CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-js-audio-intelligence

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, and entity detection. Same endpoint as plain STT, different params. Covers REST via `client.listen.v1.media.transcribeUrl` / `transcribeFile` and the WebSocket-supported subset on `client.listen.v1.createConnection()` / `connect()`. Use `deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for analytics on already-transcribed text. Triggers include "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", and "detect language audio".

71

Quality

86%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

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, well-organized skill that provides actionable code examples and clear feature availability guidance for Deepgram audio intelligence. Its main strengths are executable code snippets, a useful REST vs WSS feature matrix, and practical gotchas. Weaknesses include missing error handling/validation workflows and some token overhead from promotional and routing content.

Suggestions

Add a brief section showing how to validate that intelligence features returned expected results (e.g., checking for `results.summary`, `results.topics` in the response object) to improve workflow clarity.

Trim the 'Central product skills' block and condense the 'When to use this product' routing section to a compact bullet list to improve conciseness.

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary sections like the 'Central product skills' promo block and the 'When to use this product' section which, while useful for routing, adds tokens for context Claude could infer. The feature availability table and gotchas are well-justified. Some light verbosity in descriptions.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code for both REST and WSS paths, with concrete parameter names, specific method calls (`transcribeUrl`, `createConnection`), and real example URLs. The parameter listing and gotchas give precise, actionable guidance.

3 / 3

Workflow Clarity

The skill presents clear quick-start examples but lacks explicit validation steps or feedback loops. There's no guidance on checking response structure, handling errors, or verifying that intelligence features actually returned results. For a skill involving multiple overlapping API features, a workflow showing how to verify feature output would strengthen this.

2 / 3

Progressive Disclosure

Well-structured with clear sections progressing from overview to quick starts to parameters to references. The API reference section provides well-signaled, one-level-deep links to in-repo references, OpenAPI specs, and product docs. Example files are listed for further exploration. No bundle files exist but the skill references external docs appropriately.

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 is highly specific, well-scoped, and clearly distinguishable from related skills. It provides concrete API methods, explicit trigger terms, and clear disambiguation guidance for when to use adjacent skills instead. The only minor note is its density, but the information is all relevant and actionable for skill selection.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and features: summarize, topics, intents, sentiment, diarize, redact, detect_language, entity detection. Also specifies exact API methods like `client.listen.v1.media.transcribeUrl`, `transcribeFile`, and `createConnection()`/`connect()`.

3 / 3

Completeness

Clearly answers both 'what' (audio analytics overlays on Deepgram's /v1/listen endpoint covering summarize, topics, intents, sentiment, etc.) and 'when' (explicit 'Use when writing or reviewing JavaScript/TypeScript... that calls Deepgram audio analytics overlays' plus explicit trigger terms). Also provides disambiguation guidance for related skills.

3 / 3

Trigger Term Quality

Includes a rich set of natural trigger terms users would say: 'audio intelligence', 'summarize audio', 'diarize', 'sentiment from audio', 'redact PII', 'detect language audio'. Also includes technical terms like specific API method names and feature names that developers would reference.

3 / 3

Distinctiveness Conflict Risk

Explicitly distinguishes itself from related skills (`deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for text analytics), creating clear boundaries. The focus on audio analytics overlays on `/v1/listen` is a well-defined niche 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-js-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.