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.

75

2.88x
Quality

64%

Does it follow best practices?

Impact

98%

2.88x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 body is a well-structured, actionable SDK reference with executable code and a clearly sequenced core workflow. It is efficient and well-organized, with only minor gaps in integrated validation and a small amount of boilerplate filler.

Suggestions

Integrate the Error Handling section into the Core Workflow as an explicit validation/retry checkpoint rather than presenting it separately.

Replace the generic 'When to Use' boilerplate ('applicable to execute the workflow or actions described in the overview') with concrete trigger conditions for invoking the skill.

Flesh out the audio playback step in the event loop with a minimal NAudio example so the end-to-end flow is fully executable.

DimensionReasoningScore

Conciseness

The body is code-focused and mostly assumes Claude's competence without over-explaining concepts; only minor filler exists (the boilerplate 'When to Use' line and a redundant one-line intro), fitting 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Provides concrete, copy-paste-ready C# and `dotnet add package` commands covering session config, events, messaging, and function calling, with only minor gaps such as audio playback left as a comment.

4 / 5

Workflow Clarity

The 'Core Workflow' presents four clearly sequenced numbered steps; error handling is documented separately rather than as an integrated validation checkpoint, leaving minor validation gaps — not a destructive/batch operation so the 3-cap does not apply.

4 / 5

Progressive Disclosure

Single-file skill with no bundle files; content is well-organized under clear section headers with explicitly signaled external reference links, though inline reference tables (Key Types, Supported Models) keep it just short of an ideal split.

4 / 5

Total

16

/

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 clearly identifies the skill's domain and a concrete capability but lacks an explicit 'when to use' trigger clause, capping its completeness. It is reasonably specific and distinct but would benefit from natural trigger phrases.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when building real-time voice assistants or live speech apps with Azure AI and .NET.'

Broaden trigger-term coverage with synonyms users actually say, such as 'voice assistant', 'live speech', and 'realtime audio'.

Expand the action list beyond 'build applications' to concrete operations like 'stream bidirectional audio', 'handle function calls', and 'manage voice sessions' for fuller specificity.

DimensionReasoningScore

Specificity

Names the domain ('Azure AI Voice Live SDK for .NET') and one concrete action ('Build real-time voice AI applications with bidirectional WebSocket communication'), but coverage is not comprehensive — matches the 'domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

Has a clear 'what' (real-time voice AI SDK) but no 'Use when...' or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant natural terms ('voice AI', 'real-time voice', '.NET', 'WebSocket') but misses common variations and synonyms users might say ('speech', 'voice assistant'), fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

Targets a distinct Azure-specific .NET niche with minimal overlap risk; only minor overlap with related Azure speech skills, fitting 'mostly distinct; minor overlap risk'.

4 / 5

Total

13

/

20

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
administrakt0r/AI-Agents-Safe-Coding-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.