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

71%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugin/skills/azure-ai/SKILL.md

Quality

Discovery

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid skill description that clearly identifies its Azure AI domain and provides explicit trigger terms via a 'WHEN:' clause. Its main weakness is that it covers a very broad set of Azure AI services, which could create overlap with more specialized skills, and the actions listed are more like capability areas than specific concrete operations.

Suggestions

Add more concrete actions for each service area (e.g., 'create and configure search indexes', 'transcribe audio files', 'extract text from scanned documents') to improve specificity.

Consider narrowing scope or explicitly noting this is for Azure-specific implementations to reduce conflict risk with generic OCR, search, or speech skills.

Dimension	Reasoning	Score
Specificity	The description names the domain (Azure AI services) and lists several actions like search, speech-to-text, text-to-speech, transcription, and OCR, but these are more like feature areas than concrete specific actions (e.g., it doesn't say 'configure an Azure AI Search index' or 'transcribe audio files using Azure Speech').	2 / 3
Completeness	The description clearly answers both 'what' (Azure AI services for search, speech, OCR, Document Intelligence) and 'when' with an explicit 'WHEN:' clause listing specific trigger scenarios. This meets the criteria for explicit trigger guidance.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'vector search', 'hybrid search', 'semantic search', 'speech-to-text', 'text-to-speech', 'transcribe', 'OCR', 'AI Search', 'Document Intelligence'. These are terms users would naturally use when needing this skill.	3 / 3
Distinctiveness Conflict Risk	While Azure-specific terms help distinguish it, the skill covers a broad range of capabilities (search, speech, OCR, document processing) that could overlap with other skills focused on general OCR, speech processing, or search functionality. The Azure branding helps but the breadth increases conflict risk.	2 / 3
	Total	10 / 12 Passed

Implementation

60%

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

This skill is a well-organized reference catalog for Azure AI services that excels at conciseness and progressive disclosure. However, it lacks executable code examples and workflow guidance, making it more of a navigation aid than an actionable skill. Adding concrete code snippets for common tasks and step-by-step workflows for key operations would significantly improve its utility.

Suggestions

Add at least one executable code example per major service (e.g., a complete AI Search query using the Python SDK, a speech transcription snippet) to improve actionability.

Include a step-by-step workflow for a common multi-step operation like 'create search index → upload documents → query', with validation checkpoints to verify each step succeeded.

Add a concrete example of using the MCP tools (e.g., showing the full command and expected response for `search_query`) so Claude knows exactly how to invoke them.

Dimension	Reasoning	Score
Conciseness	The content is lean and well-structured using tables for quick reference. It avoids explaining what Azure services are or how SDKs work in general, assuming Claude's competence. Every section serves a clear purpose.	3 / 3
Actionability	The skill provides specific MCP tool commands and references to SDK guides, but lacks executable code examples. There are no concrete code snippets showing how to perform a search query, transcribe speech, or use any SDK — it's more of a reference map than executable guidance.	2 / 3
Workflow Clarity	There are no multi-step workflows, sequences, or validation checkpoints. The content is purely a reference catalog of services and tools without any guidance on how to chain operations together (e.g., create an index, populate it, then query it) or verify results.	1 / 3
Progressive Disclosure	Excellent structure with a concise overview pointing to well-organized SDK references across multiple languages and services, plus external documentation links. References are one level deep and clearly signaled with descriptive labels.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/github-copilot-for-azure
Commit: 771a666

Reviewed: 5 days 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.