CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-dotnet-speech-to-text

Use when writing or reviewing C# code in this repo that calls Deepgram Speech-to-Text for prerecorded or live transcription. Covers `ClientFactory.CreateListenRESTClient()` with `TranscribeUrl` / `TranscribeFile`, and `ClientFactory.CreateListenWebSocketClient()` with `Connect`, `Subscribe`, and `Send`. Use `deepgram-dotnet-audio-intelligence` for summaries/sentiment/topics overlays, `deepgram-dotnet-conversational-stt` for Flux-specific work, and `deepgram-dotnet-voice-agent` for full-duplex assistants.

76

Quality

93%

Does it follow best practices?

Impact

No eval scenarios have been run

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 high-quality skill that efficiently covers both REST and WebSocket Deepgram STT usage with executable C# examples, clear routing to related skills, and well-organized progressive disclosure. Its main weakness is the lack of explicit validation/error-recovery steps in the workflows, particularly for the REST path where no error handling is shown. The gotchas section is excellent and adds genuine value by documenting SDK-specific pitfalls.

Suggestions

Add brief error handling patterns for REST calls (e.g., try/catch with specific exception types or response status checking) to improve workflow clarity.

DimensionReasoningScore

Conciseness

The skill is lean and efficient. It avoids explaining what Deepgram is, what REST/WebSocket means, or how C# async works. Every section delivers actionable content without padding. The routing section at the top efficiently directs to other skills.

3 / 3

Actionability

All code examples are fully executable C# with correct using statements, client initialization, and complete call chains. The REST URL, REST file, and WebSocket live examples are copy-paste ready with real SDK types and methods.

3 / 3

Workflow Clarity

The WebSocket example includes a good sequence (Subscribe before Connect, check connection, start/stop microphone), and the gotchas section warns about ordering. However, there are no explicit validation checkpoints or error recovery loops for the REST flows, and the WebSocket error handling is minimal (just a console error and return).

2 / 3

Progressive Disclosure

The skill is well-structured with clear sections progressing from authentication to quick starts to params to references. It appropriately points to other skills for related concerns, references in-repo source files and example paths, and links to external API docs — all one level deep with clear signaling.

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 specifies concrete API methods and actions, provides explicit 'Use when' guidance, includes natural trigger terms developers would use, and carefully distinguishes itself from related skills. The cross-referencing of related skills for different use cases is particularly strong, reducing conflict risk. The description is concise yet comprehensive.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and API methods: CreateListenRESTClient with TranscribeUrl/TranscribeFile, CreateListenWebSocketClient with Connect/Subscribe/Send, plus specific use cases like summaries/sentiment/topics overlays, conversational STT, and voice agents.

3 / 3

Completeness

Clearly answers both 'what' (calling Deepgram STT APIs for prerecorded/live transcription with specific client methods) and 'when' (opens with 'Use when writing or reviewing C# code in this repo that calls Deepgram Speech-to-Text'). Also provides explicit guidance on when to use related skills instead.

3 / 3

Trigger Term Quality

Includes strong natural keywords users would say: 'C#', 'Deepgram', 'Speech-to-Text', 'transcription', 'prerecorded', 'live', 'WebSocket', 'sentiment', 'summaries', 'voice agent', plus specific API method names that developers would reference.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: C# + Deepgram Speech-to-Text + specific API methods. It even distinguishes itself from related skills (deepgram-dotnet-audio-intelligence, deepgram-dotnet-conversational-stt, deepgram-dotnet-voice-agent) by explicitly delineating boundaries.

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.