deploy-model

Name: deploy-model
Author: microsoft

1.3kstars215forks

How to install deploy-model?

microsoft/azure-skills/deploy-model

$npx -y skills add microsoft/azure-skills --skill deploy-model

Installs into the current project.

Summary

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deplo

Files · 1

View on GitHub

SKILL.md

1	# Deploy Model
2
3	> Scope — read this first. This skill creates model deployments out-of-band via Azure CLI / MCP / portal. For azd-managed Foundry projects (those scaffolded from `azd-ai-starter-basic` or via `azd ai agent init`), declare deployments in `azure.yaml services.ai-project.deployments[]` instead — `azd ai agent init` writes the entry from the sample manifest and `azd provision` creates the deployment through Bicep. See [foundry-agent/create/create-hosted.md](../../foundry-agent/create/create-hosted.md) for the Golden Path. Use this skill only for: (a) Foundry projects not managed by an azd project, (b) ad-hoc deployments outside the azd lifecycle.
4
5	Unified entry point for all Azure OpenAI model deployment workflows. Analyzes user intent and routes to the appropriate deployment mode.
6
7	## Quick Reference
8
9	\| Mode \| When to Use \| Sub-Skill \|
10	\|------\|-------------\|-----------\|
11	\| Preset \| Quick deployment, no customization needed \| [preset/SKILL.md](preset/SKILL.md) \|
12	\| Customize \| Full control: version, SKU, capacity, RAI policy \| [customize/SKILL.md](customize/SKILL.md) \|
13	\| Capacity Discovery \| Find where you can deploy with specific capacity \| [capacity/SKILL.md](capacity/SKILL.md) \|
14
15	## Intent Detection
16
17	Analyze the user's prompt and route to the correct mode:
18
19	```
20	User Prompt
21	│
22	├─ Simple deployment (no modifiers)
23	│ "deploy gpt-4o", "set up a model"
24	│ └─> PRESET mode
25	│
26	├─ Customization keywords present
27	│ "custom settings", "choose version", "select SKU",
28	│ "set capacity to X", "configure content filter",
29	│ "PTU deployment", "with specific quota"
30	│ └─> CUSTOMIZE mode
31	│
32	├─ Capacity/availability query
33	│ "find where I can deploy", "check capacity",
34	│ "which region has X capacity", "best region for 10K TPM",
35	│ "where is this model available"
36	│ └─> CAPACITY DISCOVERY mode
37	│
38	└─ Ambiguous (has capacity target + deploy intent)
39	"deploy gpt-4o with 10K capacity to best region"
40	└─> CAPACITY DISCOVERY first → then PRESET or CUSTOMIZE
41	```
42
43	### Routing Rules
44
45	\| Signal in Prompt \| Route To \| Reason \|
46	\|------------------\|----------\|--------\|
47	\| Just model name, no options \| Preset \| User wants quick deployment \|
48	\| "custom", "configure", "choose", "select" \| Customize \| User wants control \|
49	\| "find", "check", "where", "which region", "available" \| Capacity \| User wants discovery \|
50	\| Specific capacity number + "best region" \| Capacity → Preset \| Discover then deploy quickly \|
51	\| Specific capacity number + "custom" keywords \| Capacity → Customize \| Discover then deploy with options \|
52	\| "PTU", "provisioned throughput" \| Customize \| PTU requires SKU selection \|
53	\| "optimal region", "best region" (no capacity target) \| Preset \| Region optimization is preset's specialty \|
54
55	### Multi-Mode Chaining
56
57	Some prompts require two modes in sequence:
58
59	Pattern: Capacity → Deploy
60	When a user specifies a capacity requirement AND wants deployment:
61	1. Run Capacity Discovery to find regions/projects with sufficient quota
62	2. Present findings to user
63	3. Ask: "Would you like to deploy with quick defaults or customize settings?"
64	4. Route to Preset or Customize based on answer
65
66	> 💡 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".
67
68	## Project Selection (All Modes)
69
70	Before any deployment, resolve which project to deploy to. This applies to all modes (preset, customize, and after capacity discovery).
71
72	### Resolution Order
73
74	1. Check `PROJECT_RESOURCE_ID` env var — if set, use it as the default
75	2. Check user prompt — if user named a specific project or region, use that
76	3. If neither — query the user's projects and suggest the current one
77
78	### Confirmation Step (Required)
79
80	Always confirm the target before deploying. Show the user what will be used and give them a chance to change it:
81
82	```
83	Deploying to:
84	Project: <project-name>
85	Region: <region>
86	Resource: <resource-group>
87
88	Is this correct? Or choose a different project:
89	1. ✅ Yes, deploy here (default)
90	2. 📋

