azure-ai-voicelive-py

Build real-time voice AI applications with bidirectional WebSocket communication.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-ai-voicelive-py/SKILL.md

Quality

Content

72%Weight 40%Scale 1-5

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

This is a strong, highly actionable API reference with executable code across the main feature surface, though it is organized as a flat reference rather than a checkpointed workflow. Its main weakness is progressive disclosure: it points to reference files that do not exist and inlines material that belongs in those files.

Suggestions

Create the referenced bundle files (references/api-reference.md, references/examples.md, references/models.md) and move the bulk of the inlined API reference (voice/audio-format/turn-detection tables, full event catalog) into them, leaving SKILL.md as a concise overview.

Replace the generic 'When to Use' filler ('applicable to execute the workflow or actions described in the overview') with a concrete, scoped trigger statement so the skill activates only for Azure realtime voice tasks.

Add at least one explicit validation/checkpoint step for fragile flows (e.g. verify the WebSocket connection opened and the session.updated event returned before streaming audio) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is a lean, code-first reference that assumes Claude knows async Python and WebSocket basics; the only padding is the generic 'When to Use' and 'Limitations' boilerplate at the end that earns little.	4 / 5
Actionability	Provides copy-paste-ready, executable code spanning installation, auth, connection, session config, audio streaming, event handling, function tools, and error handling, covering the common cases concretely.	5 / 5
Workflow Clarity	A reasonable sequence is implied by section ordering and the Quick Start (connect → configure session → stream/handle events), but there are no explicit validation checkpoints or feedback loops, so it sits at the anchor with checkpoints missing.	3 / 5
Progressive Disclosure	References to references/api-reference.md, examples.md, and models.md are clearly signaled one level deep, but those files are absent from the bundle and substantial API-reference material (voice tables, audio formats, event lists) is inlined rather than split out.	3 / 5
	Total	15 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 is concise and third-person, naming a clear domain and mechanism, but it omits any explicit 'when to use' trigger guidance and offers only one broad action. Adding a 'Use when...' clause with concrete trigger phrases would substantially raise completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building real-time voice assistants, live audio chatbots, or bidirectional streaming audio apps with Azure OpenAI realtime models.'

Include natural synonyms and identifiers users say, such as 'voice assistant', 'realtime audio', 'speech-to-speech', and the SDK/package name 'azure-ai-voicelive'.

List 2-3 concrete actions (e.g. 'stream audio, configure turn detection, handle function calls') instead of the single verb 'Build' to improve specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('real-time voice AI applications') and one concrete action ('Build') plus a mechanism ('bidirectional WebSocket communication'), but coverage is not comprehensive — only a single high-level action is given.	3 / 5
Completeness	It clearly states what the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes relevant natural phrases like 'real-time voice AI' and 'voice AI applications', but lacks common synonyms, file extensions, and broader trigger variations a user might say.	3 / 5
Distinctiveness Conflict Risk	The 'real-time voice AI' + 'bidirectional WebSocket' niche is fairly specific with minimal overlap risk against other skills, though the lack of trigger phrases leaves minor ambiguity.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/azure-ai-voicelive-py/SKILL.md
Commit: 1f67c44

Reviewed: about 14 hours 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.