deepgram-go-management-api
Use when writing or reviewing Go code in this repo that works with Deepgram management endpoints for projects, keys, members, scopes, invitations, usage, balances, or models. Route live voice runtime to deepgram-go-voice-agent and repo workflow questions to deepgram-go-maintaining-sdk.
95
93%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 (Deepgram management endpoints in Go), lists specific resource types it covers, provides explicit trigger guidance with 'Use when...', and proactively routes adjacent concerns to other skills. The negative routing is particularly effective for reducing skill selection conflicts in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete domains: 'Deepgram management endpoints for projects, keys, members, scopes, invitations, usage, balances, or models.' Also specifies concrete actions: 'writing or reviewing Go code' and routing guidance for related but distinct skills. | 3 / 3 |
Completeness | Clearly answers both 'what' (working with Deepgram management endpoints for specific resources in Go) and 'when' (explicit 'Use when writing or reviewing Go code in this repo that works with...'). Also includes negative routing to distinguish from related skills. | 3 / 3 |
Trigger Term Quality | Includes highly natural and specific trigger terms a developer would use: 'Go code', 'Deepgram', 'management endpoints', 'projects', 'keys', 'members', 'scopes', 'invitations', 'usage', 'balances', 'models'. These are terms a user working with this SDK would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting: routes live voice runtime to 'deepgram-go-voice-agent' and repo workflow questions to 'deepgram-go-maintaining-sdk', clearly carving out its niche and reducing conflict with adjacent skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted SDK skill that efficiently covers the Deepgram management API surface. It excels at conciseness, actionability with a complete executable example, and progressive disclosure with layered references. The main weakness is the lack of any caution or validation guidance around destructive operations (delete/remove endpoints), though this is a minor concern for an API wrapper skill.
Suggestions
Add a brief note in the Gotchas section about confirming before destructive operations (DeleteProject, DeleteKey, RemoveMember) to prevent accidental data loss.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-organized. It doesn't explain what management APIs are or how Go works. Every section serves a clear purpose—routing, auth, quick start, API surface, references, and gotchas. The quick start code is minimal but complete. | 3 / 3 |
Actionability | The quick start provides a fully executable Go program with proper imports, error handling, and context usage. The key parameters section gives concrete method names, and the escape hatch (`APIRequest`) is explicitly mentioned for edge cases. | 3 / 3 |
Workflow Clarity | The skill is primarily a reference/lookup skill rather than a multi-step workflow, so the bar is lower. However, the quick start shows a clear sequence (set env var → construct client → wrap with API → call methods). There are no validation checkpoints or error recovery guidance beyond basic error returns, which is acceptable for non-destructive read operations but the skill also covers destructive operations like DeleteProject/DeleteKey/RemoveMember without any confirmation or validation guidance. | 2 / 3 |
Progressive Disclosure | The content is well-structured as an overview with clear layered references: in-repo source files, OpenAPI/AsyncAPI specs, external docs, and example files. Navigation between sections is intuitive, and the routing section at the top clearly directs users to other skills for different concerns. | 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.
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.