preset

Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).

4.17x

Quality

88%

Does it follow best practices?

Impact

96%

4.17x

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.

A well-structured, highly actionable SKILL.md with a clear sequenced workflow and concrete error recovery. Its main weaknesses are redundant presentation of the same workflow and an unreferenced bundle file (preset-workflow.md).

Suggestions

Collapse 'What This Skill Does', 'Quick Workflow', and the 'Deployment Phases' table into a single sequenced workflow view to remove triple redundancy and reduce tokens.

Link to preset-workflow.md from the body (or note its purpose) so both reference files are discoverable, not just workflow.md.

Replace the `...` placeholder in the Advanced Usage deployment-create example with a complete copy-paste-ready command, or point to the full form in the workflow reference.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient (tables, commands, no concept re-explanation) but presents essentially the same deployment flow three times — 'What This Skill Does', 'Quick Workflow', and the 'Deployment Phases' table — which could be tightened into a single sequenced view.	2 / 3
Actionability	Concrete, executable az CLI commands appear throughout the Deployment Phases table and Advanced Usage section (e.g. `az rest --method GET .../modelCapacities`, `az cognitiveservices account deployment show --query ...`), with specific flags and an actionable error-handling table.	3 / 3
Workflow Clarity	A clear 7-phase sequence, an explicit Fast-Path vs Alternative-Path decision flow, pre-flight validation (auth and capacity checks before deploy), and a symptom→resolution error table providing feedback loops for recovery.	3 / 3
Progressive Disclosure	The overview is well sectioned and clearly signals one-level-deep detail via [references/workflow.md](references/workflow.md), but the bundle file preset-workflow.md is present yet never referenced or navigated from the body, leaving a discovery gap.	2 / 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.

A strong, third-person description that states concrete capabilities, supplies explicit positive and negative trigger guidance, and clearly distinguishes itself from sibling skills. The only minor blemish is the decorative word 'Intelligently'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions', 'checks current region first and shows alternatives if needed' — rather than vague language. The only soft spot is the buzzword 'Intelligently', but the underlying actions are specific.	3 / 3
Completeness	Explicitly answers both 'what' (deploys models to optimal regions by analyzing capacity) and 'when' via an explicit USE FOR trigger clause, plus a DO NOT USE FOR clause for negative triggers.	3 / 3
Trigger Term Quality	The USE FOR clause supplies many natural phrases a user would say — 'quick deployment', 'optimal region', 'best region', 'automatic region selection', 'fast setup', 'deploy to best location' — giving broad, natural coverage.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (Azure OpenAI GlobalStandard region-capacity deployment) and the DO NOT USE FOR clause redirects SKU/version/capacity/PTU cases to the 'customize' skill, making mis-triggering unlikely.	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: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/azure-skills
Commit: 39464cb

Reviewed: about 5 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.