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.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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 (Listen v1 speech-to-text in Go), provides explicit 'Use when' triggers, and proactively routes out-of-scope tasks to sibling skills. The routing guidance is particularly strong for disambiguation in a multi-skill environment. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: transcribing prerecorded audio with Listen v1 REST, streaming live audio with Listen v1 WebSockets, and explicitly routes other tasks (text generation, text analysis, audio analytics, conversational work) to other skills. | 3 / 3 |
Completeness | Clearly answers both 'what' (transcribes prerecorded audio via REST, streams live audio via WebSockets) and 'when' (opens with 'Use when writing or reviewing Go code in this repo...'). The explicit 'Use when' clause and routing guidance to other skills are strong. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Go code', 'transcribes prerecorded audio', 'streams live audio', 'Listen v1', 'REST', 'WebSockets', 'deepgram'. Also includes routing terms for related skills, helping disambiguation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit routing instructions that direct competing tasks to named sibling skills (deepgram-go-text-to-speech, deepgram-go-text-intelligence, etc.), minimizing conflict risk. The scope is narrowly defined to Listen v1 STT in Go. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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, well-organized skill that provides executable Go examples and clear routing to related skills. Its main weaknesses are a slightly verbose WebSocket example with pseudo-code comments, and a lifecycle workflow that lacks explicit validation checkpoints or error-recovery loops for the streaming path. The progressive disclosure and actionability are strong.
Suggestions
Convert the lifecycle bullet points into a numbered workflow with explicit validation steps (e.g., check Connect() bool, handle WriteBinary errors, verify Finalize succeeds before Stop).
Remove or condense the pseudo-code comments in the WebSocket example — either make the audio streaming fully executable with a file reader or trim to just the connection setup with a brief comment.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some unnecessary verbosity: the pseudo-code comments in the WebSocket example add bulk, the 'Central product skills' section is promotional rather than instructional, and some explanatory text (e.g., 'This SDK reads env-backed defaults via the client option layer') could be tightened. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | Both the prerecorded REST and live WebSocket examples are fully executable Go programs with correct import paths, concrete option structs, and copy-paste-ready code. Key parameters and constructor families are enumerated with specific function names and field names. | 3 / 3 |
Workflow Clarity | The lifecycle section mentions Connect → Start → stream → KeepAlive → Finalize → Stop, but this is listed as bullet points rather than a clearly sequenced workflow with validation checkpoints. The WebSocket example includes pseudo-code for streaming but lacks explicit error-handling feedback loops or validation steps (e.g., checking connection health, handling reconnection). | 2 / 3 |
Progressive Disclosure | Content is well-structured with a clear quick start, then layered API references pointing to in-repo files, OpenAPI/AsyncAPI specs, and external docs — all one level deep. The routing table at the top clearly directs users to other skills. Example file paths are listed for deeper exploration. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/deepgram-go-sdk
- Commit
b7c92f4
- 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.