CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-dotnet-conversational-stt

Use when evaluating, extending, or writing C# code for conversational speech-to-text, Flux-style real-time transcription, or turn-taking streaming in the Deepgram .NET SDK. Identifies missing Flux request parameters (language_hint, eot_threshold), maps existing WebSocket response types, provides the closest supported LiveSchema code path, and guides adding TurnInfo models and Flux examples. Use `deepgram-dotnet-speech-to-text` for standard streaming transcription without turn awareness.

95

1.25x
Quality

95%

Does it follow best practices?

Impact

94%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is dense, executable, and well-structured: it states repo status, gives a working code path, and lays out a concrete extension workflow. The only gap is an implicit rather than explicit validate-fix-retry loop in the workflow.

Suggestions

Add an explicit feedback loop to the workflow (e.g. 'If tests fail, fix the new models/params and re-run before proceeding') to move workflow_clarity from 4 to 5.

Consider splitting the long 'Key params currently available' line into a small table or a reference file if more params are added later, to keep the overview scannable.

DimensionReasoningScore

Conciseness

Lean and repo-specific throughout — current status, key params, gotchas, and references add facts Claude would not already know, with no padding about what WebSockets or libraries are.

5 / 5

Actionability

Provides a copy-paste-ready C# LiveSchema example and a workflow with concrete file paths (e.g. 'Deepgram/Models/Listen/v2/WebSocket/LiveSchema.cs', 'examples/speech-to-text/websocket/flux/Program.cs') covering the common cases.

5 / 5

Workflow Clarity

The 5-step 'adding Flux support' workflow is clearly sequenced with validation checkpoints ('Validate against the AsyncAPI spec', 'Verify field names match', 'Write tests'), but lacks an explicit error-recovery feedback loop.

4 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled, one-level-deep References list pointing to real in-repo paths and external docs; no bundle files are present, but the ~90-line self-contained body is appropriately structured.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it opens with an explicit 'Use when' trigger loaded with natural synonyms, enumerates concrete capabilities, and explicitly disambiguates from a sibling skill to minimize conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Identifies missing Flux request parameters (language_hint, eot_threshold)', 'maps existing WebSocket response types', 'provides the closest supported LiveSchema code path', and 'guides adding TurnInfo models and Flux examples' — covering the skill comprehensively.

5 / 5

Completeness

Explicitly answers both 'what' (identifies params, maps response types, provides code path, guides additions) and 'when' (concrete 'Use when' clause with specific trigger phrases).

5 / 5

Trigger Term Quality

Uses 'Use when... conversational speech-to-text, Flux-style real-time transcription, or turn-taking streaming' — comprehensive coverage of natural terms with synonyms users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Deepgram .NET conversational/Flux STT) with explicit disambiguation: 'Use `deepgram-dotnet-speech-to-text` for standard streaming transcription without turn awareness.'

5 / 5

Total

20

/

20

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.

Validation16 / 16 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.