capacity

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.

1.35x

Quality

92%

Does it follow best practices?

Impact

88%

1.35x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

85%

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

A well-structured, highly actionable body with a clear sequenced workflow, real validation checkpoints, and genuine offloading of complex logic to verified bundle scripts. Its only weakness is conciseness: the intro duplicates the description and the manual Phase 3.5 quota code partly reiterates what the discovery script already does.

Suggestions

Remove or shrink the opening paragraph ('Finds available Azure OpenAI model capacity... Recommends the best deployment location...') since it restates the frontmatter description verbatim.

Condense Phase 3.5's inline PowerShell/bash quota snippets — or move the logic into the existing discover_and_rank script, which already cross-references subscription quota — so the SKILL.md stays a lean overview.

Trim overlap between the 'Quick Reference' table and the 'When to Use This Skill' section so each section adds distinct information.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept filler, but the opening paragraph restates the description nearly verbatim and Phase 3.5's hand-rolled quota-checking code overlaps work the discover_and_rank script already performs per its own header; it could be tightened to earn the lean bar.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout — 'az account show --query ... --output table', './scripts/query_capacity.sh <model-name>', '.\scripts\discover_and_rank.ps1 -ModelName ... -ModelVersion ... -MinCapacity ...', and real az cognitiveservices usage/jq snippets — not pseudocode.	3 / 3
Workflow Clarity	Clear five-phase sequence with explicit validation checkpoints (Phase 1 verifies auth/prerequisites, Phase 3.5 validates subscription quota) plus an error-handling table giving recovery actions; the read-only nature means the destructive-feedback-loop cap does not apply.	3 / 3
Progressive Disclosure	SKILL.md acts as an overview pointing to four real, verified script bundle files via a Scripts table and inline usage, with one-level-deep references and clear section navigation; the heavy REST/quota logic is correctly split into the scripts rather than inlined.	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.

A strong, third-person description with concrete actions, a rich set of natural trigger terms, and explicit what/when guidance reinforced by a DO NOT USE FOR boundary that distinguishes it from adjacent skills. No first/second-person voice or vague fluff is present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Discovers available Azure OpenAI model capacity across regions and projects', 'Analyzes quota limits, compares availability, and recommends optimal deployment locations' — rather than vague language; not the level below which only names a domain and some actions.	3 / 3
Completeness	Explicitly answers both what (discover/analyze/compare/recommend capacity) and when, via a USE FOR trigger list and a DO NOT USE FOR exclusion list; the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	The USE FOR list covers natural phrasings a user would actually say — 'find capacity', 'check quota', 'where can I deploy', 'best region for capacity', 'check TPM availability' — giving broad coverage rather than only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	A clear niche (read-only capacity discovery) with distinct triggers, and the DO NOT USE FOR clause explicitly carves off deployment (preset/customize) and quota increases (quota skill), making conflict with sibling skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 10 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/azure-skills
Commit: 39464cb

Reviewed: about 5 hours ago

Table of Contents

Discovery Implementation Validation

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.