People who liked this also viewed

6 picks

Type

deploy-model

1.3kstars215forks

View on GitHub

How to install deploy-model?

microsoft/azure-skills/deploy-model

$npx -y skills add microsoft/azure-skills --skill deploy-model

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Deploy Model
2
3	> Scope — read this first. This skill creates model deployments out-of-band via Azure CLI / MCP / portal. For azd-managed Foundry projects (those scaffolded from `azd-ai-starter-basic` or via `azd ai agent init`), declare deployments in `azure.yaml services.ai-project.deployments[]` instead — `azd ai agent init` writes the entry from the sample manifest and `azd provision` creates the deployment through Bicep. See [foundry-agent/create/create-hosted.md](../../foundry-agent/create/create-hosted.md) for the Golden Path. Use this skill only for: (a) Foundry projects not managed by an azd project, (b) ad-hoc deployments outside the azd lifecycle.
4
5	Unified entry point for all Azure OpenAI model deployment workflows. Analyzes user intent and routes to the appropriate deployment mode.
6
7	## Quick Reference
8
9	\| Mode \| When to Use \| Sub-Skill \|
10	\|------\|-------------\|-----------\|
11	\| Preset \| Quick deployment, no customization needed \| [preset/SKILL.md](preset/SKILL.md) \|
12	\| Customize \| Full control: version, SKU, capacity, RAI policy \| [customize/SKILL.md](customize/SKILL.md) \|
13	\| Capacity Discovery \| Find where you can deploy with specific capacity \| [capacity/SKILL.md](capacity/SKILL.md) \|
14
15	## Intent Detection
16
17	Analyze the user's prompt and route to the correct mode:
18
19	```
20	User Prompt
21	│
22	├─ Simple deployment (no modifiers)
23	│ "deploy gpt-4o", "set up a model"
24	│ └─> PRESET mode
25	│
26	├─ Customization keywords present
27	│ "custom settings", "choose version", "select SKU",
28	│ "set capacity to X", "configure content filter",
29	│ "PTU deployment", "with specific quota"
30	│ └─> CUSTOMIZE mode
31	│
32	├─ Capacity/availability query
33	│ "find where I can deploy", "check capacity",
34	│ "which region has X capacity", "best region for 10K TPM",
35	│ "where is this model available"
36	│ └─> CAPACITY DISCOVERY mode
37	│
38	└─ Ambiguous (has capacity target + deploy intent)
39	"deploy gpt-4o with 10K capacity to best region"
40	└─> CAPACITY DISCOVERY first → then PRESET or CUSTOMIZE
41	```
42
43	### Routing Rules
44
45	\| Signal in Prompt \| Route To \| Reason \|
46	\|------------------\|----------\|--------\|
47	\| Just model name, no options \| Preset \| User wants quick deployment \|
48	\| "custom", "configure", "choose", "select" \| Customize \| User wants control \|
49	\| "find", "check", "where", "which region", "available" \| Capacity \| User wants discovery \|
50	\| Specific capacity number + "best region" \| Capacity → Preset \| Discover then deploy quickly \|
51	\| Specific capacity number + "custom" keywords \| Capacity → Customize \| Discover then deploy with options \|
52	\| "PTU", "provisioned throughput" \| Customize \| PTU requires SKU selection \|
53	\| "optimal region", "best region" (no capacity target) \| Preset \| Region optimization is preset's specialty \|
54
55	### Multi-Mode Chaining
56
57	Some prompts require two modes in sequence:
58
59	Pattern: Capacity → Deploy
60	When a user specifies a capacity requirement AND wants deployment:
61	1. Run Capacity Discovery to find regions/projects with sufficient quota
62	2. Present findings to user
63	3. Ask: "Would you like to deploy with quick defaults or customize settings?"
64	4. Route to Preset or Customize based on answer
65
66	> 💡 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".
67
68	## Project Selection (All Modes)
69
70	Before any deployment, resolve which project to deploy to. This applies to all modes (preset, customize, and after capacity discovery).
71
72	### Resolution Order
73
74	1. Check `PROJECT_RESOURCE_ID` env var — if set, use it as the default
75	2. Check user prompt — if user named a specific project or region, use that
76	3. If neither — query the user's projects and suggest the current one
77
78	### Confirmation Step (Required)
79
80	Always confirm the target before deploying. Show the user what will be used and give them a chance to change it:
81
82	```
83	Deploying to:
84	Project: <project-name>
85	Region: <region>
86	Resource: <resource-group>
87
88	Is this correct? Or choose a different project:
89	1. ✅ Yes, deploy here (default)
90	2. 📋

People who liked this also viewed

6 picks

Type