deepgram-dotnet-audio-intelligence
Use when writing or reviewing C# code in this repo that enables Deepgram intelligence overlays on Speech-to-Text requests. Covers `PreRecordedSchema` analytics flags such as `Summarize`, `Topics`, `Intents`, `Sentiment`, `DetectLanguage`, `DetectEntities`, `Diarize`, and `Redact`, plus the smaller live-streaming subset on `LiveSchema`. Use `deepgram-dotnet-speech-to-text` for plain transcription and `deepgram-dotnet-text-intelligence` for analytics on already-transcribed text.
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 clearly defines its scope (Deepgram intelligence overlays on Speech-to-Text in C#), lists specific capabilities (8 named analytics flags across two schema types), and explicitly disambiguates from related skills. The 'Use when' clause is present and well-formed, and the trigger terms cover both technical specifics and natural user language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and capabilities: analytics flags like Summarize, Topics, Intents, Sentiment, DetectLanguage, DetectEntities, Diarize, and Redact, plus distinguishes PreRecordedSchema from LiveSchema. Very detailed. | 3 / 3 |
Completeness | Clearly answers both 'what' (enables Deepgram intelligence overlays on STT requests, covering specific analytics flags) and 'when' (opens with 'Use when writing or reviewing C# code in this repo'). Also provides explicit disambiguation guidance for when to use other skills instead. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'C#', 'Deepgram', 'Speech-to-Text', 'summarize', 'topics', 'intents', 'sentiment', 'diarize', 'redact', 'live-streaming', 'intelligence overlays'. Also references related skill names for disambiguation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit disambiguation from two related skills ('deepgram-dotnet-speech-to-text' for plain transcription and 'deepgram-dotnet-text-intelligence' for text analytics). The niche of intelligence overlays on STT is clearly carved out. | 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 solid, well-structured skill that provides actionable code examples and good progressive disclosure through layered references. Its main weaknesses are minor verbosity in some sections and the absence of error handling or validation guidance when making API calls with intelligence features. The feature availability table and gotchas section are particularly valuable additions.
Suggestions
Add a brief error handling example or validation step (e.g., checking response status, verifying that requested intelligence features returned data) to improve workflow clarity.
Trim the authentication section — the detail about what happens when credentials are missing is unnecessary for Claude, and the 'Central product skills' footer could be shortened to a single line.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., the authentication section explaining what happens when credentials are missing, the verbose 'When to use this product' section). The feature availability table and gotchas are well-justified, but the extensive list of product doc links and the 'Central product skills' section add bulk. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples for both REST and WebSocket paths with concrete schema configurations. The quick start examples are complete with imports, client creation, and response handling. | 3 / 3 |
Workflow Clarity | The skill clearly separates REST vs WebSocket paths and provides a feature availability table, but there are no validation checkpoints or error handling steps. For operations involving API calls that could fail (auth issues, invalid params, unsupported feature combinations), there's no guidance on verifying results or handling errors. | 2 / 3 |
Progressive Disclosure | Well-structured with a clear overview, quick starts, then layered API references pointing to in-repo source files, OpenAPI specs, and external docs. References are one level deep and clearly signaled. The separation between quick start, key params, API reference, and example files is logical and navigable. | 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.