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.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that is highly specific, includes strong trigger terms, clearly answers both what and when, and explicitly disambiguates from related skills. The cross-references to other skills for adjacent use cases (TTS and STT) are particularly effective for reducing conflict risk. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and components: CreateAgentWebSocketClient(), SettingsSchema, event subscriptions, microphone audio streaming, injected user messages, and function-call-related message types. These are highly specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (building an interactive Deepgram Voice Agent over WebSocket with specific components) and 'when' (writing or reviewing C# code in this repo for that purpose). Also includes explicit boundary guidance directing users to other skills for TTS-only or STT-only flows. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'C#', 'Deepgram', 'Voice Agent', 'WebSocket', 'microphone audio streaming', 'function-call', plus specific API references like 'ClientFactory.CreateAgentWebSocketClient()'. Also differentiates from related skills with explicit cross-references. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Deepgram Voice Agent, WebSocket, C#) and explicitly disambiguates from related skills ('deepgram-dotnet-text-to-speech' for synthesis, 'STT skills' for transcription-only), minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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, well-structured skill that provides actionable, executable C# code for Deepgram Voice Agent WebSocket integration. Its main strengths are concrete code examples and good progressive disclosure with layered references. The primary weaknesses are some verbosity in comments/explanations and the lack of error handling/validation steps in the workflow, which is important for WebSocket-based streaming operations.
Suggestions
Add explicit error handling and reconnection logic to the quick start (e.g., what to do when `Connect` returns false, or when the WebSocket drops mid-session).
Trim the multi-line comment in the Authentication section — Claude doesn't need a paragraph explaining why an empty string is shown; a single-line comment like `// Uses DEEPGRAM_API_KEY env var` suffices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some unnecessary verbosity — the long comment block in the Authentication section explaining what an empty string means, and the 'When to use this product' section restates things Claude could infer. The event/model listing is lean, but the overall content could be tightened. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready C# code for authentication, quick start, and microphone streaming. Concrete method names, model paths, and settings are all specified. The gotchas section gives specific, actionable warnings about real pitfalls. | 3 / 3 |
Workflow Clarity | The quick start shows a clear sequence (subscribe → configure → connect → send), but there's no explicit validation or error handling for the WebSocket connection beyond checking the boolean. For a WebSocket-based streaming operation, missing error recovery/reconnection guidance and no feedback loop for connection failures caps this at 2. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from authentication to quick start to advanced topics. The API reference section provides a well-organized layered hierarchy of in-repo sources, external docs, and context references — all one level deep. Example file paths are clearly listed for further exploration. | 3 / 3 |
Total | 10 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/deepgram-dotnet-sdk
- Commit
d0d6fee
- 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.