deepgram-dotnet-conversational-stt
Use when evaluating, extending, or writing C# code for conversational speech-to-text, Flux-style real-time transcription, or turn-taking streaming in the Deepgram .NET SDK. Identifies missing Flux request parameters (language_hint, eot_threshold), maps existing WebSocket response types, provides the closest supported LiveSchema code path, and guides adding TurnInfo models and Flux examples. Use `deepgram-dotnet-speech-to-text` for standard streaming transcription without turn awareness.
94
93%
Does it follow best practices?
Impact
94%
1.25xAverage score across 3 eval scenarios
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 rich trigger terms, clearly states both what the skill does and when to use it, and even disambiguates from a closely related skill. The technical specificity (naming parameters like language_hint, eot_threshold, and models like TurnInfo) ensures precise skill selection. The only minor note is the description is somewhat dense, but the information density is justified given the specialized domain.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: evaluating/extending/writing C# code, identifying missing Flux request parameters (language_hint, eot_threshold), mapping WebSocket response types, providing LiveSchema code paths, and guiding addition of TurnInfo models and Flux examples. | 3 / 3 |
Completeness | Clearly answers both 'what' (identifies missing parameters, maps response types, provides code paths, guides adding models) and 'when' (opens with 'Use when evaluating, extending, or writing C# code for conversational speech-to-text, Flux-style real-time transcription, or turn-taking streaming'). Also includes a disambiguation clause for a related skill. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a developer would use: 'C# code', 'speech-to-text', 'Flux', 'real-time transcription', 'turn-taking', 'streaming', 'Deepgram', '.NET SDK', 'WebSocket', 'LiveSchema', 'TurnInfo'. These are highly specific and natural keywords for this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Deepgram .NET SDK Flux-style transcription with turn-taking. The description even explicitly disambiguates from a related skill ('deepgram-dotnet-speech-to-text' for standard streaming), which further reduces conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that clearly communicates the current state of Flux support in the .NET SDK, provides actionable code for the closest available path, and gives a concrete roadmap for adding full support. Its main weakness is the lack of explicit validation checkpoints in the extension workflow, though the gotchas section partially compensates by warning against inventing unsupported APIs.
Suggestions
Add explicit validation checkpoints to the Flux extension workflow, e.g., 'Validate serialized LiveSchema output matches AsyncAPI spec fields before proceeding to response models' between steps 1 and 2.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Deepgram is, what WebSockets are, or how C# works. Every section serves a purpose: current status, closest code path, what's missing, and how to add it. No unnecessary padding. | 3 / 3 |
Actionability | Provides a fully executable C# code example for the closest supported path, lists specific file paths for modification, names exact classes and properties, and gives a concrete step-by-step workflow for adding Flux support with specific file locations. | 3 / 3 |
Workflow Clarity | The 5-step workflow for adding Flux support is clearly sequenced and logically ordered, but lacks explicit validation checkpoints or feedback loops. Step 4 mentions tests but there's no 'validate before proceeding' gate between steps like verifying AsyncAPI spec compliance before wiring events. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections progressing from status overview to code example to extension workflow. References to in-repo files and external specs are one level deep and clearly signaled. The skill appropriately directs users to other skills for different use cases. | 3 / 3 |
Total | 11 / 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
3b953f0
- 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.