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".

88

1.30x
Quality

85%

Does it follow best practices?

Impact

91%

1.30x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable reference skill: executable code for every major management resource, honest limitations, sharp gotchas, and clearly layered external references. The few deductions are for duplicated API-surface listing, the absence of an explicit validation loop around destructive calls, and inline reference material that could be offloaded.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows, but minor padding could be trimmed: the promotional "Central product skills" paragraph and the "Key parameters / API surface" section partially duplicate the quick-start snippets, placing it just below the every-token-earns-its-place anchor.

4 / 5

Actionability

Copy-paste-ready authentication and quick-start blocks cover the common cases (list/get/update projects, global and project-scoped models, keys, members, invites, requests, usage, balances), with exact method chains ("projects.usage.breakdown.list", "keys.api_keys[0].api_key.api_key_id") and a concrete in-repo example-file index — fully executable guidance.

5 / 5

Workflow Clarity

The layout gives a clear path (when to use → auth → quick starts → API surface → gotchas) with each single task unambiguous, and destructive operations are explicitly flagged ("Destructive operations are real... not safe example calls"), but no explicit validate-then-proceed or error-recovery loop is provided, so it sits below the checkpoint-rich anchor at 5.

4 / 5

Progressive Disclosure

The "API reference (layered)" section signals one-level-deep navigation clearly (in-repo reference.md, canonical OpenAPI/AsyncAPI specs, Context7, product docs) alongside an example-file index, but the inlined "Key parameters / API surface" catalog is content that arguably belongs in the separate reference file, keeping it below the cleanly-split anchor at 5.

4 / 5

Total

17

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit Use-when clause, a concrete natural-language trigger list, exact SDK namespace coverage, and explicit disambiguation from the sibling voice-agent skill. The only gaps are unstated per-resource actions and a couple of missing natural trigger terms.

DimensionReasoningScore

Specificity

Enumerates concrete resources ("projects, API keys, members, invites, requests, usage, billing, models, and agent think-model discovery") and exact SDK surface ("Covers `client.manage.v1.*` plus `client.agent.v1.settings.think.models.list()`"), but the actions per resource (list/create/delete) are implied rather than explicitly listed, falling short of the comprehensive-concrete-actions anchor at 5.

4 / 5

Completeness

Both what and when are explicit: "Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Management APIs for..." states the capability set, and the closing trigger list supplies concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

The explicit trigger list ("management API", "list projects", "API keys", "members", "invites", "usage stats", "billing", "list models", "manage.v1") gives strong natural-phrase coverage, but a few natural terms are missing — notably "think models" despite it being a headline capability, and variations like creating or rotating keys — so it sits at good-but-not-comprehensive rather than 5.

4 / 5

Distinctiveness Conflict Risk

The niche is narrow (repo-scoped JS/TS Deepgram Management API) and the description actively disambiguates the nearest sibling: "Use `deepgram-js-voice-agent` when you want to run an agent live rather than administer projects or inspect models" — minimal conflict risk.

5 / 5

Total

18

/

20

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 — 16 / 16 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.