deepgram-java-text-intelligence
Use when writing or reviewing Java code in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for text analysis. Covers `client.read().v1().text().analyze(...)` with `ReadV1Request` or `TextAnalyzeRequest`. Use `deepgram-java-audio-intelligence` when the source is audio instead of text. Triggers include "read api", "text intelligence", "analyze text", "sentiment", "topics", "intents", and "summarize text".
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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, provides specific API methods and request types, explicitly states when to use it and when not to (directing to the audio variant), and includes a comprehensive list of natural trigger terms. It is concise yet thorough, and its explicit boundary with the audio intelligence skill reduces conflict risk significantly.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: writing/reviewing Java code, calling Deepgram Text Intelligence/Read endpoint, using specific API methods like `client.read().v1().text().analyze(...)` with named request types `ReadV1Request` and `TextAnalyzeRequest`. Also distinguishes from the audio variant skill. | 3 / 3 |
Completeness | Clearly answers both 'what' (writing/reviewing Java code that calls Deepgram Text Intelligence /v1/read for text analysis with specific API methods) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms listed). Also clarifies when NOT to use it (use the audio skill instead for audio sources). | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms users would say: 'read api', 'text intelligence', 'analyze text', 'sentiment', 'topics', 'intents', 'summarize text'. These cover common user phrasings well and include both API-specific and task-oriented terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: scoped to a specific API endpoint (/v1/read), specific language (Java), specific SDK methods, and explicitly differentiates from the audio intelligence skill. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 complete executable Java code examples covering the primary use cases for Deepgram Text Intelligence. Its main strengths are the concrete, copy-paste ready code and clear gotchas section. Weaknesses include slight verbosity in framing sections and lack of bundle files to support the referenced example paths.
Suggestions
Trim the 'When to use this product' and 'Central product skills' sections to reduce token overhead — Claude can infer when text vs audio analysis applies from context.
Consider providing the referenced example files (examples/read/AnalyzeText.java, etc.) as bundle files, or remove the references if they aren't available in the bundle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like explaining when to use vs not use the product, and the 'Central product skills' section at the bottom adds promotional content. The gotchas section is useful but slightly verbose. The API reference layered section could be tighter. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready Java code for authentication, basic analysis, custom topics/intents, and async usage. Import statements are included, builder patterns are complete, and response access patterns are shown explicitly. | 3 / 3 |
Workflow Clarity | For a single-task API call skill, the workflow is clear and unambiguous: authenticate → build request → call analyze → access results. The quick start demonstrates the complete flow linearly. No destructive or batch operations require validation checkpoints. | 3 / 3 |
Progressive Disclosure | References to example files and external docs are present and well-signaled, but there are no bundle files to support the references (e.g., examples/read/AnalyzeText.java). The content is somewhat long for a single SKILL.md with no supporting bundle files, and the API reference section lists multiple external sources without clear prioritization of when to use each. | 2 / 3 |
Total | 10 / 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
de2dd4b
- 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.