CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-dotnet-voice-agent

Use when writing or reviewing C# code in this repo that builds an interactive Deepgram Voice Agent over WebSocket. Covers `ClientFactory.CreateAgentWebSocketClient()`, `SettingsSchema`, event subscriptions, microphone audio streaming, injected user messages, and function-call-related message types. Use `deepgram-dotnet-text-to-speech` for one-way synthesis and STT skills for transcription-only flows.

75

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 tight, executable reference for the .NET Voice Agent SDK with real code, repo-specific gotchas, and clean sectioning. The only soft spot is workflow framing, which lacks an explicit validation-feedback loop.

Suggestions

Convert the Quick start into a short numbered checklist with an explicit 'verify connection succeeded before sending' checkpoint to strengthen workflow clarity.

Add a one-line validate/retry note for the microphone path (e.g. confirm PortAudio is available before microphone.Start()) since that dependency is a known failure point.

DimensionReasoningScore

Conciseness

Lean throughout: sections deliver repo-specific symbol names, events, and gotchas Claude would not already know, with no padding or explanations of basic concepts like WebSocket.

5 / 5

Actionability

Copy-paste-ready Quick start and microphone-streaming code with real constructor params, a connection check, and explicit cleanup; specific examples cover the common no-mic and mic cases.

5 / 5

Workflow Clarity

The quick start shows a clear sequence (subscribe, configure, connect, check, send, stop) with a connection-failure checkpoint, but the flow is not framed as an explicit numbered checklist with a validate-fix-retry loop.

4 / 5

Progressive Disclosure

Single well-organized file with clearly signaled one-level-deep references (in-repo source paths, AsyncAPI URL, product docs) and no nested reference chains; appropriate for a self-contained API skill.

5 / 5

Total

19

/

20

Passed

Description

92%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.

A strong, specific description with explicit trigger guidance and clear boundary steering against sibling Deepgram skills. The only minor gap is trigger-term synonym coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities and names exact API symbols (`ClientFactory.CreateAgentWebSocketClient()`, `SettingsSchema`, microphone audio streaming, injected user messages, function-call message types), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (builds an interactive Deepgram Voice Agent over WebSocket with the listed capabilities) and 'when' ('Use when writing or reviewing C# code in this repo that builds...').

5 / 5

Trigger Term Quality

Natural trigger phrase 'writing or reviewing C# code' plus domain terms 'Deepgram Voice Agent' and 'WebSocket' give good coverage, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

Scoped to interactive Voice Agent over WebSocket and explicitly redirects one-way synthesis and transcription to other named skills, giving a clear niche with minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
deepgram/deepgram-dotnet-sdk
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.