CtrlK
BlogDocsLog inGet started
Tessl Logo

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

Quality

86%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

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 solid, actionable skill with excellent executable code examples and good progressive disclosure structure. Its main weaknesses are minor verbosity in introductory sections and the absence of error handling/validation guidance, which would be important for API-calling workflows. The gotchas section adds genuine value by highlighting SDK-specific pitfalls.

Suggestions

Add a brief error handling example or validation checkpoint (e.g., checking response status, handling API key errors) to improve workflow clarity.

Trim the 'When to use this product' section and 'Central product skills' block — Claude can infer when text vs. audio analysis applies, and the promotional content doesn't aid task execution.

DimensionReasoningScore

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/error-handling steps. There's no guidance on what to do if the API call fails, no mention of checking response status, and no feedback loop for common errors like invalid API keys or malformed requests.

2 / 3

Progressive Disclosure

Content is well-structured with a clear quick start, then progressive sections for advanced usage (custom topics/intents, async). References to in-repo examples, OpenAPI specs, and external docs are clearly signaled and one level deep. The layered API reference section is particularly well-organized.

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 Text Intelligence API in Java), provides specific API methods and request types, includes a comprehensive list of natural trigger terms, and explicitly disambiguates from a related skill. It uses third person voice appropriately and is concise yet thorough.

DimensionReasoningScore

Specificity

Lists specific concrete actions: calling Deepgram Text Intelligence / Read endpoint, using specific API methods (`client.read().v1().text().analyze(...)`) with specific request types (`ReadV1Request`, `TextAnalyzeRequest`). Also distinguishes from audio intelligence skill.

3 / 3

Completeness

Clearly answers both 'what' (calling Deepgram Text Intelligence / Read API for text analysis with specific methods) and 'when' (explicit 'Use when' clause for writing/reviewing Java code calling this API, plus explicit trigger terms and a disambiguation note for audio vs text).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms: 'read api', 'text intelligence', 'analyze text', 'sentiment', 'topics', 'intents', 'summarize text'. These are terms users would naturally use when working with text analysis features.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive: scoped to a specific API (Deepgram `/v1/read`), a specific language (Java), and explicitly disambiguates from the audio intelligence skill (`deepgram-java-audio-intelligence`). Very unlikely to conflict with other skills.

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.