CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-go-voice-agent

Use when writing or reviewing Go code in this repo that runs a Deepgram Voice Agent session over WebSockets, including runtime settings, prompt updates, speak updates, injected messages, and event handling. Route standalone STT/TTS work to deepgram-go-speech-to-text or deepgram-go-text-to-speech.

66

Quality

78%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/deepgram-go-voice-agent/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.

The skill provides a solid structural overview with good progressive disclosure and clear routing to related skills. However, it falls short on actionability for the core use cases it claims to cover — audio streaming, event handling, runtime updates, and function-call responses are listed but not demonstrated with executable code. The quick start establishes a connection but leaves the most important operations as comments.

Suggestions

Add executable code examples for at least one runtime operation (e.g., sending UpdatePrompt, handling a FunctionCallRequest, or streaming audio frames) beyond just establishing the connection.

Show a concrete event-handling loop using the channel handler, demonstrating how to receive and react to events like ConversationTextResponse or FunctionCallRequestResponse.

Add a validation/error-recovery pattern for WebSocket reconnection, since AttemptReconnect is listed as a key method but never demonstrated.

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary sections like the 'Central product skills' block and the 'Gotchas' section has items that could be tighter. The quick start code is clean but the trailing comments are somewhat vague rather than actionable.

2 / 3

Actionability

The quick start provides a concrete, executable connection setup, but it stops short of showing actual audio streaming, event handling, or function-call responses — the core use cases listed. Key parameters are listed but lack executable examples for runtime operations like UpdatePrompt, InjectAgentMessage, or FunctionCallResponse.

2 / 3

Workflow Clarity

The quick start shows a clear connection sequence (create settings → create handler → connect → start), but there are no validation checkpoints, no error recovery patterns for WebSocket reconnection, and the concurrent event handling / function-call response loop is mentioned but never demonstrated. For a WebSocket session involving streaming and concurrent operations, the lack of explicit feedback loops caps this at 2.

2 / 3

Progressive Disclosure

Content is well-structured with a clear quick start, key parameters summary, layered API references pointing to in-repo files and external docs, example file paths, and cross-references to related skills. References are one level deep and clearly signaled.

3 / 3

Total

9

/

12

Passed

Description

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 clearly defines its scope, includes rich trigger terms, explicitly states when to use it, and proactively addresses potential conflicts with related skills. The negative routing guidance ('Route standalone STT/TTS work to...') is a particularly strong feature that reduces ambiguity in skill selection.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: writing/reviewing Go code, running Deepgram Voice Agent sessions over WebSockets, runtime settings, prompt updates, speak updates, injected messages, and event handling. Also specifies routing for standalone STT/TTS work.

3 / 3

Completeness

Clearly answers both 'what' (writing/reviewing Go code for Deepgram Voice Agent sessions with specific features) and 'when' (explicit 'Use when' clause at the start). Also includes negative routing guidance to avoid conflicts with related skills.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms a user would say: 'Go code', 'Deepgram', 'Voice Agent', 'WebSockets', 'runtime settings', 'prompt updates', 'speak updates', 'injected messages', 'event handling', 'STT', 'TTS'. Also references related skills by name for disambiguation.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche (Deepgram Voice Agent over WebSockets in Go) and explicitly routes potential conflicts to sibling skills (deepgram-go-speech-to-text, deepgram-go-text-to-speech), minimizing overlap.

3 / 3

Total

12

/

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.