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 ./.github/plugins/azure-skills/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 provides specific concrete actions, comprehensive trigger terms covering natural user language, explicit 'USE FOR' and 'DO NOT USE FOR' clauses that clearly define scope, and excellent boundary delineation against related skills. The DO NOT USE FOR section is particularly valuable for reducing conflict risk in a multi-skill environment.
| 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 by analyzing capacity across regions) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with specific trigger scenarios and boundary conditions differentiating from the 'customize' skill). | 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'. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit DO NOT USE FOR clauses that delineate boundaries against a related 'customize' skill. The focus on automatic/optimal region selection creates a clear niche distinct from custom configuration tasks. | 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.
This skill provides a well-organized overview of Azure OpenAI model deployment with clear workflow paths and useful error handling guidance. Its main weaknesses are the lack of complete executable command examples for the core deployment flow and missing validation/feedback loops in the multi-step process. The content is moderately concise but has some structural redundancy between sections.
Suggestions
Add complete, copy-paste-ready Azure CLI command sequences for the core deployment path with realistic parameter placeholders (e.g., full `az cognitiveservices account deployment create` with all required flags).
Add explicit validation checkpoints: after deployment creation, verify with `az cognitiveservices account deployment show` and include a retry/feedback loop if provisioning state is not 'Succeeded'.
Consolidate the 'What This Skill Does' list and 'Quick Workflow' section—they convey the same information and one could be removed to improve conciseness.
Move the detailed Deployment Phases table and Error Handling table into the referenced `references/workflow.md` file, keeping only a summary in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably structured but includes some redundancy—the 'What This Skill Does' numbered list largely duplicates the Quick Workflow and Deployment Phases sections. The Notes section and some table entries could be tightened. However, it doesn't over-explain basic concepts. | 2 / 3 |
Actionability | Key Azure CLI commands are listed in the phases table and error handling section, and the Advanced Usage section has executable snippets. However, the core deployment workflow lacks complete, copy-paste-ready command sequences—the phases table shows command fragments rather than full executable examples with actual parameters and flags. | 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 capacity calculation step (50% available, min 50 TPM) is mentioned but not validated. | 2 / 3 |
Progressive Disclosure | The skill references a workflow detail file at 'references/workflow.md' and links to a quota skill, which is good progressive disclosure structure. However, no bundle files were provided, so we can't verify these references exist. The main file itself contains substantial detail (phases table, error handling table) that could arguably live in reference files, making the SKILL.md heavier than ideal for an overview. | 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/azure-skills
- Commit
d02fd24
- 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.