deepgram-js-management-api
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Management APIs for projects, API keys, members, invites, requests, usage, billing, models, and agent think-model discovery. Covers `client.manage.v1.*` plus `client.agent.v1.settings.think.models.list()`. Use `deepgram-js-voice-agent` when you want to run an agent live rather than administer projects or inspect models. Triggers include "management API", "list projects", "API keys", "members", "invites", "usage stats", "billing", "list models", and "manage.v1".
87
82%
Does it follow best practices?
Impact
91%
1.30xAverage score across 3 eval scenarios
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 marks. It provides specific concrete actions, comprehensive trigger terms, explicit 'Use when' guidance, and even disambiguates from a related skill to reduce conflict risk. The description is information-dense without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and API domains: projects, API keys, members, invites, requests, usage, billing, models, and agent think-model discovery. Also specifies exact API paths like `client.manage.v1.*` and `client.agent.v1.settings.think.models.list()`. | 3 / 3 |
Completeness | Clearly answers both 'what' (calls Deepgram Management APIs for projects, keys, members, etc.) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms listed at the end). Also includes a disambiguation note about when NOT to use it (use `deepgram-js-voice-agent` for running agents live). | 3 / 3 |
Trigger Term Quality | Includes a rich set of natural trigger terms users would say: 'management API', 'list projects', 'API keys', 'members', 'invites', 'usage stats', 'billing', 'list models', and 'manage.v1'. These cover common variations of how a developer would phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Deepgram Management APIs specifically), and explicitly disambiguates from a related skill (`deepgram-js-voice-agent`) for running agents live. The specific API paths and trigger terms make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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 executable code examples covering the full Deepgram Management API surface. Its main weaknesses are the lack of validation/error-handling workflows for destructive operations and some sections (example file listing, layered API references) that add bulk without proportional value. The gotchas section is genuinely useful and adds information Claude wouldn't otherwise know.
Suggestions
Add a short workflow with explicit validation/confirmation steps for destructive operations (delete project, remove member, delete key) — e.g., 'list first, confirm ID, then delete, then verify deletion'.
Move the 'Example files in this repo' enumeration into a referenced file or remove it, since Claude can discover files via tools; this saves ~15 lines of low-value content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some sections that could be tightened — the 'When to use this product' bullet list partially restates the description, the 'API reference (layered)' section is lengthy with external URLs that may go stale, and the 'Example files in this repo' list is low-value enumeration. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready code examples for authentication, project management, keys, members, invites, usage, billing, and model listing. The API surface section gives concrete method paths that Claude can directly use. | 3 / 3 |
Workflow Clarity | The skill presents clear API call patterns but lacks explicit validation checkpoints or feedback loops. Given that destructive operations (delete, leave, key deletion) are called out in Gotchas, the absence of a workflow showing confirmation/validation before destructive calls caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill references `reference.md` and example files for deeper detail, which is good, but no bundle files are provided to verify these references. The inline content is reasonably structured with clear sections, but the 'API reference (layered)' section dumps many external links inline rather than cleanly pointing to a single reference file, and the example file listing could be in a separate index. | 2 / 3 |
Total | 9 / 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-js-sdk
- Commit
c567b98
- 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.