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
93%
Does it follow best practices?
Impact
—
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 clearly specifies the domain (C# Deepgram STT), lists concrete API methods and actions, provides explicit 'Use when' guidance, and even disambiguates from related skills. The description is concise yet comprehensive, with strong trigger terms covering both natural language and technical specifics.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and API methods: CreateListenRESTClient with TranscribeUrl/TranscribeFile, CreateListenWebSocketClient with Connect/Subscribe/Send, plus specific related skills for summaries/sentiment/topics, conversational STT, and voice agents. | 3 / 3 |
Completeness | Clearly answers both 'what' (calling Deepgram STT APIs for prerecorded/live transcription with specific client factories and methods) and 'when' (explicitly starts with 'Use when writing or reviewing C# code in this repo that calls Deepgram Speech-to-Text'). Also provides disambiguation guidance for related skills. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'C#', 'Deepgram', 'Speech-to-Text', 'prerecorded', 'live transcription', 'WebSocket', specific method names like 'TranscribeUrl'/'TranscribeFile', plus domain terms like 'summaries', 'sentiment', 'topics', 'voice agent', 'conversational'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: C# + Deepgram Speech-to-Text for a specific repo. It even disambiguates from related sibling skills (deepgram-dotnet-audio-intelligence, deepgram-dotnet-conversational-stt, deepgram-dotnet-voice-agent), reducing conflict risk significantly. | 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 provides concrete, executable C# examples for both REST and WebSocket Deepgram transcription. The content is well-organized with clear skill boundaries, actionable code, and useful gotchas. The main weakness is limited error handling and recovery guidance in the workflows, particularly for the REST path which has no validation or error checking shown.
Suggestions
Add basic try/catch or error-checking patterns for REST calls (e.g., checking for null response or handling DeepgramException) to improve workflow robustness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows C#, async/await, and SDK patterns. No unnecessary explanations of what speech-to-text is or how WebSockets work. Every section delivers actionable information without padding. | 3 / 3 |
Actionability | All code examples are fully executable C# with correct using statements, proper initialization, and realistic parameters. The REST URL, REST file, and WebSocket examples are copy-paste ready with complete method signatures and response navigation. | 3 / 3 |
Workflow Clarity | The WebSocket example does include a connection check (if !connected), which is good. However, the workflows are presented as isolated quick-starts rather than sequenced processes with validation checkpoints. There's no explicit error handling guidance for REST calls or recovery steps for WebSocket disconnections. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections progressing from authentication to quick starts to parameters to gotchas. References to other skills (audio-intelligence, conversational-stt, voice-agent) are clearly signaled at the top. In-repo file paths and external docs are listed in a dedicated References section. No deeply nested references. | 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.