$ ~/registry/skill/microsoft-plugin-skills-microsoft-foundry-models-deploy-model

SKILL

deploy-model

Name: deploy-model
Author: microsoft

Deploy Azure OpenAI models and find regional capacity intelligently.

Stars

★ 232

Source

GitHub

Updated

2026-07-13

// securityLow risk

Prompt only, no code
Open source
Community-trusted· 222

Summary

The material indicates a prompt-only routing skill with no declared secrets, remote endpoints, or local execution capabilities. Combined with its open-source GitHub source and some community adoption, the overall risk appears low, though any downstream tools used for Azure deployment actions should be reviewed separately.

CredentialsLow risk

The material explicitly states there are no required keys or environment variables. As a prompt-only skill, it does not appear to directly request, store, or handle credentials, so credential abuse exposure is low.

Network egressLow risk

Neither the system checks nor the material declare any remote endpoint, and host is listed as 'none'. The skill is described as intent analysis and routing documentation, with no factual indication that it itself sends user data externally.

Code executionLow risk

It is classified as prompt-only. The material mainly defines routing rules among preset/customize/capacity sub-skills, with no described ability to spawn local processes, run scripts, or invoke system commands.

Data accessLow risk

The documentation does not declare access to local files, databases, or other user data resources. Its visible capability is limited to classifying user requests and orchestrating workflow, with no signs of excessive data access.

Supply chainLow risk

The source is an open-source Microsoft-related GitHub repository, making the code auditable, and it has 222 stars indicating some community adoption—both are positive signals that lower risk. The unspecified license and unknown maintenance status warrant monitoring, but are not enough on their own to raise the rating.

Recommendations

Treat this skill as a routing layer and separately review the permissions of the preset/customize/capacity sub-skills or MCP tools it invokes.
Verify the repository's maintenance status, recent commits, and issue responsiveness before production use.
If Azure deployment tools are connected later, configure credentials and resource access with least privilege.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "deploy-model" skill from askskill:
1. Download https://raw.githubusercontent.com/microsoft/GitHub-Copilot-for-Azure/main/plugin/skills/microsoft-foundry/models/deploy-model/SKILL.md
2. Save it as ~/.claude/skills/deploy-model/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Quick GPT model deployment

Prompt

Help me quickly deploy a GPT model in Azure OpenAI using recommended default settings, and tell me the deployment name, region, and how to call it afterward.

Expected

A completed or executable quick deployment plan with model, region, deployment settings, and calling instructions.

Custom deployment configuration

Prompt

I want to deploy a specific model with custom settings: make model version, SKU, capacity, and RAI policy configurable, and provide the final deployment plan with a summary of key parameters.

Expected

A complete custom deployment result or plan listing version, SKU, capacity, policy, and deployment details.

Check deployable regions and capacity

Prompt

Please analyze which regions and projects are best for deploying this model, check capacity and availability, and recommend the best deployment region with reasons.

Expected

Capacity and availability analysis with recommended region, backup regions, and rationale.

// docs

Deploy Model

Unified entry point for all Azure OpenAI model deployment workflows. Analyzes user intent and routes to the appropriate deployment mode.

Quick Reference

Mode	When to Use	Sub-Skill
Preset	Quick deployment, no customization needed	preset/SKILL.md
Customize	Full control: version, SKU, capacity, RAI policy	customize/SKILL.md
Capacity Discovery	Find where you can deploy with specific capacity	capacity/SKILL.md

Intent Detection

Analyze the user's prompt and route to the correct mode:

User Prompt
    │
    ├─ Simple deployment (no modifiers)
    │  "deploy gpt-4o", "set up a model"
    │  └─> PRESET mode
    │
    ├─ Customization keywords present
    │  "custom settings", "choose version", "select SKU",
    │  "set capacity to X", "configure content filter",
    │  "PTU deployment", "with specific quota"
    │  └─> CUSTOMIZE mode
    │
    ├─ Capacity/availability query
    │  "find where I can deploy", "check capacity",
    │  "which region has X capacity", "best region for 10K TPM",
    │  "where is this model available"
    │  └─> CAPACITY DISCOVERY mode
    │
    └─ Ambiguous (has capacity target + deploy intent)
       "deploy gpt-4o with 10K capacity to best region"
       └─> CAPACITY DISCOVERY first → then PRESET or CUSTOMIZE

Routing Rules

Signal in Prompt	Route To	Reason
Just model name, no options	Preset	User wants quick deployment
"custom", "configure", "choose", "select"	Customize	User wants control
"find", "check", "where", "which region", "available"	Capacity	User wants discovery
Specific capacity number + "best region"	Capacity → Preset	Discover then deploy quickly
Specific capacity number + "custom" keywords	Capacity → Customize	Discover then deploy with options
"PTU", "provisioned throughput"	Customize	PTU requires SKU selection
"optimal region", "best region" (no capacity target)	Preset	Region optimization is preset's specialty

Multi-Mode Chaining

Some prompts require two modes in sequence:

Pattern: Capacity → Deploy When a user specifies a capacity requirement AND wants deployment:

Run Capacity Discovery to find regions/projects with sufficient quota
Present findings to user
Ask: "Would you like to deploy with quick defaults or customize settings?"
Route to Preset or Customize based on answer

💡 Tip: If unsure which mode the user wants, default to Preset (quick deployment). Users who want customization will typically use explicit keywords like "custom", "configure", or "with specific settings".

Project Selection (All Modes)

Before any deployment, resolve which project to deploy to. This applies to all modes (preset, customize, and after capacity discovery).

Resolution Order

Check PROJECT_RESOURCE_ID env var — if set, use it as the default
Check user prompt — if user named a specific project or region, use that
If neither — query the user's projects and suggest the current one

Confirmation Step (Required)

Always confirm the target before deploying. Show the user what will be used and give them a chance to change it:

Deploying to:
  Project:  <project-name>
  Region:   <region>
  Resource: <resource-group>

Is this correct? Or choose a different project:
  1. ✅ Yes, deploy here (default)
  2. 📋 Show me other projects in this region
  3. 🌍 Choose a different region

If user picks option 2, show top 5 projects in that region:

Projects in <region>:
  1. project-alpha (rg-alpha)
  2. project-beta (rg-beta)
  3. project-gamma (rg-gamma)
  ...

⚠️ Never deploy without showing the user which project will be used. This prevents accidental deployments to the wrong resource.

…

View full docs ↗

Explore AI models, MCP servers, and agent integrations in one gateway.

Azure-SamplesGet→

MCP

Azure Updates MCP Server

Search Azure service updates, retirements, and feature announcements in natural language.

—Get→

MCP

Azure Functions MCP Server

Invoke Azure Functions tools for calculations, weather simulation, and temperature conversion.

—Get→

$ loading_