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.
61
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/plugins/azure-skills/skills/azure-ai/SKILL.mdQuality
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 the capabilities listed are more like feature categories than concrete actions, and some trigger terms (OCR, search) are generic enough to potentially conflict with non-Azure skills. The description is functional and would generally enable correct skill selection in most contexts.
Suggestions
Make capabilities more concrete by specifying actions, e.g., 'Create and configure Azure AI Search indexes, run vector/hybrid/semantic queries, transcribe audio files with Azure Speech Services, extract text from documents with Document Intelligence'.
Add 'Azure' as a qualifier to generic terms in the WHEN clause to reduce conflict risk, e.g., 'Azure OCR', 'Azure transcription', or mention specific SDK/API names.
| 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'). | 2 / 3 |
Completeness | The description clearly answers both 'what' (Azure AI services for search, speech, document intelligence) and 'when' with an explicit 'WHEN:' clause listing specific trigger scenarios. This satisfies the requirement 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'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | While Azure-specific terms help distinguish it, terms like 'OCR', 'speech-to-text', and 'search' are quite broad and could overlap with non-Azure skills that handle similar tasks (e.g., a general OCR skill or a generic search skill). The Azure branding helps but doesn't fully eliminate 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%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/azure-skills
- Commit
d02fd24
- Reviewed
Table of Contents
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.