/azure-sre-agent

name: azure-sre-agent
description: Expert knowledge for Azure Sre Agent development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when integrating SRE Agent with DevOps/GitHub, configuring KQL telemetry, AKS Java workloads, IaC deployments, or DR, and other Azure Sre Agent related development tasks. Not for Azure Monitor (use azure-monitor), Azure Reliability (use azure-reliability), Azure Resiliency (use azure-resiliency), Azure Service Health (use azure-service-health).
compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
metadata:
  generated_at: "2026-09-13"
  generator: "docs2skills/1.0.0"

Azure Sre Agent Skill

This skill provides expert guidance for Azure Sre Agent. 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](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)

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-L44 | Diagnosing and fixing SRE Agent issues: querying telemetry with KQL, filing Azure support tickets, resolving deployment/operation failures, and debugging Java performance on AKS. | | Best Practices | L45-L49 | Best practices for integrating Azure Monitor, Application Insights, and related observability tools with SRE Agent to collect, analyze, and act on telemetry and alerts. | | Decision Making | L50-L55 | Guidance on when to run deep investigations, when to use Log Analytics vs App Insights, how to estimate/control SRE Agent costs, and which Azure regions you can deploy in. | | Architecture & Design Patterns | L56-L60 | Designing cold-standby disaster recovery for Azure SRE Agent, including architecture choices, failover strategy, RPO/RTO considerations, and environment replication. | | Limits & Quotas | L61-L65 | Details of the 30-day Azure SRE Agent trial limits, including usage caps, feature restrictions, and what happens when you reach or exceed those limits. | | Security | L66-L84 | Securing Azure SRE Agent: identities, RBAC and roles, network/firewall, data privacy, GitHub/ADO access, subscription visibility, tool access policies, and approval/run-mode controls. | | Configuration | L85-L100 | Configuring SRE Agent capabilities: code interpreter, knowledge sources, tools/skills, governance hooks, subagents, incident plans, connectors, network/VNet, GitHub auth, MCP/IDE, and REST hooks. | | Integrations & Coding Patterns | L101-L121 | Integrating Azure SRE Agent with DevOps, GitHub, observability, incident tools, MCP servers, and Python/Kusto tools, plus secure API use and cross-tenant access configuration | | Deployment | L122-L125 | How to deploy Azure SRE Agent using Infrastructure-as-Code templates, including required resources, parameters, and environment configuration steps. |

Troubleshooting

| Topic | URL | |-------|-----| | Query Azure SRE Agent telemetry and actions with KQL | https://learn.microsoft.com/en-us/azure/sre-agent/audit-agent-actions | | File Azure support requests from SRE Agent troubleshooting | https://learn.microsoft.com/en-us/azure/sre-agent/create-support-request | | Troubleshoot Azure SRE Agent deployment and operations | https://learn.microsoft.com/en-us/azure/sre-agent/faq-troubleshooting | | Diagnose Java performance issues on AKS with SRE Agent | https://learn.microsoft.com/en-us/azure/sre-agent/troubleshoot-java-aks |

Best Practices

| Topic | URL | |-------|-----| | Use Azure observability tools with SRE Agent | https://learn.microsoft.com/en-us/azure/sre-agent/diagnose-azure-observability |

Decision Making

| Topic | URL | |-------|-----| | Decide when to use deep investigation in Azure SRE Agent | https://learn.microsoft.com/en-us/azure/sre-agent/deep-investigation | | Decide when to use Log Analytics and App Insights connectors in SRE Agent | https://learn.microsoft.com/en-us/azure/sre-agent/log-analytics-app-insights |

Architecture & Design Patterns

| Topic | URL | |-------|-----| | Design cold-standby disaster recovery for Azure SRE Agent | https://learn.microsoft.com/en-us/azure/sre-agent/disaster-recovery |

Limits & Quotas

| Topic | URL | |-------|-----| | Understand Azure SRE Agent 30-day trial limits | https://learn.microsoft.com/en-us/azure/sre-agent/evaluate |

Security

| Topic | URL | |-------|-----| | Understand Azure SRE Agent identities and authentication | https://learn.microsoft.com/en-us/azure/sre-agent/agent-identity | | Allow-list SRE Agent outbound IPs in Key Vault firewall | https://learn.microsoft.com/en-us/azure/sre-agent/allow-list-key-vault-firewall | | Configure secure network controls for Azure SRE Agent | https://learn.microsoft.com/en-us/azure/sre-agent/configure-network-controls | | Configure manage