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?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

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, token-efficient catalog that points to real, one-level-deep SDK reference files. It is highly actionable for MCP/CLI usage but provides no inline executable code, and its workflow is a simple conditional rather than a validated multi-step process.

Suggestions

Add one short inline code example (e.g., a Python azure-search-documents query snippet) so the most common case is copy-paste ready without opening a reference file.

Provide a brief recommended workflow for choosing between MCP vs CLI vs SDK access based on what the user needs.

Dimension	Reasoning	Score
Conciseness	The body is lean and table-driven, assuming Claude's competence — it lists tools, capabilities, and SDK reference links without explaining what search or speech services are. Every line earns its place.	5 / 5
Actionability	It gives concrete, usable identifiers (MCP tool/command pairs like 'azure__search with command search_query', CLI 'az search', real SDK reference file links), but offers no inline code examples, so it is not fully copy-paste ready.	4 / 5
Workflow Clarity	Sequencing is minimal — a single conditional branch ('If Azure MCP is not enabled: Run /azure:setup') with no validation checkpoints; however the skill is a reference/catalog rather than a destructive or batch operation, so the destructive-operation cap does not apply.	3 / 5
Progressive Disclosure	The SKILL.md is a clear overview with well-signaled one-level-deep references (verified: references/sdk/*.md files exist), organized into per-language links; bulk detail is correctly pushed to the SDK files rather than inlined.	5 / 5
	Total	17 / 20 Passed

Description

91%Weight 40%Scale 1-5

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 strong: it concisely names the domain, enumerates concrete capabilities, and provides an explicit WHEN clause rich in natural trigger terms with synonyms. It is distinctively scoped to Azure AI services with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR') covering the four named services, with minor gaps (e.g., embeddings/DALL-E only appear in the body, not the description).	4 / 5
Completeness	It explicitly answers both what ('Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR') and when ('WHEN: AI Search, query search... OCR, convert text to speech') with concrete trigger phrases.	5 / 5
Trigger Term Quality	The WHEN clause packs in natural user phrases including synonyms and variations ('query search, vector search, hybrid search, semantic search, transcribe, convert text to speech, OCR'), matching the comprehensive coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The 'Azure AI' niche plus a distinct trigger set (Azure-specific services like AI Search, Speech, Document Intelligence) gives minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 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
Path: .github/plugins/azure-skills/skills/azure-ai/SKILL.md
Commit: 16dc8c5

Reviewed: about 12 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.