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 users would naturally use, explicit 'USE FOR' and 'DO NOT USE FOR' clauses, and clear differentiation from related skills. The description is well-structured and informative without being unnecessarily verbose.
| 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 detailed trigger scenarios). The negative trigger guidance further strengthens completeness. | 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 differentiates itself from a 'quick deployment to optimal region' skill with a 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 with excellent workflow clarity and progressive disclosure — the 14-phase flow is clearly sequenced with validation checkpoints, and detailed implementation is appropriately deferred to reference files. The main weaknesses are moderate verbosity (comparison tables, emoji-laden checklists) and the fact that actionable CLI commands are mostly in the reference file rather than inline, making the SKILL.md itself more descriptive than executable.
Suggestions
Trim the 'When to Use This Skill' section and comparison table — Claude can infer when to use customize vs preset from the workflow description alone.
Include at least the core deployment CLI command (Phase 13) inline with placeholder variables so the skill is partially executable without loading the reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes useful tables and structure but has redundancy — the 'When to Use This Skill' section with checkmarks and the comparison table are somewhat verbose for Claude. The Quick Reference table repeats information found elsewhere. However, most content is domain-specific and not explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides some concrete CLI commands in troubleshooting and references executable commands like `az cognitiveservices account deployment create`, but the actual implementation details are deferred to the reference file. The phase summaries describe *what* to do but not *how* — the skill explicitly says to load the reference file for actual scripts and commands. | 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). Cross-region fallback logic and error recovery paths are well-defined. The flow includes feedback loops like 'If no capacity → cross-region fallback → user selects region.' | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references: detailed workflow implementation in `references/customize-workflow.md` and SKU/advanced guides in `references/customize-guides.md`. The SKILL.md serves as an effective overview without burying essential content in nested references. | 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
9d594ab
- 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.