CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-java-audio-intelligence

Use when writing or reviewing Java code in this repo that enables Deepgram intelligence overlays on `/v1/listen` audio transcription - diarization, entity detection, sentiment, summarize, topics, intents, language detection, and redaction. Same endpoint as plain STT, but with extra request fields on `ListenV1RequestUrl` or `MediaTranscribeRequestOctetStream`. Use `deepgram-java-speech-to-text` for plain transcripts and `deepgram-java-text-intelligence` for analysis on existing text. Triggers include "audio intelligence", "diarize", "summarize audio", "sentiment from audio", "topic detection", and "redact".

100

1.13x
Quality

Does it follow best practices?

Impact

100%

1.13x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A well-crafted code skill: executable examples for both REST and WebSocket surfaces, verified field lists, pointed gotchas, and cleanly layered references to deeper sources. Concise and actionable with no concept over-explanation.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence — runnable Java snippets, compact field lists, and pointed gotchas with no padding or explanation of basic concepts; the only mild redundancy is the analysis-field list appearing in two sections, but every token still earns its place.

3 / 3

Actionability

Provides complete, copy-paste-ready Java for both REST ('ListenV1RequestUrl.builder()...transcribeUrl(request)') and WebSocket ('V1WebSocketClient...connect(V1ConnectOptions.builder()...)') paths with real imports and verified field names, fully executable rather than pseudocode.

3 / 3

Workflow Clarity

This is a single-action reference skill (enable overlays on the Listen V1 request surface) whose action is unambiguous via the Quick start sections; no destructive/batch multi-step process exists that would require validation checkpoints, so the simple-skill allowance applies.

3 / 3

Progressive Disclosure

No bundle files exist in references/scripts/assets, and the body is well-organized into clear sections with a layered 'API reference' pointing to in-repo source, OpenAPI/AsyncAPI, Context7, and product docs as one-level-deeper sources, plus an explicit note that 'reference.md is absent here'.

3 / 3

Total

12

/

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.

A high-quality description: concrete capability list, natural trigger phrases, explicit use-when guidance, and clear disambiguation from sibling skills. Voice is appropriately imperative/trigger-based with no first/second-person slips.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities verbatim — 'diarization, entity detection, sentiment, summarize, topics, intents, language detection, and redaction' — and names the exact request surfaces ('ListenV1RequestUrl or MediaTranscribeRequestOctetStream'), matching the multiple-specific-actions anchor.

3 / 3

Completeness

Opens with 'Use when writing or reviewing Java code in this repo that enables Deepgram intelligence overlays...' answering both what it does and when to use it with explicit triggers, hitting the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Explicit 'Triggers include "audio intelligence", "diarize", "summarize audio", "sentiment from audio", "topic detection", and "redact"' are natural phrases a user would say, giving good coverage; not merely technical jargon.

3 / 3

Distinctiveness Conflict Risk

Explicitly routes adjacent needs away — 'Use deepgram-java-speech-to-text for plain transcripts and deepgram-java-text-intelligence for analysis on existing text' — carving a clear niche unlikely to trigger the wrong 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.

Validation16 / 16 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.