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".

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable reference skill with executable REST and WSS examples and a clear feature-availability matrix. It could tighten the product-doc URL list and add response-validation guidance for the API calls.

Suggestions

Consolidate the eight product-doc URLs into a single "Product docs" pointer or move them to reference.md to reduce inlined bulk and improve conciseness and progressive disclosure.

Add a brief response-validation note (e.g. check `data.results` / handle error codes) after the REST and WSS quick-start code to raise workflow clarity.

Reconcile the `summarize` parameter: the quick-start code uses `summarize: true` while gotcha #1 says it is versioned ("v2") not boolean — show the correct form in the example.

DimensionReasoningScore

Conciseness

Lean and efficient: a feature-availability table, two compact quick-start code blocks, a tight parameter list, and gotchas with no padding or explanation of concepts Claude already knows. The eight inlined product-doc URLs and some redundancy between the quick-start params and the parameter list keep it just short of a 5.

4 / 5

Actionability

Copy-paste-ready REST and WSS code drawn from real example files (`examples/22-transcription-advanced-options.ts`, `examples/07-transcription-live-websocket.ts`), with concrete parameters and a gotchas section covering the common cases. The minor `summarize: true` vs. "versioned, not boolean" inconsistency does not undermine overall executability.

5 / 5

Workflow Clarity

Two clearly sequenced paths (REST primary, WSS subset) with unambiguous single actions and a feature-availability table guiding the choice, but no error-handling or response-validation checkpoints are shown for the API calls.

4 / 5

Progressive Disclosure

Well-organized sections with a layered API reference (in-repo `reference.md` → OpenAPI → AsyncAPI → Context7 → product docs) and one-level-deep pointers to example files and source paths. The bulk of eight product-doc URLs is inlined rather than consolidated, a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what the skill does and when to use it, distinguishes it from sibling skills, and provides natural trigger phrases. Trigger-term coverage is good but could add a few more synonyms.

DimensionReasoningScore

Specificity

Names the domain (JS/TS in this repo calling Deepgram overlays on `/v1/listen`) and lists multiple concrete actions and features — summarize, topics, intents, sentiment, diarize, redact, detect_language, entity detection — plus specific SDK methods (`transcribeUrl`, `transcribeFile`, `createConnection`, `connect()`), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (analytics overlays on `/v1/listen`, REST and WSS surfaces, specific methods) and when ("Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays"), with concrete trigger phrases listed.

5 / 5

Trigger Term Quality

Includes natural trigger phrases users would say — "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", "detect language audio" — but a few common variations (e.g. "transcribe and analyze", "audio sentiment analysis") are absent, so it is not quite comprehensive.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (audio analytics overlays on `/v1/listen`) and explicitly redirects plain transcription to `deepgram-js-speech-to-text` and text analytics to `deepgram-js-text-intelligence`, minimizing conflict risk.

5 / 5

Total

19

/

20

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.

Validation16 / 16 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.