CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-go-audio-intelligence

Use when writing or reviewing Go code in this repo that applies summaries, topics, intents, sentiment, language detection, diarization, redaction, or entity extraction to audio inputs through Listen v1 REST. Route plain transcription to deepgram-go-speech-to-text and plain-text Read requests to deepgram-go-text-intelligence.

75

Quality

92%

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

92%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.

An efficient, highly actionable reference skill with a copy-paste runnable example and well-organized one-level-deep pointers. The only nit is a triplicated REST-vs-WS caveat that could be consolidated.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence, but the REST-first / WS-surface point is restated three times (Key parameters note, Gotcha #1, Gotcha #2), a minor redundancy that could be trimmed, keeping it below the every-token-earns-its-place anchor at 5.

4 / 5

Actionability

The Quick start is fully executable, copy-paste Go with real package imports, concrete options ('nova-3', Summarize 'v2'), and real response handling, covering the common pre-recorded analytics case.

5 / 5

Workflow Clarity

A simple read-only skill whose single action (construct client, layer analytics options on PreRecordedTranscriptionOptions, call FromURL, read response) is unambiguous and shown end-to-end; no validation checkpoint is needed for a non-destructive REST read.

5 / 5

Progressive Disclosure

Clear overview sections with well-signaled, one-level-deep references (layered API reference, example file paths, central product skills) and no nested indirection, giving easy navigation.

5 / 5

Total

19

/

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, concrete description with an explicit trigger clause, comprehensive capability list, and excellent routing-based distinctiveness. The only gap is a lack of synonyms and file-extension trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete analytics actions comprehensively ('summaries, topics, intents, sentiment, language detection, diarization, redaction, or entity extraction') applied via a specific REST surface, matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

Explicitly answers both what (analytics overlays via Listen v1 REST) and when (an explicit 'Use when...' clause with concrete triggers), plus routing guidance, matching the clear-what-and-when anchor.

5 / 5

Trigger Term Quality

Good keyword coverage with the natural feature names users would say, but missing common synonyms (e.g. 'sentiment analysis', 'speaker diarization') and file extensions (.wav, .mp3), so it sits below the comprehensive-synonyms anchor at 5.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (audio intelligence overlays, not plain transcription) and explicitly routes plain transcription and text requests to named sibling skills, giving minimal 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-go-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.