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.

72

Quality

88%

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

90%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 concise, highly actionable skill body built around three complete executable examples and concrete gotchas, with clean section organization. The main gap is uneven validation: the WebSocket flow has an explicit failure checkpoint while the REST flows lack any verify/retry step.

Suggestions

Add a brief validation/verify step after the REST TranscribeUrl and TranscribeFile examples (e.g. null/empty `response.Results` check) to match the WebSocket flow's `if (!connected)` checkpoint.

Surface the 'Example files in this repo' list earlier (e.g. a one-line pointer under each Quick start) so readers can navigate to the matching example without scanning to the end.

Clarify the `Send` method mentioned in the description: the body shows `Microphone(liveClient.Send)` but never documents calling `Send` directly, leaving a small gap between the description's promises and the body's coverage.

DimensionReasoningScore

Conciseness

Lean and code-first throughout: it jumps straight to executable snippets, lists key params compactly, and never explains concepts Claude already knows (no 'what a WebSocket is' or 'how transcription works' padding).

5 / 5

Actionability

Three fully executable, copy-paste-ready code blocks (REST URL, REST file, WebSocket live) covering the common cases, plus concrete key-param lists with file paths and a gotchas section of real, specific pitfalls.

5 / 5

Workflow Clarity

The WebSocket path has an explicit validation checkpoint (`if (!connected)` → error and return), but the REST paths have no equivalent verify step and the broader flow has no error-recovery feedback loop, so checkpoints are present but uneven.

4 / 5

Progressive Disclosure

Well-organized into clear sections (When to use, Authentication, Quick starts, Key params, References, Gotchas) with all references one level deep (external docs URLs and in-repo file paths); no bundle files exist, so there is nothing to split out, but the inline key-param and example-file lists could signal navigation slightly better.

4 / 5

Total

18

/

20

Passed

Description

87%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, third-person description with an explicit 'Use when' trigger, concrete API surface enumeration, and clear differentiation from sibling skills. Its only weakness is relying on SDK method names as trigger terms and omitting user-natural synonyms/extensions.

DimensionReasoningScore

Specificity

Names the domain and several concrete API actions (`CreateListenRESTClient()` with `TranscribeUrl` / `TranscribeFile`, `CreateListenWebSocketClient()` with `Connect`, `Subscribe`, and `Send`), but the actions are surface-level method enumerations rather than the broader transcription capabilities, leaving minor coverage gaps versus a fully comprehensive list.

4 / 5

Completeness

Explicitly answers both 'what' (covers the listed client/method surfaces for REST and WebSocket transcription) and 'when' (opens with 'Use when writing or reviewing C# code in this repo that calls Deepgram Speech-to-Text'), with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases like 'writing or reviewing C# code', 'Deepgram Speech-to-Text', and 'prerecorded or live transcription', but it leans on SDK method names as triggers and omits common synonyms or file extensions a user might say.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Speech-to-Text listen transcription only) and explicitly diverts to three sibling skills (`deepgram-dotnet-audio-intelligence`, `deepgram-dotnet-conversational-stt`, `deepgram-dotnet-voice-agent`), giving minimal conflict risk.

5 / 5

Total

18

/

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.