deepgram-go-text-intelligence
Use when writing or reviewing Go code in this repo that sends text to Deepgram Read via the analyze client. Route speech/audio inputs to deepgram-go-speech-to-text or deepgram-go-audio-intelligence, and management/admin work to deepgram-go-management-api.
96
95%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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 well-crafted skill description that excels at disambiguation and completeness. It clearly defines its scope (Go code for Deepgram Read text analysis) and explicitly routes adjacent use cases to other skills. The main weakness is that it could be more specific about the concrete actions it supports beyond 'writing or reviewing' code.
Suggestions
Add specific concrete actions the skill helps with, e.g., 'configure analyze requests, handle sentiment/intent/summary responses, set up topic detection' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Go code, Deepgram Read, analyze client) and mentions some actions ('writing or reviewing Go code', 'sends text to Deepgram Read'), but doesn't list multiple concrete actions like specific API operations or code patterns it helps with. | 2 / 3 |
Completeness | Clearly answers both 'what' (writing/reviewing Go code that sends text to Deepgram Read via the analyze client) and 'when' (explicit 'Use when' clause), plus provides routing guidance for when NOT to use this skill, directing to alternative skills for speech/audio and management tasks. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'Go code', 'Deepgram Read', 'analyze client', 'text', 'speech/audio', and explicitly names related skills to route to (deepgram-go-speech-to-text, deepgram-go-audio-intelligence, deepgram-go-management-api), which helps with disambiguation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-drawing: it specifies this is for text analysis via the analyze client, and explicitly routes speech/audio and management tasks to other named skills, minimizing conflict risk with related Deepgram skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently teaches Claude how to use Deepgram's text intelligence analyze client in Go. It excels at routing (clearly directing to other skills for audio/management tasks), provides a complete executable example, and organizes references in a clean layered structure. The gotchas section adds genuine value by addressing non-obvious pitfalls like package naming vs. product naming.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. It avoids explaining what Deepgram is or how Go works, assumes Claude's competence, and every section serves a clear purpose. The routing guidance at the top is essential context, not filler. | 3 / 3 |
Actionability | Provides a fully executable, copy-paste-ready Go example with proper imports, error handling, and response access. Key parameters and constructors are concretely listed with exact package paths and method names. | 3 / 3 |
Workflow Clarity | This is a single-task skill (send text to Deepgram's analyze API) with a clear, unambiguous workflow. The routing decision tree at the top acts as a validation checkpoint for choosing the right skill, and the gotchas section prevents common missteps. | 3 / 3 |
Progressive Disclosure | The skill provides a concise overview with a well-organized layered API reference section pointing to in-repo files, OpenAPI specs, and product docs — all one level deep. Example files are referenced by path. The central skills cross-reference is a nice touch for broader context. | 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.
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.