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".
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 is highly specific, well-scoped, and clearly distinguishable from related skills. It lists concrete capabilities, provides explicit trigger terms, clearly states when to use it versus sibling skills, and uses appropriate third-person voice throughout. The inclusion of exact API method names and boundary guidance makes it particularly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
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 WebSocket methods. | 3 / 3 |
Completeness | Clearly answers both 'what' (audio analytics overlays on /v1/listen including summarize, topics, intents, sentiment, etc.) and 'when' (explicit 'Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays'). Also provides boundary guidance on when to use sibling skills instead. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'audio intelligence', 'summarize audio', 'diarize', 'sentiment from audio', 'redact PII', 'detect language audio'. Also includes technical terms like endpoint paths and method names that developers would reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear boundaries: explicitly differentiates from `deepgram-js-speech-to-text` (plain transcription) and `deepgram-js-text-intelligence` (text analytics). The niche of audio analytics overlays on the listen endpoint is well-defined and unlikely to conflict. | 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 that provides executable code examples, a clear REST vs WSS feature matrix, and valuable gotchas specific to the Deepgram JS SDK's audio intelligence features. Its main weaknesses are minor verbosity (the central product skills promo, exhaustive doc links) and the inability to verify referenced bundle files. The content effectively teaches Claude what it wouldn't already know—SDK-specific parameter names, feature availability constraints, and version-specific quirks.
Suggestions
Trim or remove the 'Central product skills' section at the bottom, which reads as promotional rather than instructional.
Consider consolidating the API reference links into a single 'See [REFERENCES.md](REFERENCES.md)' pointer to reduce inline token usage.
| Dimension | Reasoning | Score |
|---|---|---|
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 explaining things Claude could infer. The feature availability table and gotchas are well-justified. Some light verbosity in the API reference section listing many external links. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code for both REST and WSS paths with real parameter examples. The authentication block, quick start examples, and parameter listings give Claude everything needed to write working code. The gotchas section adds critical implementation-specific details (e.g., summarize is 'v2' not boolean, keyterm vs keywords for Nova-3). | 3 / 3 |
Workflow Clarity | For this skill's scope (calling an API with parameters), the workflow is straightforward and clearly presented: authenticate → choose REST or WSS → pass appropriate flags. The REST vs WSS feature table serves as an effective decision checkpoint. No destructive or batch operations require validation loops, so the single-task clarity is sufficient. | 3 / 3 |
Progressive Disclosure | References to external docs, OpenAPI/AsyncAPI specs, and in-repo files are well-signaled and one level deep. However, with no bundle files provided, the references to 'reference.md' and source files in 'src/' cannot be verified. The skill inlines a reasonable amount of content but the API reference section with 8+ external doc links could be more selectively curated rather than exhaustively listed. | 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-js-sdk
- Commit
c567b98
- 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.