**WORKFLOW SKILL** — Deploy and operate Azure Local Small Form Factor (SFF) for ruggedized/edge single-host scenarios: subscription setup, install (incl. in a VM), connect via portal, run containerized/GPU workloads, and troubleshoot. WHEN: "Azure Local small form factor", "SFF Azure Local", "ruggedized Azure Local", "edge single host Azure Local", "SFF install", "SFF in a VM", "SFF configurator app", "SFF containerized workloads". USE FOR: SFF edge/single-host evaluation and operation. DO NOT USE FOR: multi-node cluster deployment (use azlocal-deploy).
インストール
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
**WORKFLOW SKILL** — Deploy and operate Azure Local Small Form Factor (SFF) for ruggedized/edge single-host scenarios: subscription setup, install (incl. in a VM), connect via portal, run containerized/GPU workloads, and troubleshoot. WHEN: "Azure Local small form factor", "SFF Azure Local", "ruggedized Azure Local", "edge single host Azure Local", "SFF install", "SFF in a VM", "SFF configurator app", "SFF containerized workloads". USE FOR: SFF edge/single-host evaluation and operation. DO NOT USE FOR: multi-node cluster deployment (use azlocal-deploy).
compatibility
Works with Claude Code, GitHub Copilot, VS Code, and any Agent Skills compatible tool.
SFF docs are vendored separately at docs/azure-local-sff/upstream/ (a pinned mirror) — not under docs/upstream/. Prefer those files and this repo's SFF guides, cite the file you used, and treat Microsoft Learn as canonical when the mirror lags.
Triggers
Activate this skill when the user wants to:
Evaluate or deploy Azure Local SFF (including testing in a Hyper-V VM)
Connect an SFF device from the portal and run edge workloads
Troubleshoot an SFF device
Rules
Use the pinned SFF mirror under docs/azure-local-sff/upstream/; cite the exact file used.
Set up the subscription and prerequisites before installing SFF.
For production, require a validated SFF device (per the overview).
Microsoft Learn / discovered governance wins over the mirror on any conflict.
Steps
Set up the subscription and prerequisites for SFF.
Install SFF on hardware or in a VM for evaluation.
Connect from the Azure portal (Configurator App / zero-touch provisioning).
Run workloads (containerized / GPU) and troubleshoot with system logs.
