CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

86%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

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 clear feature delineation between REST and WebSocket paths. Its main weaknesses are minor verbosity in some sections and the lack of validation/error-handling guidance for API interactions. The gotchas section adds genuine value by highlighting non-obvious SDK behaviors.

Suggestions

Add a brief error-handling example or validation step (e.g., checking response status, handling auth failures) to improve workflow clarity.

Trim the authentication section — the env var fallback and explicit credential details could be condensed to one line since Claude can read the SDK source.

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary explanation (e.g., the authentication section explaining env var fallback behavior, the 'When to use this product' section restating what Claude could infer). The feature availability table and gotchas are well-justified, but the extensive external links list and '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 feature availability table, key params list, and gotchas section give specific, actionable guidance that Claude can directly apply.

3 / 3

Workflow Clarity

The skill clearly separates REST vs WebSocket paths and provides a feature availability matrix, 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

Content is well-structured with clear sections progressing from overview to quick starts to details. References to in-repo source files, external docs, and related skills are clearly signaled and one level deep. The separation of concerns (pointing to other skills for plain STT and text intelligence) is well done.

3 / 3

Total

10

/

12

Passed

Description

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, lists concrete capabilities with specific flag names, and explicitly disambiguates from related sibling skills. The 'Use when' clause is present at the start, trigger terms are natural and comprehensive, and the boundary guidance minimizes conflict risk with adjacent skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and capabilities: analytics flags like Summarize, Topics, Intents, Sentiment, DetectLanguage, DetectEntities, Diarize, and Redact, plus distinguishes PreRecordedSchema vs LiveSchema usage.

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... that enables Deepgram intelligence overlays'). Also provides explicit boundary guidance on when to use sibling 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), clearly carving out its niche as the intelligence-overlay-on-STT skill.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
deepgram/deepgram-dotnet-sdk
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.