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

86%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

The body is a lean, well-organized reference catalog with good progressive disclosure and existing SDK references, but it lacks executable code and explicit validation checkpoints, capping actionability and workflow clarity at 2.

Suggestions

Add at least one copy-paste-ready executable example per primary service (e.g., a minimal python/az CLI snippet for AI Search and Speech) to lift actionability from 2 to 3.

Add a short ordered workflow with an explicit verification step — e.g., list index -> run query -> verify result count — so multi-step operations have a validation checkpoint.

Fill the empty CLI / MCP tool cells (Document Intelligence, OpenAI CLI) or note explicitly when SDK-only access applies, rather than leaving '-' placeholders.

Dimension	Reasoning	Score
Conciseness	The body uses compact tables and short bullets without explaining concepts Claude already knows; every section earns its place. Not level 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	MCP tool commands are concrete ("azure__search with command search_query"), but many table cells are empty ("-"), there is no executable code, and CLI guidance is sparse — some concrete guidance but incomplete.	2 / 3
Workflow Clarity	There is a conditional branch ("If Azure MCP is not enabled: Run /azure:setup") but no explicit multi-step sequence or validation checkpoints for operations that warrant them. Not level 1 because a sequence/branch is present; not level 3 because validation checkpoints are absent.	2 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references into references/sdk/; all 13 referenced SDK files exist and navigation is easy. Matches the clear-overview 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.

The description is concise, uses third-person voice, and clearly communicates both capabilities and explicit when-to-use triggers across the Azure AI service family. It matches the strongest anchors on all dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete services and actions — "Search, Speech, OpenAI, Document Intelligence" with "vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ("Use for Azure AI: Search, Speech, OpenAI, Document Intelligence") and when ("WHEN: AI Search, query search...") with explicit trigger guidance.	3 / 3
Trigger Term Quality	The WHEN clause covers natural terms users would say — "AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech" — broad and natural coverage.	3 / 3
Distinctiveness Conflict Risk	Azure AI services form a clear niche with distinct triggers unlikely to overlap with other skills.	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: 39464cb

Reviewed: about 6 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.