customize

Name: customize
Author: microsoft

1.3kstars215forks

How to install customize?

microsoft/azure-skills/customize

$npx -y skills add microsoft/azure-skills --skill customize

Installs into the current project.

Summary

Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing,

Files · 1

View on GitHub

SKILL.md

1	# Customize Model Deployment
2
3	Interactive guided workflow for deploying Azure OpenAI models with full customization control over version, SKU, capacity, content filtering, and advanced options.
4
5	## Quick Reference
6
7	\| Property \| Description \|
8	\|----------\|-------------\|
9	\| Flow \| Interactive step-by-step guided deployment \|
10	\| Customization \| Version, SKU, Capacity, RAI Policy, Advanced Options \|
11	\| SKU Support \| GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard \|
12	\| Best For \| Precise control over deployment configuration \|
13	\| Authentication \| Azure CLI (`az login`) \|
14	\| Tools \| Azure CLI, MCP tools (optional) \|
15
16	## When to Use This Skill
17
18	Use this skill when you need precise control over deployment configuration:
19
20	- ✅ Choose specific model version (not just latest)
21	- ✅ Select deployment SKU (GlobalStandard vs Standard vs PTU)
22	- ✅ Set exact capacity within available range
23	- ✅ Configure content filtering (RAI policy selection)
24	- ✅ Enable advanced features (dynamic quota, priority processing, spillover)
25	- ✅ PTU deployments (Provisioned Throughput Units)
26
27	Alternative: Use `preset` for quick deployment to the best available region with automatic configuration.
28
29	### Comparison: customize vs preset
30
31	\| Feature \| customize \| preset \|
32	\|---------\|---------------------\|----------------------------\|
33	\| Focus \| Full customization control \| Optimal region selection \|
34	\| Version Selection \| User chooses from available \| Uses latest automatically \|
35	\| SKU Selection \| User chooses (GlobalStandard/Standard/PTU) \| GlobalStandard only \|
36	\| Capacity \| User specifies exact value \| Auto-calculated (50% of available) \|
37	\| RAI Policy \| User selects from options \| Default policy only \|
38	\| Region \| Current region first, falls back to all regions if no capacity \| Checks capacity across all regions upfront \|
39	\| Use Case \| Precise deployment requirements \| Quick deployment to best region \|
40
41	## Prerequisites
42
43	- Azure subscription with Cognitive Services Contributor or Owner role
44	- Azure AI Foundry project resource ID (format: `/subscriptions/{sub}/resourceGroups/{rg}/providers/Microsoft.CognitiveServices/accounts/{account}/projects/{project}`)
45	- Azure CLI installed and authenticated (`az login`)
46	- Optional: Set `PROJECT_RESOURCE_ID` environment variable
47
48	## Workflow Overview
49
50	### Complete Flow (14 Phases)
51
52	```
53	1. Verify Authentication
54	2. Get Project Resource ID
55	3. Verify Project Exists
56	4. Get Model Name (if not provided)
57	5. List Model Versions → User Selects
58	6. List SKUs for Version → User Selects
59	7. Get Capacity Range → User Configures
60	7b. If no capacity: Cross-Region Fallback → Query all regions → User selects region/project
61	8. List RAI Policies → User Selects
62	9. Configure Advanced Options (if applicable)
63	10. Configure Version Upgrade Policy
64	11. Generate Deployment Name
65	12. Review Configuration
66	13. Execute Deployment & Monitor
67	```
68
69	### Fast Path (Defaults)
70
71	If user accepts all defaults (latest version, GlobalStandard SKU, recommended capacity, default RAI policy, standard upgrade policy), deployment completes in ~5 interactions.
72
73	---
74
75	## Phase Summaries
76
77	> ⚠️ MUST READ: Before executing any phase, load [references/customize-workflow.md](references/customize-workflow.md) for the full scripts and implementation details. The summaries below describe what each phase does — the reference file contains the how (CLI commands, quota patterns, capacity formulas, cross-region fallback logic).
78
79	\| Phase \| Action \| Key Details \|
80	\|-------\|--------\|-------------\|
81	\| 1. Verify Auth \| Check `az account show`; prompt `az login` if needed \| Verify correct subscription is active \|
82	\| 2. Get Project ID \| Read `PROJECT_RESOURCE_ID` env var or prompt user \| ARM resource ID format required \|
83	\| 3. Verify Project \| Parse resource ID, call `az cognitiveservices account show` \| Extracts subscription, RG, account, project, region \|
84	\| 4. Get Model \| List models via `az cognitiveservices account list-models` \| User selects from available or enters custom name \|
85	\| 5. Select Version \| Query versions for chosen model \| Recommend latest; user picks from list \|
86	\| 6. Select SKU \| Query model catalog + subscription quota, show only deployable SKUs \| ⚠️ Never hardcode SKU list

