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".

87

1.30x
Quality

84%

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

76%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.

An actionable, well-structured reference skill with copy-paste code and clear disambiguation; its main gap is the absence of explicit validation/feedback loops around the destructive admin operations it exposes.

Suggestions

Add a short validation/verification note before destructive calls (e.g., confirm project_id and dry-run/list before delete/leave/key deletion) to lift workflow_clarity above the destructive-op cap.

Trim narrative lead-ins (e.g., "Administrative REST endpoints under /v1/projects, /v1/models, and related project subresources.") to improve token efficiency.

Consider moving the full API-surface bullet list into the referenced reference.md and keeping only the most-used calls inline to tighten progressive disclosure.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence (no padded explanation of what Deepgram or an SDK is) with tight Quick-start code blocks; a few narrative lines like "Administrative REST endpoints under /v1/projects..." could be trimmed, leaving it mostly efficient with minor over-explanation.

4 / 5

Actionability

Provides copy-paste-ready executable JS for projects, keys, members, invites, usage, billing, models, and think-model discovery, plus an explicit API-surface map covering the common cases.

5 / 5

Workflow Clarity

The skill touches destructive operations (delete, leave, member/key removal) and flags them as risky in Gotchas, but provides no explicit validate→fix→retry checkpoints, so the destructive-operation cap applies.

3 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level-deep references (in-repo reference.md, canonical OpenAPI/AsyncAPI URLs, product docs, Context7); no bundle files exist, so structure is judged on the inlined overview, which is good but keeps substantial API-surface detail inline.

4 / 5

Total

16

/

20

Passed

Description

92%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, specific description that clearly states both what the skill does and when to use it, with explicit trigger phrases and disambiguation from a sibling skill. Minor room to soften technical triggers like "manage.v1".

DimensionReasoningScore

Specificity

Enumerates concrete capabilities (projects, API keys, members, invites, requests, usage, billing, models, agent think-model discovery) plus specific SDK namespaces (`client.manage.v1.*`, `client.agent.v1.settings.think.models.list()`), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers "what" (calls Deepgram Management APIs for listed resources) and "when" (Use when writing/reviewing JS/TS in this repo that calls these APIs) with a concrete Triggers list.

5 / 5

Trigger Term Quality

Lists many natural trigger phrases ("management API", "list projects", "API keys", "members", "invites", "usage stats", "billing", "list models") plus the technical "manage.v1"; good coverage with a couple of terms leaning technical rather than user-natural.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Deepgram Management API for JS/TS) and explicitly disambiguates from `deepgram-js-voice-agent`, minimizing wrong-skill triggering.

5 / 5

Total

19

/

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.

Validation16 / 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.