deepgram-dotnet-text-intelligence
Use when writing or reviewing C# code in this repo that calls Deepgram Text Intelligence / Read (`/read`) for sentiment, summarization, topic detection, and intent recognition on text or hosted text URLs. Covers `ClientFactory.CreateAnalyzeClient()` with `AnalyzeText`, `AnalyzeUrl`, and `AnalyzeFile`. Use `deepgram-dotnet-audio-intelligence` when the source is audio instead of text.
94
92%
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 rich trigger terms, clearly states both what it does and when to use it, and even proactively disambiguates from a related skill. The explicit mention of API methods, the endpoint path, and the distinction between text vs. audio sources makes this description very effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: sentiment analysis, summarization, topic detection, intent recognition, and specifies the API methods (`AnalyzeText`, `AnalyzeUrl`, `AnalyzeFile`) and factory method (`ClientFactory.CreateAnalyzeClient()`). Very concrete and detailed. | 3 / 3 |
Completeness | Clearly answers both 'what' (calls Deepgram Text Intelligence for sentiment, summarization, topic detection, intent recognition using specific API methods) and 'when' (writing or reviewing C# code that calls /read endpoint, with explicit disambiguation from the audio intelligence skill). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'C#', 'Deepgram', 'Text Intelligence', '/read', 'sentiment', 'summarization', 'topic detection', 'intent recognition', 'text URLs', 'AnalyzeClient', 'AnalyzeText', 'AnalyzeUrl', 'AnalyzeFile'. Good coverage of both domain terms and API-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically C# + Deepgram Text Intelligence + /read endpoint. Explicitly disambiguates from the audio intelligence skill (`deepgram-dotnet-audio-intelligence`), reducing conflict risk significantly. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that provides immediately actionable C# code examples for all three Deepgram text analysis input methods, with a useful Gotchas section that addresses real pitfalls. The progressive disclosure is excellent with layered references. Minor conciseness improvements could be made by eliminating the repeated initialization code between the Authentication and Quick Start sections.
Suggestions
Merge the Authentication section into the Quick Start to avoid repeating Library.Initialize() and ClientFactory.CreateAnalyzeClient() — a brief inline comment in the Quick Start code can note the env var behavior.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy — the Authentication section repeats `Library.Initialize()` and `ClientFactory.CreateAnalyzeClient()` which appear again in the Quick Start. The 'Central product skills' section at the bottom is somewhat tangential. The Gotchas section is genuinely useful and concise. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready C# code for all three input methods (text, file, URL). Key params are enumerated, input types listed, and the code examples are complete with proper using statements and initialization. | 3 / 3 |
Workflow Clarity | This is a single-task skill (call an API, get a response) without destructive or batch operations, so complex validation workflows aren't needed. The sequence is clear: install package → initialize → create client → call method. The Gotchas section serves as an effective error-prevention checklist. | 3 / 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. Example files in the repo are listed for further exploration. | 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
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.