CtrlK
BlogDocsLog inGet started
Tessl Logo

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

1.25x
Quality

93%

Does it follow best practices?

Impact

94%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

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 well-crafted 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 SDK extension workflow, which would be important for ensuring correctness when modifying SDK internals. The upfront routing to alternative skills and the 'Gotchas' section are particularly valuable.

Suggestions

Add explicit validation checkpoints to the Flux support workflow, e.g., 'Validate new LiveSchema properties serialize correctly to JSON matching the AsyncAPI spec before proceeding to step 3' and 'Run existing test suite to confirm no regressions after wiring new events.'

DimensionReasoningScore

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 padding or unnecessary context.

3 / 3

Actionability

Provides a fully executable C# code example for the closest supported path, lists specific class names and file paths for extending the SDK, and gives concrete parameter names. The workflow for adding Flux support references specific files and models to create.

3 / 3

Workflow Clarity

The 5-step workflow for adding Flux support is clearly sequenced, 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. For SDK modification (a potentially breaking operation), validation checkpoints would be important.

2 / 3

Progressive Disclosure

Content is well-structured with clear sections progressing from status overview to code to extension workflow. References to specific in-repo files, external specs, and related skills are clearly signaled. The skill appropriately directs users to other skills for different use cases at the top.

3 / 3

Total

11

/

12

Passed

Description

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 clearly defines its niche (Deepgram .NET SDK Flux/turn-taking transcription), lists specific concrete actions, includes abundant natural trigger terms, and explicitly addresses both 'what' and 'when'. The inclusion of a boundary clause distinguishing it from a related skill is a strong practice that further reduces conflict risk.

DimensionReasoningScore

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 Flux parameters, maps WebSocket response types, provides LiveSchema code paths, guides adding TurnInfo 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 negative boundary distinguishing it from the standard streaming skill.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'C# code', 'speech-to-text', 'Flux', 'real-time transcription', 'turn-taking', 'streaming', 'Deepgram', '.NET SDK', 'WebSocket', 'LiveSchema', 'TurnInfo'. These are highly specific domain terms a developer would naturally use.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: Deepgram .NET SDK Flux-style transcription with turn-taking. The description even explicitly differentiates itself from a sibling skill (`deepgram-dotnet-speech-to-text` for standard streaming), reducing conflict risk.

3 / 3

Total

12

/

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.

Validation11 / 11 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.