People who liked this also viewed

6 picks

Type

customize

1.3kstars215forks

View on GitHub

How to install customize?

microsoft/azure-skills/customize

$npx -y skills add microsoft/azure-skills --skill customize

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Customize Model Deployment
2
3	Interactive guided workflow for deploying Azure OpenAI models with full customization control over version, SKU, capacity, content filtering, and advanced options.
4
5	## Quick Reference
6
7	\| Property \| Description \|
8	\|----------\|-------------\|
9	\| Flow \| Interactive step-by-step guided deployment \|
10	\| Customization \| Version, SKU, Capacity, RAI Policy, Advanced Options \|
11	\| SKU Support \| GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard \|
12	\| Best For \| Precise control over deployment configuration \|
13	\| Authentication \| Azure CLI (`az login`) \|
14	\| Tools \| Azure CLI, MCP tools (optional) \|
15
16	## When to Use This Skill
17
18	Use this skill when you need precise control over deployment configuration:
19
20	- ✅ Choose specific model version (not just latest)
21	- ✅ Select deployment SKU (GlobalStandard vs Standard vs PTU)
22	- ✅ Set exact capacity within available range
23	- ✅ Configure content filtering (RAI policy selection)
24	- ✅ Enable advanced features (dynamic quota, priority processing, spillover)
25	- ✅ PTU deployments (Provisioned Throughput Units)
26
27	Alternative: Use `preset` for quick deployment to the best available region with automatic configuration.
28
29	### Comparison: customize vs preset
30
31	\| Feature \| customize \| preset \|
32	\|---------\|---------------------\|----------------------------\|
33	\| Focus \| Full customization control \| Optimal region selection \|
34	\| Version Selection \| User chooses from available \| Uses latest automatically \|
35	\| SKU Selection \| User chooses (GlobalStandard/Standard/PTU) \| GlobalStandard only \|
36	\| Capacity \| User specifies exact value \| Auto-calculated (50% of available) \|
37	\| RAI Policy \| User selects from options \| Default policy only \|
38	\| Region \| Current region first, falls back to all regions if no capacity \| Checks capacity across all regions upfront \|
39	\| Use Case \| Precise deployment requirements \| Quick deployment to best region \|
40
41	## Prerequisites
42
43	- Azure subscription with Cognitive Services Contributor or Owner role
44	- Azure AI Foundry project resource ID (format: `/subscriptions/{sub}/resourceGroups/{rg}/providers/Microsoft.CognitiveServices/accounts/{account}/projects/{project}`)
45	- Azure CLI installed and authenticated (`az login`)
46	- Optional: Set `PROJECT_RESOURCE_ID` environment variable
47
48	## Workflow Overview
49
50	### Complete Flow (14 Phases)
51
52	```
53	1. Verify Authentication
54	2. Get Project Resource ID
55	3. Verify Project Exists
56	4. Get Model Name (if not provided)
57	5. List Model Versions → User Selects
58	6. List SKUs for Version → User Selects
59	7. Get Capacity Range → User Configures
60	7b. If no capacity: Cross-Region Fallback → Query all regions → User selects region/project
61	8. List RAI Policies → User Selects
62	9. Configure Advanced Options (if applicable)
63	10. Configure Version Upgrade Policy
64	11. Generate Deployment Name
65	12. Review Configuration
66	13. Execute Deployment & Monitor
67	```
68
69	### Fast Path (Defaults)
70
71	If user accepts all defaults (latest version, GlobalStandard SKU, recommended capacity, default RAI policy, standard upgrade policy), deployment completes in ~5 interactions.
72
73	---
74
75	## Phase Summaries
76
77	> ⚠️ MUST READ: Before executing any phase, load [references/customize-workflow.md](references/customize-workflow.md) for the full scripts and implementation details. The summaries below describe what each phase does — the reference file contains the how (CLI commands, quota patterns, capacity formulas, cross-region fallback logic).
78
79	\| Phase \| Action \| Key Details \|
80	\|-------\|--------\|-------------\|
81	\| 1. Verify Auth \| Check `az account show`; prompt `az login` if needed \| Verify correct subscription is active \|
82	\| 2. Get Project ID \| Read `PROJECT_RESOURCE_ID` env var or prompt user \| ARM resource ID format required \|
83	\| 3. Verify Project \| Parse resource ID, call `az cognitiveservices account show` \| Extracts subscription, RG, account, project, region \|
84	\| 4. Get Model \| List models via `az cognitiveservices account list-models` \| User selects from available or enters custom name \|
85	\| 5. Select Version \| Query versions for chosen model \| Recommend latest; user picks from list \|
86	\| 6. Select SKU \| Query model catalog + subscription quota, show only deployable SKUs \| ⚠️ Never hardcode SKU list

People who liked this also viewed

6 picks

Type