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".
71
86%
Does it follow best practices?
Impact
—
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 details, includes natural trigger terms, and explicitly distinguishes itself from a related audio-focused skill. It follows best practices by using a 'Use when' clause, listing trigger terms, and providing boundary guidance. The description is concise yet comprehensive.
| 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. | 3 / 3 |
Completeness | Clearly answers both 'what' (writing/reviewing Java code that calls Deepgram Text Intelligence Read API with specific methods) and 'when' (explicit 'Use when' clause at the start, plus a 'Triggers include' list). 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'. Also includes technical terms like the endpoint path `/v1/read` and class names that developers would reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: scoped to a specific repo, a specific API (Deepgram Text Intelligence /v1/read), a specific language (Java), and explicitly differentiates from the audio intelligence skill. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 solid, actionable skill with complete executable Java code examples covering the main use cases. Its main weaknesses are minor verbosity in introductory sections and the absence of error handling or validation guidance for API calls. The progressive structure and concrete examples make it highly usable.
Suggestions
Add a brief error handling example (try/catch around the API call with guidance on common failure modes like invalid API key or rate limiting).
Trim the 'When to use this product' and 'Central product skills' sections — Claude can infer when text vs audio applies, and the promotional install block doesn't aid task execution.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., 'Analyze text you already have — transcripts, chats, documents, or other plain text' and the 'When to use this product' section explain things Claude can infer). The gotchas and API surface sections are well-targeted, but the 'Central product skills' section at the bottom adds promotional content that doesn't aid task execution. | 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 | The skill presents clear code examples but lacks explicit validation checkpoints — there's no error handling, no guidance on what to do if the API call fails, and no verification step for the response. For an API-calling skill, missing error handling/validation caps this at 2. | 2 / 3 |
Progressive Disclosure | Well-structured with a quick start, then progressive sections for custom topics, async, key parameters, and layered API references. References to example files and external docs are one level deep and clearly signaled. No bundle files are needed for this self-contained skill. | 3 / 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
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.