azure-ai-voicelive-ts

Azure AI Voice Live SDK for JavaScript/TypeScript. Build real-time voice AI applications with bidirectional WebSocket communication.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The content is highly actionable with thorough executable examples, but it is a monolithic inline API reference with redundant sections and no progressive disclosure via separate files. Splitting reference material into bundled files and removing repetition would improve conciseness and structure.

Suggestions

Move the full event-handler catalog, type reference, and voice/model/format tables into bundled reference files (e.g. references/events.md, references/types.md) and link to them from a concise overview.

De-duplicate the session configuration block that recurs across Quick Start, Session Configuration, and Function Calling.

Remove the generic filler '## When to Use' sentence and replace it with concise, specific scope guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient code and tables rather than explaining concepts Claude already knows, but it carries notable repetition (session config appears in Quick Start, Session Configuration, and Function Calling) and filler like 'This skill is applicable to execute the workflow or actions described in the overview', so it could be tightened past level 3.	2 / 3
Actionability	It provides extensive copy-paste-ready, executable TypeScript examples for client creation, session config, event handling, function calling, and error handling with specific types and values, matching the level 3 anchor.	3 / 3
Workflow Clarity	A sequence exists in Quick Start (create client, start session, updateSession, subscribe, sendAudio), but there are no validation checkpoints or error-recovery feedback loops, so it sits at level 2 rather than 3.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the entire API reference (full event-handler catalog, type reference, voice/model/format tables) is inline in a single ~470-line monolithic file with no bundle files to offload detail into, matching the level 2 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 specific and clearly niche, but it only states what the skill does without an explicit 'Use when...' trigger clause and with limited keyword coverage. Adding explicit usage triggers and more natural trigger terms would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when building real-time voice assistants, speech-to-speech apps, or bidirectional voice chat with Azure AI in Node.js or the browser.'

Broaden natural trigger terms to include variations like 'voice assistant', 'realtime audio streaming', 'speech', and 'voice chat'.

Mention a second concrete capability (e.g. function calling or transcription) to push specificity toward level 3.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure AI Voice Live SDK for JavaScript/TypeScript') and a concrete action ('Build real-time voice AI applications with bidirectional WebSocket communication'), but lists only one primary action rather than multiple specific capabilities, so it does not reach the comprehensive level 3.	2 / 3
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	'voice AI applications' and 'real-time voice' are natural terms a user might say, but coverage is thin and misses common variations like 'voice assistant', 'realtime audio', 'speech', or 'voice chat' that level 3 requires.	2 / 3
Distinctiveness Conflict Risk	The description targets a specific, niche product (Azure AI Voice Live SDK for JS/TS) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: bc6dcb0

Reviewed: 2 days 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.