CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-voicelive-ts

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

83

2.77x
Quality

58%

Does it follow best practices?

Impact

100%

2.77x

Average score across 6 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-ts/SKILL.md

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

SKILL.md
Quality
Evals
Security

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 content is a strong, executable reference for the SDK with clear structure and actionable code, but it is monolithic — inlining substantial API reference material that would be better offloaded to bundle files — and carries minor redundancy and a fluff closing line.

Suggestions

Move the large API reference (Key Types, the full event-handler catalog, and the voice/model/audio-format tables) into dedicated bundle files under references/ and link to them from SKILL.md.

De-duplicate the repeated updateSession/subscribe patterns by consolidating into one canonical example and cross-referencing it from other sections.

Remove the placeholder 'When to Use' line ("This skill is applicable to execute the workflow or actions described in the overview.") and replace it with concrete applicability criteria.

DimensionReasoningScore

Conciseness

The body is mostly efficient reference material assuming Claude's competence, but repeats the updateSession/subscribe pattern across several sections and ends with a fluff 'When to Use' line, so it could be tightened beyond minor trimming.

3 / 5

Actionability

It provides concrete, copy-paste-ready TypeScript across auth, quick start, events, function calling, and error handling, but undefined helpers (playAudioChunk, fetchWeather) and a 'see samples' stub are minor gaps preventing a clean 5.

4 / 5

Workflow Clarity

The Quick Start lays out a clear client-to-session-to-subscribe sequence with a teardown checkpoint, but lacks explicit validation or error-recovery feedback loops; no destructive/batch cap applies since real-time session management is not in that category.

4 / 5

Progressive Disclosure

The body has good section headers but inlines a large API reference (types, full event-handler list, voice/model/format tables) that belongs in separate bundle files; no bundle files are provided and references are only external URLs.

3 / 5

Total

14

/

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 conveys what the SDK does and occupies a distinct niche, but it omits any explicit trigger guidance ('Use when...') and offers limited trigger-term coverage, which caps completeness and trigger quality at the midpoint.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when building real-time voice assistants, speech-to-speech bots, or bidirectional audio streaming apps with Azure AI.'

Broaden trigger-term coverage with natural synonyms such as 'voice assistants', 'speech AI', 'real-time audio', and 'WebSocket voice streaming'.

List one or two more concrete actions (e.g. 'stream audio input/output', 'handle tool/function calls') to lift specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

The description names the domain ("Azure AI Voice Live SDK") and one concrete action ("Build real-time voice AI applications") plus a capability ("bidirectional WebSocket communication"), but coverage is not comprehensive enough for a 4.

3 / 5

Completeness

The 'what' is clearly stated but no 'Use when...' trigger guidance exists; per the rubric a missing explicit 'when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

It includes relevant natural terms like "real-time voice AI applications" but lacks common variations, synonyms, or file extensions, fitting the anchor for missing common variations.

3 / 5

Distinctiveness Conflict Risk

It targets a specific Azure real-time voice niche with minimal conflict risk, though minor overlap exists with other Azure AI or OpenAI realtime skills.

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.