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.
76
69%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/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 are listed more as feature categories than concrete actions, and some trigger terms like 'OCR' and 'search' are generic enough to potentially conflict with non-Azure skills. The description would benefit from slightly more specific action verbs and clearer Azure-specific scoping of the generic terms.
Suggestions
Make capabilities more concrete by specifying actions like 'configure Azure AI Search indexes', 'transcribe audio files using Azure Speech Services', or 'extract text from documents using Azure Document Intelligence'.
Qualify generic trigger terms to reduce conflict risk, e.g., 'Azure OCR' or 'Azure speech services' rather than just 'OCR' and 'speech-to-text', so it doesn't incorrectly trigger over non-Azure alternatives.
| 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, 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 services provide some distinctiveness, 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
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill serves well as a navigation hub and reference index for Azure AI services, with strong progressive disclosure and reasonable conciseness. However, it lacks concrete executable examples and defined workflows for common tasks, making it more of a catalog than an actionable guide. Adding a few copy-paste ready code snippets for the most common operations (e.g., a search query, a transcription call) would significantly improve its utility.
Suggestions
Add at least one executable code example per primary service (AI Search query, Speech transcription) showing actual SDK usage with realistic parameters.
Define a brief workflow for the most common task (e.g., 'Performing a hybrid search: 1. Create index with vector config → 2. Index documents → 3. Query with both text and vector'), including validation steps.
Remove or condense the capability description tables (AI Search Capabilities, Speech Capabilities) since they describe well-known features that Claude already understands — the service names are self-explanatory.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient with good use of tables, but some sections like 'Speech Capabilities' and 'AI Search Capabilities' describe features at a high level that Claude likely already knows (e.g., what full-text search or speech-to-text is). The capability tables add limited value beyond what the service names already convey. | 2 / 3 |
Actionability | The skill provides MCP tool names and commands which are somewhat actionable, and links to SDK references. However, there are no executable code examples, no concrete query patterns, and no copy-paste ready snippets. The guidance is more of a directory/catalog than step-by-step instructions. | 2 / 3 |
Workflow Clarity | There's a clear fallback path (MCP preferred → if not enabled, run 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, concrete workflows for at least the primary use cases would be expected. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview, well-organized SDK references across multiple languages, explicit 'load on demand' instructions for references, and links to external documentation. All 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
- jonathan-vella/azure-agentic-infraops
- Commit
ec7b8ff
- 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.