CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

92

4.45x
Quality

92%

Does it follow best practices?

Impact

89%

4.45x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, actionable overview with a clear phased workflow, validation checkpoints, and properly split one-level-deep references. Its main weakness is token efficiency: the same customization dimensions are repeated across several sections and could be consolidated.

Suggestions

Consolidate the repeated version/SKU/capacity/RAI/advanced-options enumeration: state it once and let the Quick Reference, When-to-Use checklist, and Selection Guides reference back rather than restating it each time.

Consider moving the customize-vs-preset comparison table (or shortening it to one row) since the description already disambiguates via "DO NOT USE FOR ... use preset", reducing duplicated rationale.

The Phase Summaries repeat phase actions already expanded in references/customize-workflow.md; trimming the per-phase detail to one-line triggers would further reduce token cost while the reference retains the how.

DimensionReasoningScore

Conciseness

The same five customization dimensions (version, SKU, capacity, RAI policy, advanced options) are restated across the Quick Reference table, the "When to Use" checklist, the customize-vs-preset comparison table, the Phase Summaries, and the Selection Guides section, so while it avoids explaining concepts Claude already knows, it could be tightened and is not fully lean.

2 / 3

Actionability

Provides concrete executable commands (e.g. `az cognitiveservices account deployment create`, `az cognitiveservices account list-models`), a copy-paste troubleshooting block, an exact PTU capacity formula, and a concrete deployment-name regex `^[\w.-]{2,64}$`, matching the fully-executable anchor.

3 / 3

Workflow Clarity

The 14-phase flow is clearly sequenced with explicit validation checkpoints (Phase 7 validates min/max/step, Phase 12 review gate) and feedback loops (error→resolution table, "DEPLOYMENT BLOCKED: Will not proceed without valid quota data", cross-region fallback), matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

The body is an overview with two well-signaled, one-level-deep references — a MUST-READ callout to references/customize-workflow.md and a callout to references/customize-guides.md — both verified to be real files with no further nested references, and detailed scripts are appropriately split out of the overview.

3 / 3

Total

11

/

12

Passed

Description

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.

The description is third-person, specific, and complete: it names concrete actions, provides explicit USE FOR triggers, and explicitly distinguishes itself from the preset skill. It is a strong model description with no notable gaps.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: "selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover)" — matches the anchor for listing multiple specific concrete actions, not the partial single-domain example below it.

3 / 3

Completeness

Clearly answers both what (guided deployment flow with full customization control) and when via an explicit "USE FOR:" trigger clause, which satisfies the rubric's requirement for an explicit Use-when equivalent and so is not capped at 2.

3 / 3

Trigger Term Quality

The "USE FOR:" block gives broad coverage of natural terms users would say ("custom deployment", "customize model deployment", "choose version", "select SKU", "PTU deployment", "provisioned throughput") rather than only jargon, matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

Has a clear niche and an explicit "DO NOT USE FOR: quick deployment to optimal region (use preset)" disambiguator, making it unlikely to trigger for the wrong sibling skill.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
microsoft/azure-skills
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.