Expert knowledge for Azure Sre Agent development including troubleshooting, best practices, decision making, security, configuration, integrations & coding patterns, and deployment. Use when wiring SRE Agent to Azure DevOps/GitHub, Log Analytics/App Insights, AKS Java workloads, or Key Vault, 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).
v1.0Latest
New~2.6kUpdated Jun 26, 2026
Azure Sre Agent Skill
This skill provides expert guidance for Azure Sre Agent. Covers troubleshooting, best practices, decision making, 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
L35-L42
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
L43-L47
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
L48-L55
Guidance on when to run deep investigations, choosing Log Analytics vs App Insights connectors, estimating/controlling SRE Agent costs, and selecting supported Azure regions.
Security
L56-L72
Securing SRE Agent identities, permissions, RBAC, approvals, network/VNet access, firewalls, and secure connections to Key Vault, ADO, and GitHub (including BYO GitHub App).
This skill provides expert guidance for Azure SRE Agent development, offering troubleshooting, best practices, security configuration, and deployment patterns. It functions as a structured reference guide with a category index that directs agents to fetch remote documentation from Microsoft Learn using MCP tools (mcp_microsoftdocs or fetch_webpage), combined with local quick-reference metadata. The skill does not perform filesystem writes, shell execution, or direct code manipulation — it is purely an information-lookup and guidance skill.
Detected Capabilities
documentation fetchingremote URL retrievalnetwork accessmcp tool invocationmetadata version checking
Trigger Keywords
Phrases that MCP clients use to match this skill to user intent.
Strength: Clear scope boundaries — explicitly excludes Azure Monitor, Reliability, Resiliency, and Service Health (directs to other skills)
Strength: Comprehensive coverage across 7 categories with 49 referenced topics spanning security, configuration, integrations, and deployment
Weakness: No supporting reference files present — the skill relies entirely on remote documentation, no local content snippets or examples
Weakness: Category index references specific line ranges (L35-L42, etc.) that do not correspond to actual SKILL.md content; this is misleading guidance for agents
Weakness: Missing error handling patterns — no guidance on how agents should handle network failures, timeout scenarios, or malformed markdown responses
Weakness: No examples of expected output format or how agents should synthesize multi-document responses into actionable guidance
Weakness: Metadata field 'generated_at: 2026-06-21' is a future date (appears to be placeholder); no clarity on how agents determine true staleness
Model: claude-haiku-4-5-20251001Analyzed: Jun 26, 2026
Reviews
Add this skill to your library to leave a review.
No reviews yet
Be the first to share your experience.
Use MicrosoftDocs/azure-sre-agent in your dev environment — a Developer account adds skills to your library and syncs them via the SkillRepo CLI.