Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoftdocs/azure-reliability
Expert knowledge for Azure Reliability development including best practices, decision making, architecture & design patterns, and limits & quotas.
Passed 17 of 20 test cases with the skill, and 8 of 20 without it.
and 10 more in the full report
12 fixed8 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
When retrieving Microsoft Learn reliability docs using HTTP tools, a standard web fetch might be logged without origin tracking. What specific tracking parameter must be appended to the query string to identify agent skill calls?
| Checked | Without skill | With skill |
|---|---|---|
| Appends from=learn-agent-skill to the URL query string | Missed | Passed |
| Ensures telemetry tracking originates from the skill client | Missed | Passed |
The instructions your model reads when the skill loads.
This skill provides expert guidance for Azure Reliability. Covers best practices, decision making, architecture & design patterns, limits & quotas, 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), useread_filewith the specified lines. For categories with file links (e.g.,[security.md](security.md)), useread_fileon the linked reference file
IMPORTANT for Agent: If
metadata.generated_atis more than 3 months old, suggest the user pull the latest version from the repository. Ifmcp_microsoftdocstools 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 |
|---|---|---|
| Best Practices | L33-L66 | Patterns and guidance to design, configure, and harden highly available, zone-resilient, and disaster-ready architectures for key Azure services and workloads. |
| Decision Making | L67-L74 | Guidance on choosing Azure regions and services for reliability, including region types, geo-pairing, multiregion-capable services, and nonregional (global) services. |
| Architecture & Design Patterns | L75-L80 | Designing Azure apps for high availability using availability zones and multiple regions, including zonal vs zone-redundant deployments, hardening patterns, and multiregion strategies in nonpaired regions. |
| Limits & Quotas | L81-L86 | Guidance on Azure Queue Storage message size limits and designing reliable, scalable Azure Web PubSub apps under service quotas and constraints |
| Deployment | L87-L90 | Which Azure services support availability zones in each region, how to check zone support, and guidance for deploying zone-redundant, highly available workloads. |
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.