Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoftdocs/azure-confidential-computing
Expert knowledge for Azure Confidential Computing development including decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Passed 11 of 16 test cases with the skill, and 14 of 16 without it.
2 fixed14 passed either way1 still failing6 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A test case the skill fixed. Same model, same prompt, with and without the skill.
In addition to disabling background agents, what user account management step is recommended when hardening Linux custom OS images for confidential VMs?
| Checked | Without skill | With skill |
|---|---|---|
| The response identifies removing administrative or sudo users. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill provides expert guidance for Azure Confidential Computing. Covers 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), 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 |
|---|---|---|
| Decision Making | L35-L46 | Guidance on choosing Azure confidential computing options: VMs (AMD/Intel), containers, GPUs, deployment models, capabilities, products, and use cases for secure workloads. |
| Architecture & Design Patterns | L47-L56 | Architectural patterns and design guidance for using Azure confidential VMs, SGX enclaves, AKS, and multi-party analytics to build secure AI and containerized workloads. |
| Limits & Quotas | L57-L62 | Intel SGX capacity, quotas, and sizing for Azure confidential computing: AKS confidential node limits, SGX VM sizing guidance, and FAQ on SGX resource constraints. |
| Security | L63-L77 | Security, attestation, and key/secrets management for Azure confidential workloads: SGX enclaves, CVMs, vTPM, AKS confidential containers, clean rooms, and hardening Linux images. |
| Configuration | L78-L89 | Configuring and deploying Azure confidential VMs and AKS (SGX, containers), managing keys and secure key release policies, and using/opt-ing out of VMMD metablob disks. |
| Integrations & Coding Patterns | L90-L100 | Coding patterns and samples for building, running, and attesting Intel SGX/AMD SEV-SNP confidential apps and containers, including SKR flows, tools, and Fortanix/Key Vault integrations. |
| Deployment | L101-L109 | How to deploy and migrate Azure confidential VMs/VMSS and AKS (SGX and confidential node pools), create custom images, and set up Fortanix CCM using CLI and ARM templates. |
| Topic | URL |
test cases passed, vs 14 / 16 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.