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 (not fully surfaced in this SDK), and `deepgram-dotnet-voice-agent` for full-duplex assistants.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 strong trigger terms, clearly states both what it does and when to use it, and proactively distinguishes itself from related skills. The explicit cross-referencing of sibling skills is particularly effective for reducing misrouting. The description uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: CreateListenRESTClient with TranscribeUrl/TranscribeFile, CreateListenWebSocketClient with Connect/Subscribe/Send, and distinguishes 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 methods) and 'when' (opens with 'Use when writing or reviewing C# code in this repo that calls Deepgram Speech-to-Text'). Also explicitly delineates 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', 'summaries', 'sentiment', 'topics', 'voice agent', plus specific API method names that developers would reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: C# + Deepgram STT + specific SDK methods. It even explicitly names sibling skills (deepgram-dotnet-audio-intelligence, deepgram-dotnet-conversational-stt, deepgram-dotnet-voice-agent) to reduce conflict risk and help Claude route correctly. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-organized skill that provides immediately executable C# code for all primary Deepgram STT use cases. Its main strengths are actionability (complete, runnable examples) and progressive disclosure (clear layered references). The main weaknesses are minor verbosity in some sections and the absence of error handling or validation checkpoints in the workflows.
Suggestions
Add error handling examples or validation checkpoints, especially for the WebSocket flow (e.g., checking `connected` result, handling disconnection events, retry patterns).
Trim the Key params section to only the most important/non-obvious parameters, or move the full list to a referenced file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but includes some unnecessary content like the full Key params list that could be a reference, the Central product skills section with install instructions, and the Context7 URLs which add bulk without clear actionability. The 'When to use this product' section is useful but slightly verbose. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready C# code for all three main use cases (REST URL, REST file, WebSocket live). Code includes proper using statements, initialization, and realistic parameter usage. The Gotchas section adds highly specific, actionable warnings about real pitfalls. | 3 / 3 |
Workflow Clarity | The quick starts show clear sequences (initialize → create client → call method → read result), and the WebSocket example correctly shows Subscribe before Connect. However, there are no validation checkpoints or error handling patterns — no guidance on checking response status, handling connection failures, or retry logic for the WebSocket flow. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from authentication to quick starts to advanced references. The API reference section provides a layered hierarchy of in-repo source files, external specs, and docs. Cross-references to other skills (audio-intelligence, conversational-stt, voice-agent) are clearly signaled. Example file paths give easy navigation. | 3 / 3 |
Total | 10 / 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
d0d6fee
- 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.