx.aio async clients in the same call path. Choose one mode per module.with Client(...) as client: (sync) or async with Client(...) as client: (async). For async DefaultAzureCredential from azure.identity.aio, also use async with credential: so tokens and transports are cleaned up.DefaultAzureCredential for code that runs locally. Use a specific token credential for code that runs in Azure.| File | Contents |
|------|----------|
| references/capabilities.md | Additional non-hero capabilities, operation-group coverage, and production checklists. |
| references/non-hero-scenarios.md | Dedicated non-hero examples for secondary/advanced scenarios. |
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
Google Cloud Platform CLI - manage GCP resources including Compute Engine, Cloud Run, GKE, Cloud Functions, Storage, BigQuery, and more.
Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and observability. Use PROACTIVELY when creating new backend services or APIs.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment. Use when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire distributed application.
Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Returns a structured report with exact patch locations.
Microsoft Store Developer CLI (msstore) for publishing Windows applications to the Microsoft Store. Use when asked to configure Store credentials, list Store apps, check submission status, publish submissions, manage package flights, set up CI/CD for Store publishing, or integrate with Partner Center. Supports Windows App SDK/WinUI, UWP, .NET MAUI, Flutter, Electron, React Native, and PWA applications.
Take microsoft/azure-mgmt-botservice-py from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.