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).
Install with Tessl CLI
npx tessl i github:microsoft/github-copilot-for-azure --skill customize88
Quality
85%
Does it follow best practices?
Impact
89%
4.45xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugin/skills/microsoft-foundry/models/deploy-model/customize/SKILL.mdDiscovery
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 concrete actions, comprehensive trigger terms covering both technical and natural language, explicit 'USE FOR' and 'DO NOT USE FOR' clauses, and clear differentiation from related skills. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover)'. Very detailed enumeration of capabilities. | 3 / 3 |
Completeness | Clearly answers both what (interactive guided deployment flow with full customization) AND when (explicit 'USE FOR:' clause with trigger terms, plus 'DO NOT USE FOR:' to clarify boundaries). The explicit trigger guidance is comprehensive. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'custom deployment', 'customize model deployment', 'choose version', 'select SKU', 'set capacity', 'configure content filter', 'RAI policy', 'PTU deployment', 'provisioned throughput'. Includes both technical and natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche with distinct triggers for Azure OpenAI custom deployments. The 'DO NOT USE FOR: quick deployment to optimal region (use preset)' explicitly differentiates from related skills, 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 skill demonstrates strong workflow organization with clear phase sequencing and validation checkpoints, plus excellent progressive disclosure to reference files. However, actionability suffers because the main file describes phases rather than providing executable code directly—users must load the reference file for actual implementation. Some content could be tightened for better token efficiency.
Suggestions
Include at least one complete executable example (e.g., the deployment CLI command with all parameters) directly in the main skill file rather than deferring all implementation to references
Consolidate the 'When to Use' and 'Comparison' sections to reduce redundancy—the comparison table largely repeats the bullet points above it
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some redundancy (comparison table duplicates information, verbose phase summaries). The tables are useful but some explanatory text could be tightened. | 2 / 3 |
Actionability | Provides concrete CLI commands in troubleshooting section and references executable scripts, but the main workflow phases only describe what to do rather than showing executable code. The actual implementation is deferred to a reference file. | 2 / 3 |
Workflow Clarity | Excellent 14-phase workflow with clear sequencing, explicit validation checkpoints (Phase 7 capacity validation, Phase 12 review before deployment), cross-region fallback logic, and error handling table with resolutions. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview, phase summaries in main file, and explicit one-level-deep references to detailed implementation (references/customize-workflow.md, references/customize-guides.md). Navigation is clear and appropriately signaled. | 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.