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.
71
86%
Does it follow best practices?
Impact
—
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 specifies the domain (C#, Deepgram Text Intelligence /read endpoint), lists concrete capabilities (sentiment, summarization, topic detection, intent recognition), provides explicit trigger guidance ('Use when writing or reviewing C# code...'), and even disambiguates from a related skill for audio. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: sentiment analysis, summarization, topic detection, intent recognition, and names specific API methods like `CreateAnalyzeClient()`, `AnalyzeText`, `AnalyzeUrl`, `AnalyzeFile`. | 3 / 3 |
Completeness | Clearly answers both 'what' (calls Deepgram Text Intelligence API for sentiment, summarization, topic detection, intent recognition) and 'when' (writing or reviewing C# code that calls /read endpoint, with explicit disambiguation from the audio intelligence skill). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms: 'C#', 'Deepgram', 'Text Intelligence', '/read', 'sentiment', 'summarization', 'topic detection', 'intent recognition', 'text URLs', 'AnalyzeClient'. Also distinguishes from audio use case with a redirect to another skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: C# + Deepgram + text intelligence specifically. Explicitly disambiguates from the audio intelligence skill (`deepgram-dotnet-audio-intelligence`), reducing conflict risk significantly. | 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, actionable skill with executable code examples covering all three input methods and a well-organized progressive structure. Its main weaknesses are minor redundancy between the Authentication and Quick Start sections, and the absence of error handling or response validation guidance. The Gotchas section adds genuine value by addressing SDK-specific pitfalls that Claude wouldn't inherently know.
Suggestions
Remove the standalone Authentication section and fold the credential notes into the Quick Start to eliminate the duplicated `Library.Initialize()` / `ClientFactory.CreateAnalyzeClient()` code.
Add a brief error handling example or note about checking response status, especially for URL-based analysis where network failures are likely.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally 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 valuable and lean. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready C# code for all three input methods (text, file, URL). The AnalyzeSchema configuration is concrete with specific boolean properties, and the Key params section gives a clear enumeration of options. | 3 / 3 |
Workflow Clarity | This is primarily a single-action API call skill, so complex workflows aren't needed. However, there's no error handling guidance, no validation of responses, and no mention of what to do when the API call fails or returns unexpected results. For an API integration skill, some error handling or response validation would strengthen it. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from authentication to quick starts to advanced reference. The API reference section provides a layered hierarchy of sources (in-repo, OpenAPI, docs) with specific file paths. Example files are clearly listed. References are one level deep and well-signaled. | 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
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.