From azure-agent-skills
Provides expert guidance for Azure CycleCloud development including troubleshooting, architecture, security, and integration with Slurm/LSF/HTCondor. Use when automating CycleCloud via API/CLI or tuning autoscaling.
How this skill is triggered — by the user, by Claude, or both
Slash command
/azure-agent-skills:azure-cyclecloudThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides expert guidance for Azure CycleCloud. Covers troubleshooting, best practices, decision making, architecture & design patterns, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
This skill provides expert guidance for Azure CycleCloud. Covers troubleshooting, best practices, decision making, architecture & design patterns, 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 |
|---|---|---|
| Troubleshooting | L36-L42 | Troubleshooting CycleCloud errors, node startup failures, and locating/analyzing server/node log files to diagnose and resolve deployment or runtime issues. |
| Best Practices | L43-L47 | Guidance for configuring and tuning Azure HB/HC-series HPC VMs in CycleCloud, including networking, storage, MPI, BIOS, and performance best practices. |
| Decision Making | L48-L55 | Guidance on VM placement/availability sets, choosing custom images, planning migration from CycleCloud 7, and using Spot VMs for cost-effective, resilient CycleCloud clusters. |
| Architecture & Design Patterns | L56-L60 | Architectural guidance for designing, deploying, and operating resilient, scalable multi‑region Azure HPC clusters with CycleCloud, including networking, failover, and regional topology patterns. |
| Security | L61-L75 | Securing CycleCloud: auth methods (Entra, service principals, managed identities), SSL, SSH/Bastion access, SELinux, and network security for clusters, nodes, and the web portal |
| Configuration | L76-L121 | Designing, installing, and tuning CycleCloud clusters: templates, networking, storage, autoscaling, security/SSH, proxies, events, CLI/server setup, and node/volume configuration. |
| Integrations & Coding Patterns | L122-L142 | APIs, CLI, and Python client for automating CycleCloud, plus patterns to integrate schedulers (Slurm, Grid Engine, HTCondor, LSF, OpenPBS, HPC Pack), NFS, OOD, Prometheus/Grafana, and Event Grid |
| Deployment | L143-L153 | Installing, upgrading, and deploying Azure CycleCloud and Slurm workspaces (CLI/ARM/containers), plus planning production setups and moving cluster resources between resource groups. |
| Topic | URL |
|---|---|
| Interpret and resolve common Azure CycleCloud error messages | https://learn.microsoft.com/en-us/azure/cyclecloud/error-messages?view=cyclecloud-8 |
| Diagnose and report Azure CycleCloud node startup issues | https://learn.microsoft.com/en-us/azure/cyclecloud/how-to/report-issues?view=cyclecloud-8 |
| Locate Azure CycleCloud server and node log files | https://learn.microsoft.com/en-us/azure/cyclecloud/log-locations?view=cyclecloud-8 |
| Topic | URL |
|---|---|
| Apply HB/HC VM best practices in Azure CycleCloud | https://learn.microsoft.com/en-us/azure/cyclecloud/how-to/hb-hc-best-practices?view=cyclecloud-8 |
| Topic | URL |
|---|---|
| Choose VM placement models and availability sets in CycleCloud | https://learn.microsoft.com/en-us/azure/cyclecloud/how-to/availability-sets?view=cyclecloud-8 |
| Select and configure custom images for CycleCloud clusters | https://learn.microsoft.com/en-us/azure/cyclecloud/how-to/create-custom-image?view=cyclecloud-8 |
| Plan migration for Azure CycleCloud 7 retirement | https://learn.microsoft.com/en-us/azure/cyclecloud/how-to/cyclecloud7-retirement-guide?view=cyclecloud-8 |
| Use Spot VMs effectively in Azure CycleCloud clusters | https://learn.microsoft.com/en-us/azure/cyclecloud/how-to/use-spot-instances?view=cyclecloud-8 |
| Topic | URL |
|---|---|
| Design and deploy multi‑region Azure HPC clusters | https://learn.microsoft.com/en-us/azure/cyclecloud/concepts/multi-region-cluster-deployment?view=cyclecloud-8 |
npx claudepluginhub microsoftdocs/agent-skills --plugin azure-agent-skillsExpert guidance for Azure HPC Cache: troubleshooting, best practices, architecture, configuration, and deployment. Helps with namespaces, NFS/Blob targets, client access, data ingest, and cache failover.
Routes Azure tasks to the right specialist agent from a catalog. Classifies tasks into domains (architecture, containers, database, etc.) and dispatches single agents or parallel teams. Does not answer Azure questions itself.
Provides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.