deepgram-java-management-api
Use when writing or reviewing Java code in this repo that calls Deepgram Management APIs for projects, project models, API keys, members, invites, usage, and billing. Covers `client.manage().v1().*` plus related think-model discovery under `client.agent().v1().settings().think().models()`. Use `deepgram-java-voice-agent` for live agent conversations instead of admin APIs. Triggers include "management api", "list projects", "api keys", "members", "invites", "usage", "billing", and "models".
71
86%
Does it follow best practices?
Impact
—
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 hits all the key criteria. It provides specific capabilities, explicit trigger terms, clear 'use when' guidance, and even includes negative scoping to distinguish it from a related skill. The description is concise yet comprehensive, using third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and API domains: projects, project models, API keys, members, invites, usage, billing, and think-model discovery. Also specifies the exact client paths (`client.manage().v1().*` and `client.agent().v1().settings().think().models()`). | 3 / 3 |
Completeness | Clearly answers both 'what' (writing/reviewing Java code for Deepgram Management APIs covering specific domains) and 'when' (explicit 'Use when' clause at the start, plus a 'Triggers include' list). Also provides negative scoping by directing live agent conversations to a different skill. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms users would say: 'management api', 'list projects', 'api keys', 'members', 'invites', 'usage', 'billing', and 'models'. These are terms a developer would naturally use when working with Deepgram management functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Deepgram Management APIs in Java), explicit boundary with the voice agent skill (`deepgram-java-voice-agent`), and specific API paths that make it very unlikely to conflict with other skills. | 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 SDK skill that provides actionable, executable Java code with good progressive disclosure and clear navigation to supporting resources. Its main weaknesses are minor verbosity in framing sections and the lack of explicit validation/error-recovery workflows for destructive management operations (create/delete). The gotchas section adds genuine value by documenting non-obvious SDK behaviors.
Suggestions
Add an explicit validation workflow for destructive operations (e.g., create key → verify key exists → delete key → verify deletion) to improve workflow clarity.
Trim the 'Central product skills' section to 1-2 lines or move it to a footnote, as it's tangential to the management API skill itself.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., 'Administrative REST APIs for project metadata, project-scoped resources, and model discovery' restates what the heading already conveys, and the 'Central product skills' section at the bottom is tangential). The 'When to use this product' section with negative guidance is useful but slightly verbose. | 2 / 3 |
Actionability | Provides fully executable Java code for authentication, listing projects, and accessing sub-resources. The code includes proper imports, error handling (empty project guard), and concrete method chains that are copy-paste ready. | 3 / 3 |
Workflow Clarity | The quick-start sections implicitly sequence steps (authenticate → list projects → use project ID for sub-resources) and include a guard against empty projects, but there are no explicit validation checkpoints or error-recovery feedback loops for operations like create/delete keys or members. The destructive operations are mentioned as commented out but no validation workflow is provided. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from authentication to quick starts to API surface to gotchas. References to in-repo source files, external docs, and example files are clearly signaled and one level deep. The layered API reference section is particularly well-organized. | 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-java-sdk
- Commit
6d7d7d5
- 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.