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).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-5

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

A well-structured, action-oriented skill body that sequences a 14-phase deployment workflow with validation checkpoints and cleanly delegates detailed scripts to one-level-deep reference files. Minor conciseness gains are available by de-duplicating the phase listing.

Suggestions

Remove the duplicate 14-phase enumeration: keep it only in the 'Phase Summaries' table and have 'Workflow Overview' reference it, or vice versa, to cut ~15 redundant lines.

Tighten the 'Quick Reference' table so it does not restate items already covered in 'When to Use This Skill', keeping it to net-new facts (authentication, tools, SKU support).

Inline one minimal end-to-end 'az cognitiveservices account deployment create' example in the body so the common case is copy-paste ready without loading the workflow reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient using tables and phase summaries rather than prose, but the 14-phase list appears in both the 'Workflow Overview' code block and the 'Phase Summaries' table, and the Quick Reference table partly reiterates the When-to-Use section — minor redundancy that could be trimmed.	4 / 5
Actionability	Embeds concrete CLI commands (az cognitiveservices account list-models, deployment create) and a validation regex, with copy-paste-ready troubleshooting commands; however the bulk of executable scripts and capacity formulas are deferred to reference files, leaving minor gaps inline.	4 / 5
Workflow Clarity	A clear 14-phase sequence with explicit validation checkpoints — Phase 7 validates min/max/step at input, Phase 12 requires review/confirm before proceeding, and error handling marks deployment as 'BLOCKED' without valid quota data — providing strong feedback loops for this deployment operation.	5 / 5
Progressive Disclosure	The body is a concise overview that points to two real, one-level-deep reference files (customize-workflow.md, customize-guides.md) via clearly signaled '> MUST READ' and 'load references/...' callouts, with content appropriately split and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

A high-quality description that is specific, comprehensive, and well-bounded. It uses third-person voice, lists concrete capabilities, supplies abundant natural trigger terms, and explicitly disambiguates from the related preset skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy, and advanced options (dynamic quota, priority processing, spillover) — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (interactive guided deployment flow with step-by-step selection) and 'when' (concrete 'USE FOR' trigger phrases plus a 'DO NOT USE FOR' boundary), matching the score-5 anchor.	5 / 5
Trigger Term Quality	The 'USE FOR' clause provides comprehensive natural trigger phrases including synonyms ('PTU deployment' / 'provisioned throughput', 'customize model deployment' / 'custom deployment') that users would naturally say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (custom Azure OpenAI deployment) with distinct triggers and an explicit 'DO NOT USE FOR: quick deployment to optimal region (use preset)' boundary that disambiguates it from the sibling preset skill.	5 / 5
	Total	20 / 20 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
Path: .github/plugins/azure-skills/skills/microsoft-foundry/models/deploy-model/customize/SKILL.md
Commit: 16dc8c5

Reviewed: about 12 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.