CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

68

Quality

86%

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 strong single-file reference skill: fully executable quick start, exact parameter and type names, and a clearly layered API reference. Main improvements would be de-duplicating the REST-only note and moving the long product-docs URL list into a separate reference file.

Suggestions

Collapse the REST-only limitation into one statement — it currently appears in the Key parameters bullet and twice in Gotchas 1 and 2.

Trim or fold the "When to use this product" section, which repeats the frontmatter description's routing information verbatim in structure.

Move the 8-URL product-docs list into a references file and keep only the top links inline to reduce SKILL.md bulk.

DimensionReasoningScore

Conciseness

The body is lean with a complete, uncommented executable quick start, but the REST-only limitation is stated three times (Key parameters bullet, Gotchas 1 and 2) and the "When to use this product" section restates the frontmatter description.

4 / 5

Actionability

Quick start is copy-paste ready with imports, client construction, options, and response handling; Key parameters names exact struct fields with the types-file path; Gotchas give the concrete starting call and example file paths cover the remaining features.

5 / 5

Workflow Clarity

The single path (auth → NewRESTWithDefaults → FromURL with analytics flags → read typed response) is clear and unambiguous, but there is no error-recovery guidance and payload handling is shown for only one feature.

4 / 5

Progressive Disclosure

Well-organized sections with a numbered, one-level-deep layered reference list (in-repo files → OpenAPI → AsyncAPI → Context7 → product docs), though the 8-URL product-docs list is bulk reference material inlined rather than split into a references file.

4 / 5

Total

17

/

20

Passed

Description

83%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 description: specific capability enumeration, an explicit use-when trigger, and explicit routing to sibling skills. The only weaknesses are a few missing natural synonyms and a "what" that is implied by the trigger clause rather than stated directly.

DimensionReasoningScore

Specificity

Enumerates eight concrete capabilities ("summaries, topics, intents, sentiment, language detection, diarization, redaction, or entity extraction") plus the exact API surface ("Listen v1 REST", Go SDK), matching the comprehensive-coverage anchor.

5 / 5

Completeness

The "when" is explicit and concrete ("Use when writing or reviewing Go code in this repo that applies..."), and the "what" is conveyed through the feature enumeration, but it is framed as a trigger condition rather than a direct statement of what the skill provides.

4 / 5

Trigger Term Quality

Natural terms like "summaries", "sentiment", "diarization", "redaction", "Go", and "writing or reviewing" are present, but common user variants such as "audio intelligence", "sentiment analysis", or "transcription analytics" are missing.

4 / 5

Distinctiveness Conflict Risk

"Route plain transcription to deepgram-go-speech-to-text and plain-text Read requests to deepgram-go-text-intelligence" explicitly disambiguates the two adjacent skills, giving a clear niche with minimal conflict risk.

5 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

deepgram/deepgram-go-sdk

Path

.agents/skills/deepgram-go-audio-intelligence/SKILL.md

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.