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).
83
75%
Does it follow best practices?
Impact
96%
4.17xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugin/skills/microsoft-foundry/models/deploy-model/preset/SKILL.mdQuality
Discovery
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.
This is a strong skill description that excels across all dimensions. It clearly articulates specific capabilities (deploying Azure OpenAI models with automatic region capacity analysis), provides comprehensive trigger terms via the USE FOR clause, and explicitly defines boundaries with the DO NOT USE FOR clause to minimize conflicts with related skills. The description is well-structured and concise while being information-dense.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: deploys Azure OpenAI models, analyzes capacity across regions, checks current region first, shows alternatives. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (deploys Azure OpenAI models to optimal regions by analyzing capacity) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with specific trigger scenarios and boundary conditions). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'quick deployment', 'optimal region', 'best region', 'automatic region selection', 'fast setup', 'multi-region capacity check', 'high availability deployment', 'deploy to best location'. Also includes negative triggers to reduce false matches. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit DO NOT USE FOR clauses that delineate boundaries against a 'customize' skill. The focus on automatic/optimal region selection creates a clear niche distinct from manual configuration skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a solid structural overview of the Azure OpenAI deployment workflow with clear dual-path logic and useful error handling. However, it falls short on actionability—lacking complete executable command sequences for the core workflow—and on workflow clarity by missing validation checkpoints and feedback loops for what is essentially a multi-step cloud deployment operation. The referenced bundle file (references/workflow.md) is absent, undermining the progressive disclosure strategy.
Suggestions
Add complete, executable command sequences for the core deployment workflow with templated parameters (e.g., `az rest --method GET --url 'https://management.azure.com/subscriptions/{sub-id}/providers/Microsoft.CognitiveServices/locations/{location}/modelCapacities?api-version=2024-10-01'`)
Add explicit validation checkpoints after deployment creation (e.g., poll deployment status and verify provisioningState=Succeeded before reporting success)
Either provide the referenced references/workflow.md bundle file or inline the critical step-by-step details; the current state leaves a gap in the guidance
Remove the 'What This Skill Does' numbered list since it duplicates the Quick Workflow and Deployment Phases sections
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably structured but includes some unnecessary verbosity—the 'What This Skill Does' section largely duplicates the Quick Workflow section, and the deployment phases table repeats information. The Notes section and some explanatory text could be tightened. | 2 / 3 |
Actionability | The skill provides specific Azure CLI commands in the phases table and error handling section, and the Advanced Usage section has executable commands. However, the core workflow lacks complete, copy-paste-ready command sequences—the phases table lists commands but doesn't show full executable examples with parameters filled in or templated. | 2 / 3 |
Workflow Clarity | The two workflow paths (fast path and alternative region path) are clearly diagrammed, and the phases table provides good sequencing. However, there are no explicit validation checkpoints or feedback loops—no 'verify deployment succeeded before proceeding' step, no retry logic for failed deployments, and the monitoring step mentioned in 'What This Skill Does' (#7) isn't elaborated in the workflow. | 2 / 3 |
Progressive Disclosure | The skill references a workflow detail file (references/workflow.md) and a quota skill, which is good progressive disclosure structure. However, no bundle files were provided, so the referenced workflow.md doesn't actually exist, and the main SKILL.md still contains substantial inline detail (the full phases table, error handling table) that could have been offloaded to the referenced file. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- microsoft/github-copilot-for-azure
- Commit
915f809
- Reviewed
Table of Contents
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.