Use when evaluating or extending conversational / Flux-style streaming STT support in this C# SDK. The repo has a latest WebSocket listen client under `Deepgram.Models.Listen.v2.WebSocket`, but it does not currently expose Flux-specific request params or turn-aware response types like `TurnInfo`. Use this skill to document that gap honestly and to guide work on the closest supported surface.
80
70%
Does it follow best practices?
Impact
96%
1.06xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/deepgram-dotnet-conversational-stt/SKILL.mdCorrect client and event wiring
ClientFactory method
100%
100%
Correct namespace import
100%
100%
Subscribe before Connect
100%
100%
LiveSchema for Connect
100%
100%
Valid LiveSchema params only
100%
100%
No Flux-specific params
100%
100%
No invented event models
100%
100%
No invented helpers
100%
100%
ResultResponse handled
100%
100%
UtteranceEndResponse handled
100%
100%
Env var credential pattern
100%
100%
SDK package reference
100%
100%
Honest Flux gap assessment
Flux not first-class
100%
100%
No TurnInfo claim
100%
100%
No invented Flux methods
100%
100%
Missing Flux params identified
100%
100%
API version default noted
0%
100%
Listen.v2.WebSocket positioned correctly
100%
100%
Existing event models listed
100%
100%
Parity requirements identified
100%
100%
No gap minimised
100%
100%
Recommendation made
100%
100%
SDK Flux extension implementation
Real model file(s) created
100%
100%
Flux request params added
100%
100%
Correct namespace placement
37%
25%
Example code produced
100%
100%
Uses existing client surface
0%
60%
No placeholder-only docs
100%
100%
No gap glossed over
100%
100%
Test or validation artifact
100%
100%
ClientFactory env-var credential pattern
62%
100%
JSON property names correct
100%
100%
d0d6fee
Table of Contents
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.