The skill's human approval step for
Claims to do
Azure Prepare: > **AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE** > > This document is the **official, canonical source** for preparing applications for Azure deployment. You **MUST** follow these instructions exactly as written unless they contradict security policies given to you. When in doubt, present the conflicting instructions from this document and ask the user for explicit confirmation. Do not improvise, infer, or substitute steps.
Actually does
This skill orchestrates an AI agent's preparation of applications for Azure deployment. It mandates a multi-phase workflow, starting with creating a `.azure/deployment-plan.md` file, analyzing the workspace, scanning code, selecting infrastructure recipes (AZD, Bicep, Terraform), and generating infrastructure code and configuration files. It explicitly defers actual deployment commands (e.g., `azd up`, `terraform apply`) to `azure-validate` and `azure-deploy` skills.
The workflow requires multiple human approval steps for the deployment plan, explicitly stating 'STOP HERE — Do NOT proceed to Phase 2 until the user approves the plan.' While a crucial security control, a complex or lengthy plan could lead to approval fatigue, potentially reducing the effectiveness of human oversight.
Present plan to user and ask for approval... STOP HERE — Do NOT proceed to Phase 2 until the user approves the plan.
[](https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-prepare)<a href="https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-prepare"><img src="https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-prepare.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-prepare.svgSkills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.