deepgram-dotnet-text-to-speech
Use when writing or reviewing C# code in this repo that calls Deepgram Text-to-Speech. Covers `ClientFactory.CreateSpeakRESTClient()` with `ToStream` / `ToFile`, and `ClientFactory.CreateSpeakWebSocketClient()` with `Connect`, `SpeakWithText`, `Flush`, and streaming `AudioResponse` events. Use `deepgram-dotnet-voice-agent` for full-duplex assistants instead of one-way synthesis.
86
82%
Does it follow best practices?
Impact
Pending
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 is highly specific, includes rich trigger terms matching developer vocabulary, clearly states both what it does and when to use it, and proactively distinguishes itself from a related skill. The explicit mention of API method names and the boundary with the voice agent skill make it exceptionally well-suited for accurate skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and API methods: CreateSpeakRESTClient with ToStream/ToFile, CreateSpeakWebSocketClient with Connect/SpeakWithText/Flush, and streaming AudioResponse events. Also distinguishes from a related skill for full-duplex assistants. | 3 / 3 |
Completeness | Clearly answers both 'what' (covers REST and WebSocket TTS clients with specific methods) and 'when' (opens with 'Use when writing or reviewing C# code in this repo that calls Deepgram Text-to-Speech'). Also includes a negative trigger distinguishing from the voice agent skill. | 3 / 3 |
Trigger Term Quality | Includes highly relevant natural keywords: 'C#', 'Deepgram', 'Text-to-Speech', 'SpeakRESTClient', 'SpeakWebSocketClient', 'ToStream', 'ToFile', 'streaming', 'AudioResponse', 'one-way synthesis'. These are terms a developer would naturally use when working with this SDK. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: C# + Deepgram TTS specifically. Explicitly differentiates from the related 'deepgram-dotnet-voice-agent' skill for full-duplex assistants, reducing conflict risk with similar skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A solid skill with excellent actionability — the code examples are complete, executable, and well-structured for both REST and WebSocket TTS use cases. The main weaknesses are missing error handling/validation in workflows and some verbosity in the reference and promotional sections. The gotchas section is genuinely valuable and adds information Claude wouldn't inherently know.
Suggestions
Add error handling to the WebSocket example (handle `connected == false`, catch exceptions) and a brief validation step to verify audio output integrity.
Trim the 'Central product skills' section and condense the 5-layer API reference into a more compact format — the layered structure adds tokens without proportional value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary content — the 'Central product skills' section at the bottom is promotional/boilerplate, the authentication section explains things Claude would know (SDK reads env var), and the API reference section with 5 external URLs is verbose. The core code examples are lean though. | 2 / 3 |
Actionability | Both REST and WebSocket quick starts are fully executable, copy-paste ready C# code with correct imports, initialization, and complete workflows. Key params and gotchas provide specific, concrete guidance with actual method names and class paths. | 3 / 3 |
Workflow Clarity | The REST and WebSocket workflows are clear sequences, but there are no validation checkpoints — no error handling examples, no verification that audio output is valid, no feedback loop for connection failures. The WebSocket example does check `connected` but doesn't handle the false case. | 2 / 3 |
Progressive Disclosure | Good structure with clear sections and references to in-repo source files and example paths. However, there are no bundle files to offload detailed content to, and the API reference section with 5 layers of external links feels like it could be better organized. The inline content is reasonably sized but the references section is heavy. | 2 / 3 |
Total | 9 / 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.