azure-ai-voicelive-ts

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

2.77x

Quality

54%

Does it follow best practices?

Impact

100%

2.77x

Average score across 6 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-voicelive-ts/SKILL.md

The canonical home for this skill is azure-ai-voicelive-ts in sickn33/agentic-awesome-skills

Quality

Content

63%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.

The skill body is highly actionable with comprehensive executable TypeScript examples and a clear high-level workflow. Its main weaknesses are length/repetition (conciseness) and the absence of any progressive disclosure via separate reference files despite a large API surface.

Suggestions

Move the full event-handler reference and type tables into a separate references/ file and link to it, keeping SKILL.md as a concise overview.

De-duplicate the tool/function-calling configuration block that recurs across Session Configuration and Function Calling sections.

Either complete the browser microphone pipeline inline or link explicitly to a samples file rather than an ellipsis comment.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-organized with code-first sections, but it is quite long and repeats concepts across Quick Start, Session Configuration, Function Calling, and Event Handling sections (e.g., the full tool config appears twice), which could be tightened.	3 / 5
Actionability	Provides concrete, copy-paste-ready TypeScript examples for client creation, session config, event subscription, and function calling with only minor gaps (e.g., the browser mic pipeline references 'see samples' rather than completing the example).	4 / 5
Workflow Clarity	A clear logical sequence is laid out (install -> authenticate -> start session -> configure -> subscribe -> send audio) with cleanup guidance (subscription.close()), though it lacks explicit validation/checkpoint steps; the skill is non-destructive so the destructive-operation cap does not apply.	4 / 5
Progressive Disclosure	Content is well-sectioned but everything is inlined into a single ~470-line SKILL.md with no bundle files (references/scripts/assets absent); large reference material (full event handler list, type tables) that could live in separate files is inline.	3 / 5
	Total	14 / 20 Passed

Description

45%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 clearly states what the SDK is and its primary use, but omits any 'Use when...' trigger guidance, which the rubric penalizes heavily for completeness. It is reasonably distinct but only moderately specific about capabilities.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when building voice assistants, real-time speech apps, or bidirectional audio streaming with Azure AI').

List 2-3 more concrete actions (e.g., 'stream audio input/output, handle turn detection, manage conversation state') to raise specificity.

Include natural synonyms users say — 'voice assistant', 'speech', 'real-time audio' — alongside the current technical terms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure AI Voice Live SDK for JavaScript/TypeScript') and one concrete action ('Build real-time voice AI applications with bidirectional WebSocket communication'), but provides only a single high-level capability rather than a list of specific actions.	3 / 5
Completeness	It has a clear 'what' but no 'when' / 'Use when...' clause; per the rubric guidelines a missing explicit trigger guidance caps completeness, and here the 'when' is entirely absent.	2 / 5
Trigger Term Quality	Includes relevant terms like 'voice AI', 'real-time', and 'WebSocket communication', but lacks common natural phrases a user would say (e.g., 'voice assistant', 'speech', 'real-time audio') and has no file extensions or synonyms.	3 / 5
Distinctiveness Conflict Risk	The Azure Voice Live SDK niche is specific and clearly distinct from most skills, with only minor overlap risk against other Azure AI / real-time audio skills.	4 / 5
	Total	12 / 20 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-voicelive-ts/SKILL.md
Commit: debb2ec

Reviewed: 1 day 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.