azure-ai-voicelive-py
Build real-time voice AI applications with bidirectional WebSocket communication.
46
48%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/azure-ai-voicelive-py/SKILL.mdQuality
Discovery
32%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 identifies a clear domain (real-time voice AI with WebSockets) but is too terse and lacks both specific concrete actions and explicit trigger guidance. It would benefit significantly from listing specific capabilities and adding a 'Use when...' clause with natural user terms.
Suggestions
Add a 'Use when...' clause with trigger terms like 'voice assistant', 'audio streaming', 'speech-to-text', 'real-time audio', 'conversational AI', or 'WebSocket audio'.
List specific concrete actions such as 'stream audio input/output', 'handle voice activity detection', 'manage WebSocket connections for audio', 'implement turn-taking logic'.
Include common file types or API references users might mention (e.g., 'OpenAI Realtime API', 'Twilio Media Streams', 'LiveKit') to improve trigger term coverage and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('voice AI applications') and a key technical approach ('bidirectional WebSocket communication'), but does not list multiple concrete actions like 'stream audio', 'handle turn-taking', 'transcribe speech', etc. | 2 / 3 |
Completeness | Describes what the skill does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also not very detailed, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'voice AI', 'real-time', and 'WebSocket', but misses common user variations such as 'speech-to-text', 'audio streaming', 'voice assistant', 'STT', 'TTS', or 'conversational AI'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'voice AI' and 'WebSocket' is somewhat distinctive, but 'real-time' and 'applications' are generic enough that it could overlap with other real-time communication or WebSocket-related skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable SDK reference skill with excellent concrete code examples covering authentication, streaming, event handling, and common patterns. Its main weaknesses are length (reference tables and repeated patterns inflate the file beyond what's needed in the overview) and the absence of explicit validation/verification steps in workflows. The referenced bundle files are missing, undermining the progressive disclosure strategy.
Suggestions
Move the voice options table, audio formats table, and turn detection options into the referenced models.md or api-reference.md to reduce SKILL.md length and improve progressive disclosure.
Add explicit validation checkpoints: verify session.created event before proceeding, check connection health, and include a reconnection pattern for dropped WebSocket connections.
Remove the Quick Start section's redundant authentication setup by referencing the Authentication section above it, or consolidate into a single complete example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some redundancy (Quick Start repeats the authentication pattern already shown above, voice/audio format tables add reference bulk that could be in a separate file, and the boilerplate 'When to Use' and 'Limitations' sections add little value). | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready Python code for every major operation: connection, session config, audio streaming, event handling, function calls, error handling. All examples are concrete with real imports and method calls. | 3 / 3 |
Workflow Clarity | The skill covers many patterns clearly (manual turn mode, interrupt handling, function call response flow), but lacks explicit validation checkpoints or feedback loops. For a WebSocket-based real-time system, there's no guidance on verifying connection health, handling reconnection, or validating session setup succeeded before proceeding. | 2 / 3 |
Progressive Disclosure | References to api-reference.md, examples.md, and models.md are listed at the bottom, but no bundle files are provided so these references are unverifiable. The main file is quite long (~250 lines of content) with reference tables (voices, audio formats) that would be better placed in the referenced files, keeping the SKILL.md leaner. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
9e5d4dd
- 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.