CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-go-speech-to-text

Use when writing or reviewing Go code in this repo that transcribes prerecorded audio with Listen v1 REST or streams live audio with Listen v1 WebSockets. Route text generation to deepgram-go-text-to-speech, text analysis to deepgram-go-text-intelligence, audio analytics overlays to deepgram-go-audio-intelligence, and Flux or other v2 conversational work to deepgram-go-conversational-stt.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is well-structured, actionable, and respectful of Claude's competence, with runnable REST code and a clear WebSocket lifecycle. The main gaps are the WebSocket example being a skeleton and the absence of bundle files to offload the inline API reference.

Suggestions

Provide a complete, runnable WebSocket streaming example (e.g., reading PCM from a file) instead of leaving the audio-write loop as pseudo-code comments.

Move the layered API reference and Key parameters detail into a references/ file (e.g., REFERENCE.md) and link to it from SKILL.md to improve progressive disclosure.

Add an explicit validation checkpoint for the WebSocket flow (e.g., confirm Connect() succeeded and verify an Open/Metadata event before streaming) to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

Sections are dense and assume Go competence (e.g., the Key parameters and Gotchas blocks), with the WebSocket pseudo-code comments explicitly justified; minor padding in the WS narrative comments keeps it just below lean.

4 / 5

Actionability

The REST example is fully copy-paste runnable with real imports and calls, but the WebSocket example is a skeleton whose core streaming loop is left as pseudo-code, a minor gap versus the fully-executable 5 anchor.

4 / 5

Workflow Clarity

The lifecycle is sequenced concretely (Connect returns bool, Start, stream, KeepAlive, Finalize, defer Stop) and the example checks Connect's return, but there are no explicit validate-and-retry checkpoints, sitting between 3 and 5.

4 / 5

Progressive Disclosure

No bundle files exist, and the body inlines a fair amount of API-reference material (Key parameters, layered API reference list) that could live in separate files; still, sections are well-organized and repo/external references are clearly signaled one level deep.

4 / 5

Total

16

/

20

Passed

Description

87%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.

The description is strong: it pairs an explicit "Use when" trigger with concrete capabilities and proactive routing away from sibling skills. Minor gaps are the absence of speech-to-text/STT synonyms and a slightly narrow action enumeration.

DimensionReasoningScore

Specificity

"transcribes prerecorded audio with Listen v1 REST" and "streams live audio with Listen v1 WebSockets" name several concrete actions, but the action set is essentially two (transcribe, stream) rather than a comprehensive enumeration, so it sits below the 5 anchor.

4 / 5

Completeness

It explicitly answers both what (transcribe prerecorded via REST, stream live via WS) and when ("Use when writing or reviewing Go code in this repo that transcribes..."), with concrete trigger phrases matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural phrases like "writing or reviewing Go code", "transcribes prerecorded audio", and "streams live audio" are present, but common synonyms such as "speech-to-text", "STT", and "transcription" are missing, leaving it just below comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

It carves a clear STT-v1-in-Go niche and actively routes TTS, text analysis, audio analytics, and Flux/v2 work to named sibling skills, minimizing conflict risk as the 5 anchor describes.

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.

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.