CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-voicelive-py

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

52

Quality

59%

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.

The body is a well-organized, highly actionable reference with executable code throughout, but it inlines a lot of material that the (nonexistent) reference files are meant to hold and lacks explicit validation checkpoints. Creating the referenced bundle files and tightening the workflow would lift the weaker dimensions.

Suggestions

Create references/api-reference.md, references/examples.md, and references/models.md and move the bulk of the inline event catalog, voice/format tables, and type details there, keeping SKILL.md as an overview.

Add a short end-to-end "Workflow" section with explicit checkpoints (e.g. verify connection opened, confirm session.updated event received, validate audio format before streaming) rather than only scattered patterns.

Replace undefined helper stubs (read_audio_from_microphone, play_audio, handle_function) with concrete implementations or clearly marked placeholders so examples are copy-paste runnable.

DimensionReasoningScore

Conciseness

The body is dense and code/table-heavy with almost no padding, and it does not explain concepts Claude already knows; the only redundancy is the intro line repeating the description. This is efficient with minor trimmable instances, matching anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

It provides extensive copy-paste-ready code across installation, auth, quick start, session config, audio streaming, and event handling. It falls short of anchor 5 only because helper stubs like read_audio_from_microphone(), play_audio(), and handle_function() are undefined, so examples are not fully runnable as-is.

4 / 5

Workflow Clarity

Quick Start gives a usable sequence (connect, session.update, event loop, break on response.done) with error handling shown, but there are no explicit validation checkpoints or feedback loops. This is reference-style rather than a checkpointed workflow, matching anchor 3.

3 / 5

Progressive Disclosure

A References section clearly signals one-level-deep pointers, but the referenced files (references/api-reference.md, examples.md, models.md) do not exist in the bundle, and substantial reference material (full event catalog, voice/format tables) is inlined rather than split out. This matches anchor 3 (references present, content that should be separate is inline).

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 states what the skill does and targets a reasonably distinct niche, but it omits any "Use when..." trigger guidance and relies on somewhat technical language. Adding explicit activation triggers would raise completeness and trigger-term quality.

Suggestions

Append a "Use when..." clause naming concrete triggers, e.g. "Use when building real-time voice assistants, live audio streaming, or bidirectional WebSocket voice apps with Azure AI."

Add natural user-facing synonyms (e.g. "live voice", "speech", "realtime audio") alongside the technical "bidirectional WebSocket" phrasing.

List a couple more concrete actions (e.g. "stream audio, handle function calls, manage conversation state") to lift specificity from one action to several.

DimensionReasoningScore

Specificity

"Build real-time voice AI applications with bidirectional WebSocket communication" names the domain and one concrete action with a technical qualifier, but does not list several distinct actions. It sits at anchor 3 (domain + 1-2 concrete actions) and below 4, which requires multiple specific actions.

3 / 5

Completeness

The description gives a clear "what" (build real-time voice AI apps) but no "Use when..." trigger clause, so per the rubric guideline completeness is capped at 3. It does not reach anchor 4, which requires an explicit (if imperfect) "when".

3 / 5

Trigger Term Quality

"voice AI" and "real-time voice AI" are natural terms a user might say, but "bidirectional WebSocket communication" is technical jargon and common synonyms/variations are missing. This matches anchor 3 (some relevant keywords, missing common variations).

3 / 5

Distinctiveness Conflict Risk

"real-time voice AI" plus "bidirectional WebSocket" carves a fairly distinct niche with only minor overlap risk against other Azure/realtime skills. It is more distinct than anchor 3 but lacks the explicit trigger phrases that would 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.

Validation14 / 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
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.