CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

89

1.30x
Quality

86%

Does it follow best practices?

Impact

91%

1.30x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

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 reference skill with strong actionability—concrete, executable code examples covering the full management API surface. Its main weaknesses are moderate redundancy between sections (use-cases vs. API surface) and the lack of validation/safety workflows around destructive operations despite explicitly acknowledging their danger. The progressive disclosure and organization are excellent.

Suggestions

Add a brief workflow with validation checkpoints for destructive operations (e.g., 'Before deleting a key: list keys → confirm key ID → delete → verify deletion'), since the Gotchas section already warns about them.

Consolidate the 'When to use this product' bullets and 'Key parameters / API surface' section to reduce duplication—one could be a concise summary and the other the detailed reference.

DimensionReasoningScore

Conciseness

The skill is mostly efficient and avoids explaining basic concepts, but includes some sections that could be tightened—e.g., the 'When to use this product' bullet list partially duplicates the 'Key parameters / API surface' section, and the extensive API reference links and example file listing add bulk without proportional value.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code for authentication, project listing, key/member/invite/usage/billing operations, and model discovery. The SDK method chains are concrete and specific, covering the full API surface with real method signatures.

3 / 3

Workflow Clarity

The skill covers many API calls but presents them as flat listings rather than sequenced workflows. Given that destructive operations (delete, leave, key deletion) are explicitly called out in Gotchas, there are no validation checkpoints or feedback loops for those risky operations, which caps this at 2.

2 / 3

Progressive Disclosure

Content is well-structured with clear sections progressing from authentication to quick starts to full API surface to gotchas. References to external resources (reference.md, OpenAPI spec, product docs, example files) are clearly signaled and one level deep. The layered API reference section is particularly well-organized.

3 / 3

Total

10

/

12

Passed

Description

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 API administration in JS/TS), provides rich trigger terms, and explicitly distinguishes itself from a related skill. It covers all rubric dimensions well with concrete actions, explicit 'Use when' guidance, and a clear boundary statement.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: calling Deepgram Management APIs for 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' (writing/reviewing JS/TS code calling Deepgram Management APIs for specific resources) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms listed at the end). Also includes a helpful negative boundary distinguishing it from the voice agent skill.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms including 'management API', 'list projects', 'API keys', 'members', 'invites', 'usage stats', 'billing', 'list models', and 'manage.v1'. These are terms users would naturally use when working with Deepgram management functionality.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche (Deepgram Management APIs specifically). Explicitly differentiates itself from the `deepgram-js-voice-agent` skill for running agents live, reducing conflict risk. The specific API paths and management-focused trigger terms make it unlikely to be confused with other skills.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
deepgram/deepgram-js-sdk
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.