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
Quality
77%
Does it follow best practices?
Impact
99%
2.02xAverage score across 3 eval scenarios
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 description effectively communicates Azure AI service capabilities with strong trigger term coverage and explicit 'WHEN' guidance. The main weakness is that capabilities are listed as feature categories rather than concrete actions, and some terms like 'OCR' and 'transcription' could conflict with non-Azure skills offering similar functionality.
Suggestions
Rephrase capabilities as concrete actions: 'Index and query documents with vector/hybrid search, transcribe audio files, convert text to speech, extract text from images via OCR'
Add Azure-specific qualifiers to generic terms to reduce conflict: 'Azure OCR', 'Azure transcription' in the WHEN clause
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure AI services) and lists several actions like 'search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR', but these are more feature categories than concrete actions. Missing specific verbs like 'extract', 'convert', 'index', 'query'. | 2 / 3 |
Completeness | Clearly answers both what ('Azure AI: Search, Speech, OpenAI, Document Intelligence' with capabilities listed) and when (explicit 'WHEN:' clause with comprehensive trigger terms). The structure explicitly addresses both questions. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'AI Search', 'vector search', 'hybrid search', 'semantic search', 'speech-to-text', 'text-to-speech', 'transcribe', 'OCR'. These are terms users would naturally use when needing these capabilities. | 3 / 3 |
Distinctiveness Conflict Risk | While Azure-specific, terms like 'OCR', 'speech-to-text', and 'transcription' could overlap with other skills offering similar capabilities through different services. The Azure branding helps but generic AI terms create some 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 excels at concise organization and progressive disclosure, using tables effectively to compress service information and clearly pointing to SDK references. However, it lacks executable code examples and workflow guidance for common operations like performing a vector search or transcribing audio, which limits its actionability for Claude.
Suggestions
Add at least one executable code example for the most common operation (e.g., a simple AI Search query using the Python SDK)
Include a brief workflow for a common multi-step task like 'index documents then query' with validation checkpoints
Add example MCP tool invocations showing actual parameters, not just command names
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables to compress information. No unnecessary explanations of what Azure services are or how they work - assumes Claude's competence with cloud services. | 3 / 3 |
Actionability | Provides specific MCP tool commands and references to SDK guides, but lacks executable code examples. The guidance is concrete (tool names, commands) but not copy-paste ready for actual implementation. | 2 / 3 |
Workflow Clarity | No clear multi-step workflows are provided. The skill lists capabilities and tools but doesn't show how to sequence operations or validate results. The '/azure:setup' fallback is mentioned but no validation steps for search queries or speech operations. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview tables, well-signaled one-level-deep references to SDK guides and external documentation. Content is appropriately split between overview and detailed references. | 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.
- 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.