CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-ai-voicelive-java

Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-ai-voicelive-java/SKILL.md
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 content is an efficient, well-structured SDK guide built around executable Java examples with a clear numbered core workflow and explicit error handling. Its main weaknesses are undefined helper placeholders in the code, a pinned beta version, and no progressive disclosure into reference files for the more advanced sections.

Suggestions

Define or stub the helper placeholders ('readAudioChunk()', 'playAudioChunk()', 'parametersSchema') or show their signatures so the examples are copy-paste ready.

Move the pinned version '1.0.0-beta.2' and model names into a clearly labeled version/compatibility note so time-sensitive details don't penalize the evergreen content.

Add an explicit shutdown/validation step (e.g. a complete session close snippet with error recovery) to close the workflow's feedback loop.

DimensionReasoningScore

Conciseness

The body is dominated by executable code with minimal prose padding, and sections like 'Audio Requirements' and 'Key Concepts' are dense and useful. Minor trimmable items exist: the hardcoded version '1.0.0-beta.2' (time-sensitive, not in a deprecated section) and generic filler like 'This skill is applicable to execute the workflow or actions described in the overview.'

4 / 5

Actionability

Concrete Java code covers auth, session configuration, audio input, event handling, and error handling, which is mostly executable. Minor gaps remain: 'readAudioChunk()', 'playAudioChunk()', and 'parametersSchema' are undefined placeholders, and 'session' is referenced outside the scope where section 1 obtained it.

4 / 5

Workflow Clarity

The 'Core Workflow' is explicitly sequenced (1. Start Session, 2. Configure Session Options, 3. Send Audio Input, 4. Handle Events) with concrete code per step, plus a dedicated Error Handling section. Minor validation gaps: no explicit validate/retry feedback loop, and proper session close appears only as a best-practices bullet.

4 / 5

Progressive Disclosure

No bundle files exist; the single SKILL.md is well-sectioned with clear headers and a 'Reference Links' table pointing one level deep to GitHub source and samples. Inline detail sections (Voice Configuration variants, Function Calling) could be split into reference files, so structure is good but not fully split.

4 / 5

Total

16

/

20

Passed

Description

57%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 is concise, in third person, and highly distinctive, but it omits any 'Use when...' trigger guidance and lacks natural trigger-term variations. It states one concrete capability without enumerating the SDK's main actions, leaving it adequate but not comprehensive.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when building Java voice assistants, real-time speech applications, or WebSocket audio streaming with Azure AI.'

Include natural synonyms and trigger variations users would actually say, such as 'speech', 'audio streaming', 'voice agent', and 'realtime conversation'.

Enumerate 1-2 more concrete capabilities (e.g. session configuration, turn detection, audio transcription, function calling) to raise specificity.

DimensionReasoningScore

Specificity

Names the domain ('Azure AI VoiceLive SDK for Java') and one concrete capability ('Real-time bidirectional voice conversations with AI assistants using WebSocket'), but does not list several specific actions like session management, audio streaming, or turn detection. It sits at 'names domain and 1-2 concrete actions' rather than 'several specific actions'.

3 / 5

Completeness

The 'what' is clearly stated (real-time bidirectional voice conversations via WebSocket), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Contains relevant keywords ('Azure', 'VoiceLive', 'voice', 'Java', 'real-time', 'WebSocket') but misses common natural variations users would say such as 'speech', 'audio', 'voice assistant', or 'realtime audio streaming'.

3 / 5

Distinctiveness Conflict Risk

'Azure AI VoiceLive SDK for Java' identifies a highly specific niche with distinct triggers; it is unlikely to be confused with any other skill, matching 'clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

14

/

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.

Validation — 15 / 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/agentic-awesome-skills

Path

skills/azure-ai-voicelive-java/SKILL.md

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.