Expert knowledge for Azure Microsoft Discovery development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring Discovery workspaces, supercomputers, ACR-based tools, REST job APIs, or shared sessions, and other Azure Microsoft Discovery related development tasks. Not for Azure Portal (use azure-portal), Azure Resource Graph (use azure-resource-graph), Azure Monitor (use azure-monitor), Azure Cost Management (use azure-cost-management).
npx skills add https://github.com/MicrosoftDocs/Agent-Skills --skill azure-microsoft-discovery
This skill provides expert guidance for Azure Microsoft Discovery. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
> IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g., L35-L120), use read_file with the specified lines. For categories with file links (e.g., security.md), use read_file on the linked reference file
> IMPORTANT for Agent: If metadata.generated_at is more than 3 months old, suggest the user pull the latest version from the repository. If mcp_microsoftdocs tools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.| Category | Lines | Description |
|----------|-------|-------------|
| Troubleshooting | L37-L41 | Diagnosing and fixing Discovery Engine task execution failures, including common error patterns, configuration issues, and steps to restore successful task runs. |
| Best Practices | L42-L49 | Best practices for structuring projects and shared sessions, applying responsible AI, calibrating trust and safety patterns, and planning tool capabilities and compute for Discovery. |
| Decision Making | L50-L57 | Guidance on selecting ACR setup, agent types, pricing/billing, and suitable AI models to design and configure Microsoft Discovery agents effectively. |
| Architecture & Design Patterns | L58-L62 | Designing and implementing advanced shared session patterns in Discovery Engine, including multi-user session management, data sharing, and scalable architecture best practices. |
| Limits & Quotas | L63-L68 | Planning capacity and Azure quotas for Microsoft Discovery deployments, plus required naming conventions and rules for Discovery resources. |
| Security | L69-L83 | Security, encryption, RBAC, managed identities, private networking, supercomputer network hardening, and audit logging for protecting Microsoft Discovery resources. |
| Configuration | L84-L104 | Configuring Discovery workspaces, supercomputers, storage, tools, data handling, and querying operational/indexing logs via Log Analytics, Kusto, and Azure activity logs |
| Integrations & Coding Patterns | L105-L112 | Integrating custom tools/models into Discovery workflows, containerizing them with Docker, calling Discovery Supercomputer REST job APIs, and writing action scripts for action-based tools. |
| Deployment | L113-L119 | Deploying Discovery infrastructure and tools: network-hardened stacks, Bicep-based deployments, REST provisioning of supercomputer resources, and publishing tool images to Azure Container Registry. |
| Topic | URL |
|-------|-----|
| Troubleshoot Discovery Engine task execution issues | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-debug-task-execution |
| Topic | URL |
|-------|-----|
| Apply projects and shared session best practices in Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-projects-investigations |
| Apply responsible AI practices in Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-responsible-ai |
| Calibrate trust and basic shared session patterns in Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-trust-basic-investigation-patterns |
| Plan tool functionality and compute for Discovery tools | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-plan-tool-requirements |
| Topic | URL |
|-------|-----|
| Choose and configure Azure Container Registry for Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-azure-container-registry |
| Choose the right Microsoft Discovery agent type | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-discovery-agent-types |
| Understand Microsoft Discovery billing and charges | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-discovery-billing |
| Choose appropriate models for Microsoft Discovery agents | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-select-models-for-agents |
| Topic | URL |
|-------|-----|
| Apply advanced shared session patterns with Discovery Engine | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-advanced-investigation-patterns |
| Topic | URL |
|-------|-----|
| Plan Azure quotas and capacity for Microsoft Discovery deployments | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-quota-reservation |
| Apply Microsoft Discovery resource naming rules | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-resource-naming |
| Topic | URL |
|-------|-----|
| Understand Microsoft Discovery code of conduct and acceptable use | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-code-of-conduct |
| Manage data encryption at rest in Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-data-encryption-at-rest |
| Configure managed identities for Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-managed-identities |
| Configure network security for Microsoft Discovery workspaces | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-network-security |
| Configure RBAC role assignments for Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-role-assignments |
| Assign Microsoft Discovery persona RBAC roles via PowerShell | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-assign-persona-roles |
| Configure user-assigned managed identities for Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-configure-managed-identity |
| Configure network security and private access for Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-configure-network-security |
| Secure networking for Discovery Supercomputer | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-configure-supercomputer-network-security |
| Enable and export audit logs for Discovery resources | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-enable-audit-logging |
| Configure customer-managed keys for Discovery resources | https://learn.microsoft.com/en-us/azure/microsoft-discovery/howto-data-encryption-at-rest |
| Topic | URL |
|-------|-----|
| Manage files and storage assets in Microsoft Discovery shared sessions | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-files-storage-assets |
| Register Microsoft Discovery resource provider in Azure | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-resource-provider-registration |
| Configure Azure Blob Storage for Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-storage-account |
| Configure storage containers and assets for Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-storage-containers-assets |
| Access Log Analytics workspaces for Discovery resources | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-access-resource-logs |
| Author tool definition YAML for Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-create-tool-definition |
| Configure data handling for tools and agents in Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-data-handling-with-tools-agents |
| Configure Bookshelf and index knowledgebases in Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-index-bookshelf-knowledgebase |
| Configure storage containers and assets in Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-manage-storage-containers |
| Create and manage Discovery Supercomputers and node pools | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-manage-supercomputers |
| Create and manage Microsoft Discovery workspaces | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-manage-workspaces |
| Query bookshelf indexing logs in Discovery supercomputers | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-query-bookshelf-indexing-logs |
| Query bookshelf knowledgebase query logs in Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-query-bookshelf-logs |
| Query CogLoop orchestration logs for Discovery investigations | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-query-cognitive-loop-logs |
| Query supercomputer platform and tool logs in Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-query-supercomputer-logs |
| Query Discovery workspace logs with Kusto and correlation IDs | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-query-workspace-logs |
| View Azure activity logs for Discovery control plane | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-view-activity-logs |
| Topic | URL |
|-------|-----|
| Integrate tools and models into Microsoft Discovery workflows | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-tools-model-integration |
| Create Dockerfiles to containerize Discovery tools | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-create-tool-docker-file |
| Use Discovery Supercomputer REST APIs for jobs | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-run-jobs-supercomputer-rest-api |
| Implement action scripts for Discovery action-based tools | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-write-tool-action-scripts |
| Topic | URL |
|-------|-----|
| Deploy a fully network-hardened Microsoft Discovery stack | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-deploy-network-hardened-stack |
| Deploy and register tools to Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-deploy-tool-to-discovery |
| Provision Discovery Supercomputer infrastructure via REST API | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-manage-supercomputers-rest-api |
| Publish Discovery tool images to Azure Container Registry | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-publish-tool-to-acr |
Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).
Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
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.
Take microsoftdocs/azure-microsoft-discovery 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.