CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-dotnet-management-api

Use when writing or reviewing C# code in this repo that calls Deepgram Management APIs for projects, models, keys, members, invitations, usage, balances, and auth token grants. Covers `ClientFactory.CreateManageClient()` and `ClientFactory.CreateAuthClient()`. Unlike some other SDKs, this repo does not currently expose reusable Voice Agent configuration management endpoints.

73

Quality

90%

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

88%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 tight, highly actionable body with complete executable examples and an explicit verify-delete-verify workflow for destructive calls. Slight redundancy between the method list and quick-start code, and the absence of any bundle reference files keeps progressive disclosure from a top score.

DimensionReasoningScore

Conciseness

The body is largely lean with code-first, no-filler sections, but the 'Key methods' list partially overlaps the quick-start code and the 'References' section duplicates some in-repo paths already surfaced, so it is not maximally tight.

4 / 5

Actionability

Multiple complete, executable C# code blocks with real method names and schemas cover the common cases (projects/models, keys/invites/members/usage, auth token grant, destructive guard), making it copy-paste ready.

5 / 5

Workflow Clarity

The destructive-operation guard is a fully sequenced verify-delete-verify pattern with try/catch error feedback, and the quick-start sections explicitly sequence prerequisite steps (fetch projectId before sub-resource calls), satisfying the feedback-loop expectation.

5 / 5

Progressive Disclosure

Section headers and a clearly signaled 'References'/'Example files' structure make navigation easy with one-level-deep pointers, but no bundle reference files actually exist, so the across-files splitting aspect is only partially exercised.

4 / 5

Total

18

/

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 highly specific, well-triggered description that clearly states both what the skill covers and when to use it, with explicit boundary guidance against sibling SDK skills. Minor room for more natural synonyms in the trigger terms.

DimensionReasoningScore

Specificity

Enumerates concrete resources ('projects, models, keys, members, invitations, usage, balances, and auth token grants') and concrete factory methods ('ClientFactory.CreateManageClient() and ClientFactory.CreateAuthClient()'), giving comprehensive coverage rather than just naming the domain.

5 / 5

Completeness

Explicitly answers both 'what' (calls Deepgram Management APIs for the listed resources; covers the two factory methods) and 'when' via the concrete 'Use when writing or reviewing C# code in this repo that calls Deepgram Management APIs' clause.

5 / 5

Trigger Term Quality

Natural developer terms ('C# code', 'Deepgram Management APIs', 'projects, models, keys, members, invitations, usage, balances') are well covered with some synonyms, though a few common variants like '.NET' or 'API keys' are absent.

4 / 5

Distinctiveness Conflict Risk

Niche is sharply scoped to C#/.NET Management APIs and explicitly distinguishes itself from sibling skills ('this repo does not currently expose reusable Voice Agent configuration management endpoints'), minimizing wrong-skill triggers.

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-dotnet-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.