deploy-model

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 deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

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 routing skill with concrete executable commands and strong validation checkpoints, but it carries some redundant explanatory prose and its progressive-disclosure references are partly broken: the linked sub-skills are absent and the bundled URL-generation scripts are never referenced from the body.

Suggestions

Tighten the opening scope paragraph and the routing-tip prose — the quick-reference and routing-rule tables already convey this information, so the surrounding explanation can be trimmed for token efficiency.

Fix broken progressive-disclosure links: either restore the preset/SKILL.md, customize/SKILL.md, and capacity/SKILL.md sub-skills, or inline the essential parts and drop the links so navigation is not dangling.

Reference the existing scripts/generate_deployment_url.sh and .ps1 from the body (e.g., in a post-deployment step) so the bundled assets are discoverable and tied into the workflow.

Dimension	Reasoning	Score
Conciseness	The routing tables and intent-detection diagrams are efficient, but the opening scope block re-explains azd-managed project context at length and some explanatory prose ('Users who want customization will typically use explicit keywords...') restates what the table already shows; mostly efficient but could be tightened, matching level 2.	2 / 3
Actionability	Provides fully executable commands (az cognitiveservices model list, usage list) with concrete jq/filter guidance and exact usage-name patterns, plus copy-paste confirmation dialogs, matching the level-3 anchor for executable copy-paste-ready guidance.	3 / 3
Workflow Clarity	Multi-step flows are explicitly sequenced with validation checkpoints — the required confirmation step before deploying, and the pre-deployment validation loop (query model SKUs, check quota, only present passing options) with explicit warnings, matching the level-3 anchor for clear sequence with explicit validation and feedback loops.	3 / 3
Progressive Disclosure	The body is cleanly organized as an overview with one-level-deep sub-skill links (preset/customize/capacity), but those referenced paths do not exist in the bundle and the provided scripts/generate_deployment_url.* are not referenced anywhere in the body; structure is present but references are incompletely signaled/verified, matching level 2.	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 high-quality, third-person description that concretely enumerates capabilities, supplies abundant natural trigger terms, and explicitly separates use-cases from exclusions to minimize routing conflicts. It is dense but every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects' — matching the level-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (the three deployment modes) and when via 'USE FOR:' and 'DO NOT USE FOR:' clauses, matching the level-3 anchor for clear what-and-when with explicit triggers.	3 / 3
Trigger Term Quality	Strong natural-language trigger coverage ('deploy gpt', 'set up model', 'find capacity', 'where can I deploy', 'best region for model'); these are phrases a user would actually say, matching the level-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The 'DO NOT USE FOR' list actively disambiguates from listing deployments, deletion, agent creation, and project creation, giving it a clear niche unlikely to conflict, matching the level-3 anchor.	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: 6 missing, 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.