azure-ai

Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

87%

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

A well-structured, token-efficient dispatcher skill that points to real SDK references and gives concrete MCP/CLI commands. Its main weakness is the absence of any sequenced workflow with validation checkpoints, since the body is a lookup catalog rather than a process.

Suggestions

Add a short ordered workflow for at least one common task (e.g. query an AI Search index) with an explicit verification step so workflow_clarity can reach 3.

Link references/auth-best-practices.md from the body — it exists in the bundle but is currently undiscoverable from SKILL.md.

Show one copy-paste-ready MCP invocation example with parameters to strengthen actionability beyond tool/command name listings.

Dimension	Reasoning	Score
Conciseness	Lean table-based overview with no concept-explaining fluff; every section earns its place without padding that Claude would already know.	3 / 3
Actionability	Gives concrete MCP tool/command pairs (e.g. 'azure__search with command search_query'), CLI commands ('az search', 'az cognitiveservices'), and a clear setup fallback ('/azure:setup').	3 / 3
Workflow Clarity	The body is a reference catalog with one conditional branch (MCP not enabled -> run setup) but no sequenced multi-step process or validation checkpoints.	2 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep links into references/sdk/*.md (verified to exist) plus external docs; content is appropriately split and easy to navigate.	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 description that concisely states capabilities and provides explicit WHEN triggers in third-person voice. It clearly establishes a distinct Azure AI niche with good natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names concrete services (Search, Speech, OpenAI, Document Intelligence) and specific actions (vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR) rather than vague language.	3 / 3
Completeness	Explicitly answers 'what' (services and actions) and 'when' via an explicit 'WHEN:' trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Broad natural-term coverage users would actually say: 'search', 'vector search', 'speech-to-text', 'transcribe', 'OCR', 'convert text to speech', 'semantic search'.	3 / 3
Distinctiveness Conflict Risk	Scoped to the Azure AI niche with distinct triggers; unlikely to fire for unrelated skills despite a few generic terms like 'search' and 'OCR'.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 14 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 14 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: microsoft/azure-skills
Commit: 2cd48ca

Reviewed: about 8 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.