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".
88
82%
Does it follow best practices?
Impact
100%
1.13xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
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 (intelligence overlays on audio transcription), explicitly differentiates from two related skills, and provides natural trigger terms. It answers both what and when comprehensively, and the specificity of endpoint names, class references, and feature enumeration makes it highly actionable for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: diarization, entity detection, sentiment, summarize, topics, intents, language detection, and redaction. Also names specific classes like `ListenV1RequestUrl` and `MediaTranscribeRequestOctetStream`, and distinguishes from related skills. | 3 / 3 |
Completeness | Clearly answers both 'what' (enables Deepgram intelligence overlays on /v1/listen for diarization, entity detection, sentiment, etc.) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms and differentiation from related skills). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'audio intelligence', 'diarize', 'summarize audio', 'sentiment from audio', 'topic detection', 'redact'. Also includes domain terms like 'diarization', 'entity detection', 'language detection' that users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from `deepgram-java-speech-to-text` (plain transcripts) and `deepgram-java-text-intelligence` (text analysis), creating a clear niche for audio intelligence overlays on the /v1/listen endpoint. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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, actionable skill with executable Java code examples and clear guidance on when to use this skill vs. alternatives. Its main weaknesses are some content duplication (analysis fields listed twice in nearly identical form), missing error handling/validation guidance, and a somewhat long body that could benefit from splitting reference material into a separate file. The gotchas section is genuinely valuable and adds unique, non-obvious information.
Suggestions
Remove the duplicate field listing — the 'Key parameters / API surface' section largely repeats 'What else the REST request surface supports'. Consolidate into one authoritative list.
Add a brief error handling example or validation step (e.g., checking response status, verifying that requested intelligence fields are present in the response) to improve workflow clarity.
Move the extensive product docs links and API reference layering into a separate REFERENCE.md file, keeping only a one-line pointer in the main skill body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples and structured sections, but includes some unnecessary verbosity — the extensive list of product doc links, the repeated enumeration of fields in both the 'What else the REST request surface supports' section and the 'Key parameters / API surface' section (near-duplicate content), and some explanatory text that could be tightened. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready Java code for both REST and WebSocket paths, with specific import statements, builder patterns, and concrete class names. The authentication, quick start examples, and field listings give Claude everything needed to write working code. | 3 / 3 |
Workflow Clarity | The skill clearly delineates when to use this skill vs. others and provides good quick-start patterns, but lacks explicit validation/verification steps — there's no guidance on checking response status, handling errors, or verifying that intelligence fields actually returned results. For an API integration skill, some error handling guidance would strengthen the workflow. | 2 / 3 |
Progressive Disclosure | The skill has good structure with clear sections and references to external docs and repo examples, but with no bundle files provided, the references to example files and source paths are unverifiable. The layered API reference section is well-organized, but the content itself is somewhat monolithic — the duplicate field listings and extensive doc links could be split into a reference file. | 2 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/deepgram-java-sdk
- Commit
6d7d7d5
- 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.