CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-voicelive-dotnet

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

49

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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 complete, executable code examples and a clear core workflow, but it lacks validation checkpoints in the workflow and keeps reference-style material inline rather than offloading it to bundled files.

Suggestions

Add explicit validation checkpoints to the core workflow (e.g. confirm the session is connected/configured before sending audio, verify audio format negotiation succeeded).

Move the Key Types Reference, Supported Models, and Reference Links tables into bundled reference files (e.g. references/types.md, references/resources.md) and link to them one level deep.

Trim time-sensitive inline detail (specific version numbers, restated best-practice bullets) to reduce token cost, or isolate version info in a clearly marked section.

DimensionReasoningScore

Conciseness

The body is mostly efficient with focused code examples, but it pads in time-sensitive detail (specific version numbers, a full Key Types table that partly restates the code) and some restated best-practice guidance that could be tightened.

2 / 3

Actionability

Provides copy-paste-ready, executable C# for session start, event handling, messaging, and function calling with concrete class names and parameters, matching the level-3 anchor.

3 / 3

Workflow Clarity

A numbered core workflow is present, but there are no validation/verification checkpoints (e.g. confirming the WebSocket is open, checking session readiness) and only a partial error-handling example, leaving sequence checkpoints implicit.

2 / 3

Progressive Disclosure

The file is a single well-organized SKILL.md with no bundle files and clear sections, but the large inline API/type tables and reference links are content that could be split into separate reference files; navigation is flat rather than one-level-deep references.

2 / 3

Total

9

/

12

Passed

Description

42%

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 concrete and domain-specific about what the SDK does, but it omits any explicit "Use when..." trigger guidance, which caps its completeness and limits its usefulness as a skill trigger.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger terms, e.g. 'Use when building real-time voice assistants, voice chat, or bidirectional audio streaming in .NET with Azure.'

Broaden trigger terms to include user-natural phrasings such as 'voice assistant', 'real-time audio', or 'voice chat' rather than only SDK-centric jargon.

Sharpen distinctiveness by tying triggers to the specific SDK context (Azure AI Voice Live / .NET) so it does not conflict with generic speech skills.

DimensionReasoningScore

Specificity

Lists concrete actions ("Build real-time voice AI applications with bidirectional WebSocket communication") for a named domain (Azure AI Voice Live SDK for .NET), matching the level-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

It states what the SDK does but has no "Use when..." clause or equivalent trigger guidance, which the guidelines explicitly cap at 2; since the when is entirely missing rather than implied, it scores 1.

1 / 3

Trigger Term Quality

Includes relevant terms ("real-time voice AI", "bidirectional WebSocket") but lacks natural user-side phrasings like "voice assistant", "voice chat", or "real-time audio"; misses common variations a user would say.

2 / 3

Distinctiveness Conflict Risk

The Azure/.NET/Voice Live framing is fairly specific, but the broad phrase "real-time voice AI applications" could overlap with general speech or realtime skills, so it is not clearly niche.

2 / 3

Total

8

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/antigravity-awesome-skills
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.