customize
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
88
85%
Does it follow best practices?
Impact
89%
4.45xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 covers all key dimensions thoroughly. It provides specific concrete actions, comprehensive trigger terms, explicit use/don't-use guidance, and clear differentiation from related skills. The DO NOT USE FOR clause is a particularly strong addition for disambiguation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: step-by-step selection of model version, SKU types (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). Very detailed and concrete. | 3 / 3 |
Completeness | Clearly answers both 'what' (interactive guided deployment flow for Azure OpenAI models with full customization control) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with specific trigger scenarios). The DO NOT USE FOR clause adds extra clarity for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'custom deployment', 'choose version', 'select SKU', 'set capacity', 'configure content filter', 'RAI policy', 'advanced deployment', 'PTU deployment', 'provisioned throughput'. These are terms users would naturally use when requesting these capabilities. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (custom/advanced Azure OpenAI deployment) and explicitly distinguishes itself from a 'quick deployment to optimal region' skill via the DO NOT USE FOR clause, minimizing conflict risk. | 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 is a well-structured skill for a complex multi-phase deployment workflow with good progressive disclosure and clear workflow sequencing. Its main weakness is that the SKILL.md itself lacks executable code for the core deployment flow, deferring everything to a reference file, which reduces actionability. The content could also be tightened — the comparison table and use-case checklist consume tokens on information that could be more concise.
Suggestions
Include at least one complete executable example command for the core deployment (Phase 13's `az cognitiveservices account deployment create` with realistic parameters) directly in the SKILL.md rather than deferring all implementation to the reference file.
Condense the 'When to Use This Skill' section and the customize vs preset comparison table into a brief 2-3 line summary to save tokens — Claude can infer most of these distinctions from context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes useful tables and structured information but is verbose in places — the 'When to Use This Skill' checklist, the customize vs preset comparison table, and the Quick Reference table all add significant token overhead for information that could be more concise. The phase summaries table is reasonably efficient given the complexity. | 2 / 3 |
Actionability | The skill provides some concrete CLI commands in the troubleshooting section and references specific Azure CLI commands in the phase table, but the actual implementation is deferred entirely to references/customize-workflow.md. The SKILL.md itself contains no executable deployment workflow — it describes what to do rather than providing copy-paste ready commands for the core flow. | 2 / 3 |
Workflow Clarity | The 14-phase workflow is clearly sequenced with explicit validation checkpoints (Phase 7 validates capacity min/max/step, Phase 12 requires user review/approval before proceeding, capacity query failure blocks deployment). The cross-region fallback at Phase 7b shows error recovery logic, and the error handling table explicitly notes prevention and blocking behaviors. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to references/customize-workflow.md for implementation details and references/customize-guides.md for SKU guides and advanced topics. The SKILL.md serves as an effective navigation hub without inlining excessive detail, and related skills are clearly linked. | 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.
- 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.