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.
85
77%
Does it follow best practices?
Impact
99%
2.02xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugin/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 strengths are comprehensive trigger term coverage and clear completeness with both what/when answered. Its weaknesses are 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.
Suggestions
Make capabilities more concrete by specifying actions like 'configure search indexes', 'index documents for vector search', 'transcribe audio files', 'extract text from scanned documents' rather than just listing feature areas.
Add 'Azure' as a qualifier to more trigger terms to reduce conflict risk with non-Azure skills (e.g., 'Azure OCR', 'Azure Speech Services', 'Azure Document Intelligence').
| 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 services provide some distinctiveness, terms like 'OCR', 'speech-to-text', and 'search' are quite generic 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
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is well-organized and token-efficient, serving as a strong reference index for Azure AI services with excellent progressive disclosure to SDK guides. Its main weakness is the lack of executable code examples and concrete workflows—it tells Claude what tools exist but doesn't show how to use them in practice. Adding even one concrete example per service (e.g., a search query, a transcription call) would significantly improve actionability.
Suggestions
Add at least one executable code example per major service (e.g., a Python snippet for AI Search query, a speech transcription call) to make the skill copy-paste actionable.
Include a brief step-by-step workflow for a common task like 'perform a hybrid search' or 'transcribe an audio file' with validation/verification steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured using tables to convey information densely. No unnecessary explanations of what Azure services are or how they work conceptually—it jumps straight to actionable reference material. | 3 / 3 |
Actionability | The skill provides specific MCP tool commands and references to SDK guides, which is useful. However, it lacks executable code examples—no actual search query, no speech transcription snippet, no SDK usage code. It describes what tools exist rather than showing how to use them. | 2 / 3 |
Workflow Clarity | There's a clear fallback instruction ('If Azure MCP is not enabled, run /azure:setup'), but no multi-step workflows are defined for common tasks like performing a hybrid search or transcribing audio. For a skill covering multiple services with potentially complex operations, the absence of step-by-step workflows is a gap. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a concise overview in the main file and well-organized, clearly signaled one-level-deep references to SDK guides across multiple languages and services, plus links to external Microsoft documentation. | 3 / 3 |
Total | 10 / 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/github-copilot-for-azure
- Commit
a46a937
- 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.