azure-ai-voicelive-dotnet
Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication.
46
48%
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 ./skills/azure-ai-voicelive-dotnet/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a specific technology stack (Azure AI Voice Live SDK for .NET) but reads more like a tagline than a functional skill description. It lacks concrete actions, natural trigger terms users would say, and critically has no 'Use when...' clause to guide skill selection.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to build or debug real-time voice applications using Azure AI Voice Live SDK in C# or .NET projects.'
List specific concrete actions the skill covers, such as 'configure WebSocket connections, stream audio input/output, handle voice session lifecycle, implement turn-taking, process real-time transcriptions.'
Include natural trigger terms users might say, such as 'speech-to-text', 'voice assistant', 'audio streaming', 'C#', 'NuGet', 'Azure Cognitive Services', or 'conversational AI'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Azure AI Voice Live SDK, .NET) and a key action ('Build real-time voice AI applications with bidirectional WebSocket communication'), but doesn't list multiple concrete actions like 'stream audio, transcribe speech, synthesize responses'. | 2 / 3 |
Completeness | Describes what the skill is about at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Azure AI', 'Voice', '.NET', 'WebSocket', and 'real-time', but misses common user variations such as 'speech-to-text', 'text-to-speech', 'audio streaming', 'voice assistant', or 'conversational AI'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Azure AI Voice Live SDK' and '.NET' is fairly specific and narrows the niche, but without explicit trigger conditions it could overlap with other Azure SDK skills or general voice/audio processing skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid SDK reference skill with excellent actionability — the code examples are complete, executable, and cover the key use cases well. The main weaknesses are the lack of validation checkpoints in the workflow (important for WebSocket-based real-time communication) and some verbosity in auxiliary sections that don't add much value for Claude. The monolithic structure is acceptable given no bundle exists, but could benefit from splitting reference tables into separate files.
Suggestions
Add validation checkpoints after session creation and configuration (e.g., verify session connected, check for SessionUpdateSessionCreated event before proceeding)
Add a reconnection/error recovery loop for WebSocket disconnections, which are common in real-time communication
Remove or significantly trim the 'When to Use', 'Limitations', 'Related SDKs', and 'Reference Links' sections — these are boilerplate that consume tokens without adding actionable guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary sections like 'When to Use' and 'Limitations' boilerplate, the 'Related SDKs' table, and reference links that add little value for Claude. The Best Practices section contains some obvious advice (e.g., 'Never hardcode API keys'). The overall length (~250 lines) could be tightened. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready C# code for every major operation: authentication, session setup, event processing, function calling, and error handling. Code examples are complete with proper imports and realistic patterns. | 3 / 3 |
Workflow Clarity | The core workflow is clearly numbered (1-4) with a logical sequence from session creation through event processing and function calling. However, there are no validation checkpoints — no guidance on verifying the session connected successfully, no error recovery loops for WebSocket disconnections, and no verification that configuration was accepted before proceeding to send audio/messages. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and tables, but it's a monolithic file with no bundle files to offload detailed content. The reference tables, voice options, and model lists could be in separate files. The Reference Links section points to external URLs but there's no internal file structure for progressive discovery. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
9e5d4dd
- 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.