CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-java-conversational-stt

Use when writing or reviewing Java code in this repo that calls Deepgram Conversational STT v2 / Flux over `/v2/listen`. Covers `client.listen().v2().v2WebSocket()`, `V2ConnectOptions`, `onTurnInfo`, and turn-aware close handling. Use `deepgram-java-speech-to-text` for standard v1 transcription and `deepgram-java-voice-agent` for fully interactive assistants. Triggers include "flux", "conversational stt", "listen v2", "turn detection", "end of turn", and "eot".

76

Quality

93%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

This is a strong, well-crafted skill that efficiently teaches Claude how to use Deepgram's Conversational STT v2 in Java. The code is executable and complete, the gotchas section adds genuine value by highlighting SDK-specific pitfalls, and the progressive disclosure is excellent with layered references. The only notable weakness is the lack of explicit error-handling or validation steps in the workflow, though this is partially mitigated by the gotchas section.

Suggestions

Add a brief error-handling checkpoint after `connect(...).get(...)` — e.g., wrapping in try-catch with guidance on common failure modes (auth errors, invalid model string) to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

The content is lean and efficient. It doesn't explain what WebSockets are, what STT means, or how Java works. Every section earns its place — the 'When to use' section is brief and differentiating, the code is minimal, and the gotchas are specific to this SDK rather than general knowledge.

3 / 3

Actionability

The quick start provides fully executable, copy-paste-ready Java code with correct imports, connection setup, event handling, and close flow. Key parameters are enumerated with their exact method names. The authentication section is concrete and complete.

3 / 3

Workflow Clarity

The quick start shows a clear sequence (connect → handle events → send media → close), and gotcha #7 explicitly warns about ordering. However, there's no explicit validation/error-handling checkpoint — e.g., what to do if connect fails, or how to verify the connection is healthy before sending media. The workflow is implicit in the code rather than explicitly sequenced with checkpoints.

2 / 3

Progressive Disclosure

Content is well-structured with a clear overview, quick start, key parameters, and layered API references pointing to in-repo source, AsyncAPI spec, and external docs. References are one level deep and clearly signaled. The skill appropriately keeps the overview concise while pointing to example files and central skills for deeper exploration.

3 / 3

Total

11

/

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 hits all the marks. It provides specific API-level details, explicitly states when to use it (and when NOT to use it by pointing to sibling skills), and includes a comprehensive list of natural trigger terms. The differentiation from related skills is particularly well done.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and API elements: 'client.listen().v2().v2WebSocket()', 'V2ConnectOptions', 'onTurnInfo', 'turn-aware close handling', and references the specific endpoint '/v2/listen'. Very concrete and actionable.

3 / 3

Completeness

Clearly answers both 'what' (writing/reviewing Java code for Deepgram Conversational STT v2/Flux, covering specific API classes and patterns) and 'when' (explicit 'Use when' clause plus differentiation from related skills and explicit trigger list).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms explicitly listed: 'flux', 'conversational stt', 'listen v2', 'turn detection', 'end of turn', 'eot'. Also includes natural terms like 'Java code', 'Deepgram', and 'v2/listen' throughout the description.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — explicitly differentiates itself from two related skills ('deepgram-java-speech-to-text' for v1 and 'deepgram-java-voice-agent' for interactive assistants), carving out a clear niche for v2/Flux conversational STT specifically.

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-java-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.