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).
89
Quality
85%
Does it follow best practices?
Impact
96%
4.17xAverage score across 3 eval scenarios
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 an excellent skill description that hits all the marks. It provides specific capabilities, comprehensive trigger terms that match natural user language, explicit 'USE FOR' and 'DO NOT USE FOR' clauses that clearly define scope, and strong distinctiveness through boundary conditions that prevent conflicts with related customization skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'deploys Azure OpenAI models', 'analyzing capacity across all available regions', 'checks current region first', 'shows alternatives'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (deploys models by analyzing capacity, checks current region, shows alternatives) AND when (explicit 'USE FOR' clause with trigger scenarios). Also includes helpful 'DO NOT USE FOR' guidance to prevent misuse. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural 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'. These match how users naturally phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Azure OpenAI intelligent/automatic deployment) and explicit boundary conditions via 'DO NOT USE FOR' clause that directs users to 'customize' skill for specific configurations. This prevents conflicts with related skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides good structural organization and workflow clarity with clear decision paths and error handling. However, it sacrifices actionability by using incomplete command fragments and deferring core instructions to reference files. The content could be more concise by removing redundant workflow representations and trimming explanatory text.
Suggestions
Replace command fragments with complete, executable examples (e.g., full `az rest` command with actual endpoint path)
Consolidate the two workflow representations (Quick Workflow and Deployment Phases table) into a single, more detailed format
Remove or inline the ARM ID format explanation since Claude understands Azure resource ID structures
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is reasonably efficient but includes some redundancy (workflow shown twice in different formats) and explanatory text that could be trimmed. The prerequisites section explains ARM ID format which Claude likely knows. | 2 / 3 |
Actionability | Provides command references and a workflow table, but lacks complete executable examples. Commands shown are fragments (e.g., `az rest --method GET .../modelCapacities` with ellipsis) rather than copy-paste ready. The actual deployment workflow defers to a reference file. | 2 / 3 |
Workflow Clarity | Clear multi-step workflow with two distinct paths (fast path vs alternative region). Phases are well-sequenced in the table, error handling covers common failure modes with resolutions, and the workflow includes validation checkpoints (auth verification, capacity checks before deployment). | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate use of tables for dense information, and proper one-level-deep references to detailed workflow and related skills. Content is appropriately split between overview and reference materials. | 3 / 3 |
Total | 10 / 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.
- 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.