CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-java-speech-to-text

Use when writing or reviewing Java code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live transcription. Covers `client.listen().v1().media().transcribeUrl` / `transcribeFile` (REST) and `client.listen().v1().v1WebSocket()` (WebSocket). Use `deepgram-java-audio-intelligence` for analytics overlays, `deepgram-java-conversational-stt` for Flux `/v2/listen`, and `deepgram-java-voice-agent` for full-duplex assistants. Triggers include "transcribe", "speech to text", "STT", "listen v1", "nova-3", "live transcription", and "websocket transcription".

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 strong, actionable skill with excellent executable code examples covering REST and WebSocket use cases, good progressive disclosure with clear routing to related skills, and a useful gotchas section. The main weaknesses are moderate verbosity in the code examples (especially the visitor pattern) and missing validation/error-recovery steps in the WebSocket workflow.

Suggestions

Tighten the REST URL example by extracting the transcript access into a helper or simplifying the guard logic — the current visitor implementation is verbose with duplicated `.getAlternatives().orElse(...)` calls.

Add explicit error handling and validation steps to the WebSocket workflow (e.g., check connect result, handle onError before sending audio, verify final results received before closing).

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some unnecessary verbosity — the REST URL example has a lengthy visitor pattern with redundant guard code and comments, and some explanatory sentences (e.g., 'Default API-key auth sends...') could be tighter. The 'Key parameters / API surface' section is a useful reference but borders on exhaustive listing. Overall decent but could be trimmed.

2 / 3

Actionability

All code examples are fully executable with correct imports, concrete builder patterns, and real method calls. The REST URL, REST file, WebSocket, and async examples are all copy-paste ready with specific class names and methods. The gotchas section provides highly specific, actionable warnings.

3 / 3

Workflow Clarity

The skill presents clear individual steps for each use case (REST URL, REST file, WebSocket) but lacks explicit validation checkpoints. For WebSocket streaming — a multi-step process involving connect, send, and close — there's no error recovery guidance or validation loop. The gotchas partially compensate but aren't integrated into the workflow steps themselves.

2 / 3

Progressive Disclosure

Content is well-structured with clear sections progressing from authentication to quick starts to advanced reference. External references are clearly signaled and one level deep (API docs, OpenAPI/AsyncAPI specs, example files, related skills). The 'When to use this product' section effectively routes to sibling skills.

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 (Deepgram STT v1 in Java), lists concrete API methods and actions, provides explicit trigger terms, and proactively distinguishes itself from related sibling skills. It is concise yet comprehensive, uses third-person voice appropriately, and would enable Claude to confidently select or reject this skill from a large pool.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: writing/reviewing Java code, calling Deepgram STT v1 `/v1/listen`, prerecorded and live transcription, specific API methods (`transcribeUrl`, `transcribeFile`, `v1WebSocket`), and distinguishes REST vs WebSocket approaches.

3 / 3

Completeness

Clearly answers both 'what' (Java code for Deepgram STT v1 prerecorded/live transcription via REST and WebSocket) and 'when' (explicit 'Use when' clause at the start plus explicit trigger terms). Also clarifies when NOT to use it by pointing to sibling skills.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms explicitly listed: 'transcribe', 'speech to text', 'STT', 'listen v1', 'nova-3', 'live transcription', 'websocket transcription'. These are terms users would naturally use when needing this skill.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — scoped to a specific API version (`/v1/listen`), specific language (Java), and specific vendor (Deepgram). Explicitly delineates boundaries by naming three sibling skills for analytics, v2/Flux, and voice agents, minimizing overlap risk.

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.