azure-ai-voicelive

Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.

Install with Tessl CLI

npx tessl i github:microsoft/agent-skills --skill azure-ai-voicelive

What are skills?

Overall
score

92%

Review — 93%

Does it follow best practices?

Validation — 12 / 16 Passed

Validation for skill structure

SKILL.md

Review

Evals

Discovery

100%

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 an excellent skill description that hits all the marks. It provides specific capabilities, comprehensive trigger terms covering both technical and natural language, explicit 'Use this skill when' guidance with concrete scenarios, and a distinctive focus on Azure AI Voice Live SDK that clearly differentiates it from other voice or AI skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'real-time bidirectional audio communication', 'voice assistants', 'voice-enabled chatbots', 'real-time speech-to-speech translation', 'voice-driven avatars', 'WebSocket-based audio streaming'. Also enumerates specific features: Server VAD, turn-based conversation, function calling, MCP tools, avatar integration, transcription.	3 / 3
Completeness	Clearly answers both what ('Build real-time voice AI applications using Azure AI Voice Live SDK') and when ('Use this skill when creating Python applications that need real-time bidirectional audio communication...') with explicit trigger scenarios and use cases.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'voice AI', 'real-time', 'voice assistants', 'chatbots', 'speech-to-speech translation', 'avatars', 'audio streaming', 'Azure AI', 'Python applications', 'WebSocket'. Includes both technical terms and natural language variations.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche: specifically targets Azure AI Voice Live SDK (azure-ai-voicelive), Python applications, and real-time audio/voice scenarios. The combination of Azure-specific SDK, voice/audio focus, and WebSocket streaming creates a unique fingerprint unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-crafted skill that provides comprehensive, actionable guidance for building voice AI applications with Azure. The code examples are executable and cover the full range of SDK capabilities. The main weakness is the lack of explicit validation steps in workflows involving audio streaming and connection management, which could lead to silent failures.

Suggestions

Add validation checkpoints to the Quick Start and Audio Streaming sections (e.g., verify connection state before streaming, check audio format compatibility)

Include a troubleshooting workflow for common failure modes like connection drops or audio format mismatches with explicit recovery steps

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, jumping straight into installation and executable code without explaining what WebSockets are or how real-time communication works. Every section provides actionable information without padding.	3 / 3
Actionability	Provides fully executable, copy-paste ready Python code throughout. Examples include complete connection setup, audio streaming, event handling patterns, and error handling with real imports and proper async context managers.	3 / 3
Workflow Clarity	While individual code patterns are clear, the skill lacks explicit validation checkpoints for the multi-step audio streaming workflow. There's no guidance on verifying connection success before streaming, or validating audio format compatibility before sending data.	2 / 3
Progressive Disclosure	Excellent structure with a quick start section followed by progressively detailed sections. Clear references to external files (api-reference.md, examples.md, models.md) for deeper content, all one level deep with descriptive labels.	3 / 3
	Total	11 / 12 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_trigger_hint	Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...')	Warning
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning
body_steps	No step-by-step structure detected (no ordered list); consider adding a simple workflow	Warning

	Total	12 / 16 Passed

Reviewed: about 1 month ago

Table of Contents

Discovery Implementation Validation

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.