CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

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 strong, executable reference skill: copy-paste Java quick-starts with a real validation guard, a concrete API-surface map, and well-signaled external pointers. It stays lean but has minor redundancy across its API-surface, example-file, and gotcha sections that could be consolidated.

Suggestions

Collapse the "Key parameters / API surface" bullet list and the "Example files in this repo" list into the quick-start/reference sections to remove overlap and tighten the file.

Add a short validate→fix→retry note for the commented-out create/delete examples so destructive calls have an explicit feedback loop before uncommenting.

Consider moving the bulk API-surface enumeration into a one-level reference file (or the cited in-repo source) to keep SKILL.md a pure overview.

DimensionReasoningScore

Conciseness

Lean and free of concept padding, assuming Claude's competence, but the API-surface bullet list, the "Example files in this repo" list, and the Gotchas mildly overlap content already shown in the quick-start blocks and could be trimmed.

4 / 5

Actionability

Fully executable Java with imports, env-var auth, real method chains, and an empty-project guard — copy-paste ready and covering the common list/inspect cases across projects, keys, members, invites, usage, and billing.

5 / 5

Workflow Clarity

Sequences list-projects → guard-against-empty → pick projectId → scoped resource calls with an explicit IllegalStateException validation checkpoint, but lacks a full validate→fix→retry feedback loop or checklist for the (default read-only) destructive operations.

4 / 5

Progressive Disclosure

No bundle files exist; the single SKILL.md is well-organized with clearly signaled one-level-deep references (in-repo source paths, OpenAPI, Context7, product docs), though the inline API-surface and example-file lists are mildly bulky for an overview file.

4 / 5

Total

17

/

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 tight, high-signal description that concretely enumerates capabilities, gives an explicit use-when clause with natural triggers, and cleanly distinguishes itself from sibling skills. The only minor gap is trigger phrasing that lists keywords without synonym/extension variants.

DimensionReasoningScore

Specificity

Lists multiple concrete administrative resources — "projects, project models, API keys, members, invites, usage, and billing" plus the specific think-model discovery path — giving comprehensive, non-abstract coverage of capabilities.

5 / 5

Completeness

Explicitly answers both what ("calls Deepgram Management APIs for projects, project models, API keys, members, invites, usage, and billing") and when ("Use when writing or reviewing Java code in this repo that calls...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides eight natural trigger phrases ("management api", "list projects", "api keys", "members", "invites", "usage", "billing", "models") users would actually say, but they read as a keyword enumeration rather than a synonym/extension-rich set.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (Java Deepgram Management/admin APIs) and explicitly redirects to `deepgram-java-voice-agent` for live agents, 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-java-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.