voice-provider-review
Skill2 starsChanged 4 months agoMITView on GitHub
Evaluates pluggable voice telephony providers, audio streaming performance, fallback handling, and latency metrics for VoxDesk AI.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- browser-verificationSkill
- database-migration-safetySkill
- demo-data-integritySkill
- github-authorship-auditSkill
- portfolio-captureSkill
- security-auditSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use when reviewing or adding telephony adapters (Twilio, Vapi, Retell, LiveKit), evaluating speech recognition (STT) or synthesis (TTS) …
- Very specific: line 21
Verify adapter implementation against common VoiceProvider interface.
- Very specific: line 22
Test fallbacks to DemoVoiceProvider when external API credentials are absent or fail health checks.
- Distinctive: line 24
Document provider health status and fallback triggers.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Voice Provider Review Skill
When to Use
Use when reviewing or adding telephony adapters (Twilio, Vapi, Retell, LiveKit), evaluating speech recognition (STT) or synthesis (TTS) providers, or verifying latency benchmarks.
Inputs Required
- Provider specification / API contract.
- Expected audio streaming format (e.g., PCM 16kHz, Mulaw 8kHz).
- Network latency targets (<500ms total response time).
Step-by-Step Process
- Inspect provider SDK capabilities and streaming protocol (WebSocket / WebRTC / HTTP REST).
- Verify adapter implementation against common
VoiceProviderinterface. - Test fallbacks to
DemoVoiceProviderwhen external API credentials are absent or fail health checks. - Measure latency metrics: Speech-to-Text (STT), Language Model (LLM), Text-to-Speech (TTS).
- Document provider health status and fallback triggers.
Decision Tree
- Are credentials present?
- YES -> Run active health check -> If success, mark OPERATIONAL; If fail, mark DEGRADED.
- NO -> Fall back to
DemoVoiceProvider-> Mark DEMO mode.
Validation Checklist
- Provider interface adheres to standard
createAgent,startCall,endCall,verifyWebhookmethods. - No client-side exposure of API keys.
- Latency metrics tracked per call.
Failure Conditions
- Telephony webhook fails signature verification.
- Provider call setup hangs exceeding 3000ms timeout.
Expected Output
Structured provider health audit report with latency breakdowns and fallback verification.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

