customize

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, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).

4.45x

Quality

—

Does it follow best practices?

Impact

89%

4.45x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content provides a clear, well-validated multi-phase workflow with sound progressive disclosure to real reference files. It is slightly held back by redundant restating of guide content and limited executable code in the main body.

Suggestions

Trim duplicated SKU/capacity/advanced-option detail from the main body since it is covered in references/customize-guides.md, keeping only the pointer.

Add a minimal copy-paste-ready deployment command example in the body rather than only in the reference, to raise actionability.

Collapse the Comparison and Quick Reference tables where they restate the frontmatter description to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but repeats the SKU list, capacity ranges, and advanced-option descriptions that already appear in the referenced guides, and the Quick Reference / When to Use / Comparison tables restate the description, adding some padding.	2 / 3
Actionability	Phase summaries name commands but defer the executable scripts to references; the body itself shows only generic troubleshooting commands and capacity formula text rather than copy-paste-ready deployment commands, landing between concrete and incomplete.	2 / 3
Workflow Clarity	A clearly numbered 13-phase sequence with explicit validation checkpoints (auth verification, capacity min/max/step validation, review-before-proceed, deployment-blocked-on-quota) and an error-handling table with resolutions, satisfying the top anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points one level deep to real, well-signaled references (customize-workflow.md, customize-guides.md), both of which exist in ./references/, with clear MUST READ callouts; navigation is easy.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and explicitly answers both what and when, with a clear contrast against the preset skill to reduce conflict. Third-person voice is used throughout. Minor verbosity is the only drawback.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — selection of model version, SKU (with named types), capacity, RAI policy, and advanced options (dynamic quota, priority processing, spillover) — matching the top anchor.	3 / 3
Completeness	Explicitly states what the skill does AND when to use it via a 'USE FOR' clause, plus a 'DO NOT USE FOR' clause with a redirect to preset, satisfying both what and when.	3 / 3
Trigger Term Quality	Includes a broad, natural trigger list ('custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter') that maps well to phrasing a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The 'DO NOT USE FOR: quick deployment to optimal region (use preset)' clause carves out a distinct niche from the sibling preset skill, lowering conflict risk.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/azure-skills
Commit: 2cd48ca

Reviewed: about 8 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.