CtrlK
BlogDocsLog inGet started
Tessl Logo

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

4.17x
Quality

Does it follow best practices?

Impact

96%

4.17x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A well-organized, actionable skill body that uses tables and concrete az commands effectively and points to a real one-level reference. Its main weaknesses are redundant restatements of the deployment phases and the absence of an explicit post-deploy validation checkpoint in the workflow.

Suggestions

Collapse the three restatements of the 7-phase flow ('What This Skill Does', 'Quick Workflow', 'Deployment Phases') into one canonical sequence to remove redundancy and save tokens.

Add an explicit Phase 8 'Verify deployment' checkpoint (e.g. `az cognitiveservices account deployment show` polling provisioningState until Succeeded) to close the validation gap in the workflow.

Either link references/preset-workflow.md from the body or remove it, so every bundle file is discoverable from the overview.

DimensionReasoningScore

Conciseness

Mostly efficient (tables, no concept-explaining fluff) but restates the same 7-phase flow three times — numbered 'What This Skill Does', ascii 'Quick Workflow', and the 'Deployment Phases' table — which could be tightened. Not score 1 because it avoids explaining concepts Claude already knows; not 3 due to the redundant representations.

2 / 3

Actionability

Provides concrete, executable `az` commands per phase, a specific API version (2024-10-01), GlobalStandard SKU, an explicit capacity formula (50% available, min 50 TPM), and copy-paste-ready advanced-usage commands. Not below 3 because guidance is specific and runnable rather than pseudocode.

3 / 3

Workflow Clarity

The 7-phase sequence and two-path branching are clearly listed with an error-handling table, but the phase flow lacks an explicit post-deploy validation/verification checkpoint for a mutating operation. Per the rubric cap for missing validation in such workflows, this stays at 2 rather than 3; it is above 1 because steps are well-sequenced.

2 / 3

Progressive Disclosure

SKILL.md is a clear overview with a well-signaled one-level reference to references/workflow.md (a real file), and detailed steps are appropriately split out. The unreferenced preset-workflow.md in references/ is a minor navigation gap, but structure and signaling remain strong enough for the top anchor.

3 / 3

Total

10

/

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.

A strong, third-person description that states concrete capabilities and provides explicit USE FOR / DO NOT USE FOR trigger guidance with clear distinctiveness from sibling skills. No first/second-person voice to penalize; every dimension lands at the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'deploys Azure OpenAI models to optimal regions', 'analyzing capacity across all available regions', 'checks current region first and shows alternatives' — matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both 'what' (deploys to optimal regions via capacity analysis) and 'when' (explicit 'USE FOR:' trigger clause), satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

The USE FOR clause gives natural phrasings a user would say ('quick deployment', 'optimal region', 'best region', 'automatic region selection', 'fast setup'), with good coverage of variations.

3 / 3

Distinctiveness Conflict Risk

Clear Azure OpenAI region-selection niche with a 'DO NOT USE FOR' clause disambiguating from the 'customize' skill, making conflict with other skills unlikely.

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: 2 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.