CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-go-text-to-speech

Use when writing or reviewing Go code in this repo that synthesizes audio with Speak v1 REST or Speak WebSockets. Route transcription work to deepgram-go-speech-to-text, voice conversation runtime work to deepgram-go-voice-agent, and repository maintenance work to deepgram-go-maintaining-sdk.

68

Quality

81%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

This is a solid, actionable skill with fully executable Go examples for both REST and WebSocket TTS workflows, clear routing to sibling skills, and well-organized progressive disclosure. Its main weaknesses are moderate verbosity in the boilerplate-heavy code examples and the lack of explicit validation/error-recovery steps in the WebSocket streaming workflow. The 'Central product skills' section adds marginal value relative to its token cost.

Suggestions

Add explicit validation/error-recovery guidance for the WebSocket flow (e.g., what to do when Connect() fails, how to verify audio output integrity, handling partial audio frames).

Trim Go boilerplate in examples — consider showing just the run() function body since Claude knows how to write main() with log.Fatal patterns.

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some unnecessary verbosity. The two full main() boilerplate examples could be trimmed (Claude knows Go main/log patterns). The 'Central product skills' section at the bottom adds tokens for cross-promotion rather than actionable guidance. However, it avoids explaining what TTS is or how Go works.

2 / 3

Actionability

Both REST and WebSocket examples are fully executable, copy-paste ready Go programs with correct imports and error handling. Key parameters, constructors, and methods are concretely listed. The authentication section gives a specific export command.

3 / 3

Workflow Clarity

The quick start examples show clear sequences (create client → connect → send text → flush → stop), but there are no explicit validation checkpoints or error recovery feedback loops. For WebSocket flows involving streaming audio, there's no guidance on what to do if Connect() returns false beyond returning an error, and no verification that audio was correctly received/saved.

2 / 3

Progressive Disclosure

Content is well-structured with clear sections progressing from routing/authentication through quick start to parameters and references. The API reference section provides a well-organized layered hierarchy of in-repo files, external specs, and product docs. Example file paths are clearly listed for deeper exploration.

3 / 3

Total

10

/

12

Passed

Description

89%

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 a strong description with excellent completeness and distinctiveness. The explicit 'Use when' clause and routing to sibling skills make it highly effective for skill selection in a multi-skill environment. The main weakness is that the specific capabilities (concrete actions beyond 'writing or reviewing') could be more detailed to help Claude understand the full scope of what this skill covers.

Suggestions

Add 2-3 more specific concrete actions such as 'generate audio from text, configure voice parameters, manage WebSocket streaming connections' to improve specificity.

DimensionReasoningScore

Specificity

It names the domain (Go code, audio synthesis with Speak v1 REST or Speak WebSockets) and mentions some actions (writing, reviewing), but doesn't list specific concrete actions like 'generate audio from text, configure voice parameters, handle streaming audio output'.

2 / 3

Completeness

Clearly answers both 'what' (writing/reviewing Go code for audio synthesis with Speak v1 REST or WebSockets) and 'when' (explicit 'Use when' clause plus routing guidance for when NOT to use it, directing to sibling skills).

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'Go code', 'synthesizes audio', 'Speak v1 REST', 'Speak WebSockets', 'text-to-speech' is implied via 'Speak'. Also includes routing terms that help distinguish from related skills like 'transcription', 'voice agent', 'SDK maintenance'.

3 / 3

Distinctiveness Conflict Risk

Excellent distinctiveness — explicitly routes competing concerns (transcription, voice agent, SDK maintenance) to named sibling skills, making it very clear when this skill should and should not be selected.

3 / 3

Total

11

/

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.