name: azure-microsoft-discovery
description: 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 building Discovery workspaces, shared sessions, supercomputer jobs, Docker tools, or Log Analytics queries, and other Azure Microsoft Discovery related development tasks. Not for Azure Resource Graph (use azure-resource-graph), Azure Portal (use azure-portal), Azure Monitor (use azure-monitor), Azure Policy (use azure-policy).
compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
metadata:
generated_at: "2026-06-14"
generator: "docs2skills/1.0.0"
Azure Microsoft Discovery Skill
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.
How to Use This Skill
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](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:
- Preferred: Use
mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.
- Fallback: Use
fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.
Category Index
| 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 registries, agent types, billing options, and LLM models for Microsoft Discovery, including configuration, cost implications, and matching models/agents to workloads. |
| 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-L82 |
Security and compliance for Discovery: encryption at rest, customer-managed keys, managed identities, RBAC/persona roles, network/private access, and audit logging configuration. |
| Configuration |
L83-L103 |
Configuring Discovery workspaces, supercomputers, storage, tools, data handling, and querying operational/indexing logs via Log Analytics and Kusto. |
| Integrations & Coding Patterns |
L104-L111 |
Patterns and APIs for integrating tools/models into Discovery workflows, containerizing tools with Docker, writing action scripts, and submitting/monitoring Supercomputer jobs via REST |
| Deployment |
L112-L118 |
Deploying Microsoft Discovery: secure stack setup, provisioning supercomputer infra via REST, registering tools, and publishing tool images to Azure Container Registry. |
Troubleshooting
Best Practices
Decision Making
Architecture & Design Patterns
Limits & Quotas
Security
Configuration
Integrations & Coding Patterns
Deployment