CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-ai-voicelive-py

Build real-time voice AI applications with bidirectional WebSocket communication.

Quality

66%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-ai-voicelive-py/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

A strong, highly actionable API-oriented body with executable code for every major feature and efficient token usage. Its weaknesses are the absence of explicit validation checkpoints in the connect-then-stream workflow and a References section pointing at files that are missing from the bundle.

Suggestions

Add explicit validation checkpoints, e.g., wait for 'session.created'/'session.updated' before appending audio, and verify credentials resolve before connecting, plus a retry path for ConnectionError.

Create the referenced bundle files (references/api-reference.md, references/examples.md, references/models.md) or remove the References section — currently all three links are broken.

Move the voice options, audio formats, and turn detection variant tables into references/models.md to slim the main file, and de-duplicate the DefaultAzureCredential example between Authentication and Quick Start.

DimensionReasoningScore

Conciseness

The body is dense with executable code and reference tables with no explanations of concepts Claude already knows. Minor over-explanation/redundancy remains: the DefaultAzureCredential connection example is repeated nearly verbatim in Authentication and Quick Start, and the closing 'This skill is applicable to execute the workflow or actions described in the overview' sentence is pure filler — keeps it below anchor 5.

4 / 5

Actionability

Provides mostly executable, copy-paste-ready guidance: install command, env vars, both auth flows, session update, audio streaming, match-based event handling, and error handling. Minor gaps: 'read_audio_from_microphone()' and 'handle_function()' are undefined placeholders, and 'os'/'json' are used in snippets without being imported — anchor 4 rather than 5.

4 / 5

Workflow Clarity

A buildable sequence is implicitly conveyed by section order (install → env vars → auth → connect → session update → stream/handle events), but there are no explicit validation checkpoints (e.g., wait for 'session.created' before streaming, verify auth before use) or fix-and-retry loops. Sequence present, checkpoints missing or implicit — anchor 3.

3 / 5

Progressive Disclosure

Sections are well organized and the References section clearly signals one-level-deep files, but all three referenced files (references/api-reference.md, references/examples.md, references/models.md) do not exist in the bundle — navigation is broken. Reference-style tables (voice options, audio formats, turn detection variants) are inlined in SKILL.md instead of living in those files. Some structure, but organization and broken references keep it at anchor 3.

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 has a clear what and a fairly distinct technical niche, but it entirely lacks a 'Use when...' trigger clause and natural trigger-term variations, capping both completeness and trigger-term quality. Adding explicit usage triggers would move it to the top of the scale.

Suggestions

Add an explicit trigger clause, e.g., 'Use when building voice assistants, real-time speech-to-speech apps, or audio streaming over WebSockets with the Azure AI Voice Live SDK.'

Expand capability coverage with concrete actions users need, such as 'stream audio in both directions, configure sessions and turn detection, handle transcription and function calls.'

Include natural synonyms and product terms ('speech', 'audio streaming', 'voice agent', 'azure-ai-voicelive') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ('real-time voice AI applications') with one concrete action ('Build') and a mechanism ('bidirectional WebSocket communication'), matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It does not list several specific actions (e.g., streaming audio, session configuration, transcription), so it falls short of anchor 4.

3 / 5

Completeness

The 'what' is clear (build real-time voice AI apps with bidirectional WebSocket communication) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains relevant keywords like 'real-time', 'voice AI', and 'WebSocket', but misses natural variations and synonyms users would say such as 'speech', 'audio streaming', 'voice assistant', or SDK names. Some relevant keywords present, common variations missing — anchor 3.

3 / 5

Distinctiveness Conflict Risk

'Real-time voice AI applications with bidirectional WebSocket communication' describes a mostly distinct niche with minor overlap risk against generic WebSocket or Azure SDK skills. Lacks the distinct trigger phrases needed for anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

14

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/azure-ai-voicelive-py/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.