CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-go-conversational-stt

Use when planning or reviewing Go SDK work for Deepgram conversational STT / Flux v2. This repo does not currently ship a first-class v2 listen client, so route supported v1 transcription to deepgram-go-speech-to-text and document raw WebSocket fallback honestly when v2 is requested.

78

1.15x
Quality

66%

Does it follow best practices?

Impact

99%

1.15x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/deepgram-go-conversational-stt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

This skill excels at honestly communicating the current state of v2 support (absent) and directing users to appropriate alternatives, with good progressive disclosure and layered references. However, it falls short on actionability — the primary use case (raw WebSocket fallback for v2) lacks any executable code example or step-by-step workflow, making it more of a status document than an actionable skill. Some content is repeated across sections, slightly hurting conciseness.

Suggestions

Add a minimal executable Go code example showing how to establish a raw WebSocket connection to the Deepgram v2 endpoint using the shared plumbing in pkg/client/common/v1/websocket.go, even if marked as unsupported/experimental.

Provide a step-by-step workflow for the raw v2 integration path: configure credentials → set up WS connection with path overrides → send audio → handle responses → validate output, with explicit checkpoints.

Consolidate the repeated 'v2 is not implemented' messaging — state it once prominently at the top and remove redundant mentions in Key parameters, Gotchas, and Example files sections.

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but includes some redundancy — the 'Key parameters' section largely restates what's already in 'Quick start', and the 'Central product skills' section at the bottom adds promotional content that isn't strictly necessary. The repeated emphasis on 'not implemented' could be consolidated.

2 / 3

Actionability

The skill is honest about what doesn't exist and points to specific file paths for raw integration, but it provides no executable code or concrete WebSocket example for the v2 fallback path. The authentication section shows an env var export but nothing that uses it. For a skill whose main value is 'here's how to do it raw,' the absence of even a minimal working WebSocket snippet is a gap.

2 / 3

Workflow Clarity

The skill provides a clear decision tree (use v1 skill vs. raw v2 prototype) and lists relevant files, but there's no step-by-step workflow for the raw WebSocket integration path — no sequence of actions, no validation checkpoints, no error handling guidance. For a manual integration task this is a notable gap.

2 / 3

Progressive Disclosure

The content is well-structured with clear sections, appropriately references other skills (deepgram-go-speech-to-text, deepgram-go-voice-agent), provides a layered API reference section with in-repo files, external docs, and OpenAPI/AsyncAPI links, and points to central product skills. References are one level deep and clearly signaled.

3 / 3

Total

9

/

12

Passed

Description

75%

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 well-structured with an explicit 'Use when' clause and a clearly defined niche around Deepgram Go SDK v2 migration. Its main weakness is that the concrete actions described are more about workaround guidance (routing to v1, documenting fallbacks) than listing specific capabilities, and trigger term coverage could be broader to capture more natural user queries.

Suggestions

Add more natural trigger term variations such as 'speech-to-text', 'streaming audio', 'real-time transcription', or 'deepgram-go-sdk' to improve discoverability.

List more concrete actions the skill performs (e.g., 'generates WebSocket connection code', 'configures transcription options', 'reviews SDK integration patterns') to strengthen specificity.

DimensionReasoningScore

Specificity

The description names a specific domain (Go SDK for Deepgram conversational STT / Flux v2) and mentions some actions like 'route supported v1 transcription' and 'document raw WebSocket fallback,' but the actions are more about routing/documenting limitations than listing concrete capabilities the skill performs.

2 / 3

Completeness

The description explicitly answers both 'what' (route v1 transcription to deepgram-go-speech-to-text, document raw WebSocket fallback for v2) and 'when' ('Use when planning or reviewing Go SDK work for Deepgram conversational STT / Flux v2'), with a clear 'Use when...' clause at the start.

3 / 3

Trigger Term Quality

Includes relevant terms like 'Go SDK', 'Deepgram', 'STT', 'Flux v2', 'WebSocket', and 'transcription' which are natural for developers in this domain. However, it misses common variations like 'speech-to-text', 'streaming audio', 'real-time transcription', or 'deepgram-go-sdk' that users might naturally say.

2 / 3

Distinctiveness Conflict Risk

This is highly specific to a particular SDK (Deepgram Go SDK) and a particular version transition (v1 to v2 / Flux v2), making it very unlikely to conflict with other skills. The niche is clearly defined.

3 / 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.

Validation11 / 11 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.