microsoft/skills is a collection of skills, custom agents, AGENTS.md templates, plugins, hooks, commands, and MCP configurations that give AI coding agents context for Azure SDK and Microsoft AI Foundry development. Developers use it to install selected domain-specific guidance into coding-agent environments. The catalogue entries are the repository’s own agent resources and supporting configurations.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/skills --skill azure-mgmt-arizeaiobservabilityeval-dotnetgit clone --depth 1 https://github.com/microsoft/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/skills/azure-mgmt-arizeaiobservabilityeval-dotnet)<a href="https://agentmods.dev/skills/microsoft/skills/azure-mgmt-arizeaiobservabilityeval-dotnet"><img src="https://agentmods.dev/badge/skills/microsoft/skills/azure-mgmt-arizeaiobservabilityeval-dotnet/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/skills/azure-mgmt-arizeaiobservabilityeval-dotnet"><img src="https://agentmods.dev/badge/skills/microsoft/skills/azure-mgmt-arizeaiobservabilityeval-dotnet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.01848 |
| Opus 5 | $0.00044 | $0.00924 |
| Sonnet 5 | $0.00018 | $0.00370 |
| Haiku 4.5 | $0.00009 | $0.00185 |
Grade A, and why
azure-mgmt-arizeaiobservabilityeval-dotnet scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
3 near-identical copies found in the catalogue:
- azure-mgmt-arizeaiobservabilityeval-dotnet — 94% identical, 31 lines differ
- azure-mgmt-arizeaiobservabilityeval-dotnet — 94% identical, 31 lines differ
- azure-mgmt-arizeaiobservabilityeval-dotnet — 92% identical, 34 lines differ
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure.ResourceManager.ArizeAIObservabilityEval
.NET SDK for managing Arize AI Observability and Evaluation resources on Azure.
Installation
dotnet add package Azure.ResourceManager.ArizeAIObservabilityEval --version 1.0.0
Package Info
| Property | Value |
|---|---|
| Package | Azure.ResourceManager.ArizeAIObservabilityEval |
| Version | 1.0.0 (GA) |
| API Version | 2024-10-01 |
| ARM Type | ArizeAi.ObservabilityEval/organizations |
| Dependencies | Azure.Core >= 1.46.2, Azure.ResourceManager >= 1.13.1 |
Environment Variables
AZURE_SUBSCRIPTION_ID=<your-subscription-id> # Required: Azure subscription ID
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
AZURE_TENANT_ID=<your-tenant-id> # For service principal auth (optional)
AZURE_CLIENT_ID=<your-client-id> # For service principal auth (optional)
AZURE_CLIENT_SECRET=<your-client-secret> # For service principal auth (optional)
Authentication
using Azure.Identity;
using Azure.ResourceManager;
using Azure.ResourceManager.ArizeAIObservabilityEval;
// Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
var credential = new DefaultAzureCredential(
DefaultAzureCredential.DefaultEnvironmentVariableName
);
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/dotnet/api/overview/azure/identity-readme?view=azure-dotnet#credential-classes
// var credential = new ManagedIdentityCredential();
var armClient = new ArmClient(credential);
Core Workflow
Create an Arize AI Organization
using Azure.Core;
using Azure.ResourceManager.Resources;
using Azure.ResourceManager.ArizeAIObservabilityEval;
using Azure.ResourceManager.ArizeAIObservabilityEval.Models;
// Get subscription and resource group
var subscriptionId = Environment.GetEnvironmentVariable("AZURE_SUBSCRIPTION_ID");
var subscription = await armClient.GetSubscriptionResource(
SubscriptionResource.CreateResourceIdentifier(subscriptionId)).GetAsync();
var resourceGroup = await subscription.Value.GetResourceGroupAsync("my-resource-group");
// Get the organization collection
var collection = resourceGroup.Value.GetArizeAIObservabilityEvalOrganizations();
// Create organization data
var data = new ArizeAIObservabilityEvalOrganizationData(AzureLocation.EastUS)
{
Properties = new ArizeAIObservabilityEvalOrganizationProperties
{
Marketplace = new ArizeAIObservabilityEvalMarketplaceDetails
{
SubscriptionId = "marketplace-subscription-id",
OfferDetails = new ArizeAIObservabilityEvalOfferDetails
{
PublisherId = "arikimlabs1649082416596",
OfferId = "arize-liftr-1",
PlanId = "arize-liftr-1-plan",
PlanName = "Arize AI Plan",
TermUnit = "P1M",
TermId = "term-id"
}
},
User = new ArizeAIObservabilityEvalUserDetails
{
FirstName = "John",
LastName = "Doe",
EmailAddress = "[email protected]"
}
},
Tags = { ["environment"] = "production" }
};
// Create (long-running operation)
var operation = await collection.CreateOrUpdateAsync(
WaitUntil.Completed,
"my-arize-org",
data);
var organization = operation.Value;
Console.WriteLine($"Created: {organization.Data.Name}");
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 238 lines · 89 tokens per session scan A 511734ed1e01
azure-mgmt-arizeaiobservabilityeval-dotnet is a skill published in the GitHub repository microsoft/skills (3,004 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 1,848 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agents-v2-py-v2
Azure AI Hosted Agents (Python) workflow skill. Use this skill when the user needs Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry and the operator should preserve the upstream workflow…
FOCUS Data Engineer
End-to-end ingest, transform, and conformance specialist for FOCUS-shaped cost datasets. Handles AWS CUR 2.0, Azure Cost Management exports, GCP billing export, OCI cost & usage, and SaaS billing. Operates the FOCUS Validator and Requirements Analyzer; orchestrates parallel-run migrations.
Workload Cost Optimizer
Compute-pattern specialist for ML training/inference, serverless (Lambda/Cloud Functions/Azure Functions), and spot/preemptible/low-priority strategies. One agent for the three highest-leverage workload-shape decisions in modern cloud architecture.
CUR & FOCUS Data Engineer
Builds reliable ingest and transformation pipelines for AWS CUR 2.0, Azure Cost Management exports, GCP billing export, and the FOCUS specification. Turns raw vendor exports into a trusted cost warehouse.
ML Workload Cost Optimizer
Specialist in ML training and inference cost -- GPU selection, spot strategies, multi-region training, inference optimization via quantization and batching, and managed-service tradeoffs (SageMaker / Vertex AI / Azure ML).
agents-v2-py
Azure AI Hosted Agents (Python) workflow skill. Use this skill when the user needs Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry and the operator should preserve the upstream workflow…