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.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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 specifies the domain (C# Deepgram Management APIs), lists concrete entities and methods, provides an explicit 'Use when' trigger clause, and even distinguishes itself from related skills by noting what it does NOT cover. The description is concise yet comprehensive, making it easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and entities: 'Deepgram Management APIs for projects, models, keys, members, invitations, usage, balances, and auth token grants.' Also names specific factory methods like `CreateManageClient()` and `CreateAuthClient()`. | 3 / 3 |
Completeness | Clearly answers both 'what' (calls Deepgram Management APIs for various resources, covers specific client factory methods) and 'when' (explicitly starts with 'Use when writing or reviewing C# code in this repo that calls Deepgram Management APIs'). Also includes a helpful exclusion note about Voice Agent configuration. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords a user would say: 'C#', 'Deepgram', 'Management APIs', 'projects', 'keys', 'members', 'invitations', 'usage', 'balances', 'auth token', plus specific method names. Good coverage of domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: C# code specifically for Deepgram Management APIs. The mention of specific factory methods and the explicit exclusion of Voice Agent configuration endpoints further reduces conflict risk with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 well-structured, highly actionable skill with executable C# examples covering the full breadth of the Deepgram Management API. Its main weakness is the lack of explicit validation/verification steps for destructive operations (delete, remove) and some minor verbosity in sections like the central product skills promo. The progressive disclosure and reference layering are excellent.
Suggestions
Add an explicit guard/confirmation pattern for destructive operations (DeleteProject, DeleteKey, RemoveMember) — e.g., a code snippet showing how to verify the resource exists and confirm before deletion, rather than just advising to 'comment or guard'.
Trim the 'Central product skills' section to 1-2 lines or move it to a footnote — it reads more like marketing than actionable guidance for Claude.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but includes some unnecessary explanation (e.g., the 'Central product skills' section and the detailed env var fallback behavior description). The 'Key methods' bullet list is borderline redundant given the code examples already demonstrate usage patterns, though it serves as a quick reference. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready C# code examples covering all major use cases (projects, keys, invites, members, usage, balances, auth token grants). Code includes proper using statements, realistic parameter values, and demonstrates the complete workflow from client creation to API calls. | 3 / 3 |
Workflow Clarity | The quick-start sections show clear sequences (initialize → create client → call methods), and gotcha #3 warns about destructive operations. However, there are no explicit validation checkpoints or feedback loops for destructive operations like DeleteProject/DeleteKey/RemoveMember — the skill only says to keep them 'commented or guarded' without showing how to verify before proceeding. | 2 / 3 |
Progressive Disclosure | Well-structured with a clear overview, quick-start sections for different use cases, a concise key methods reference, and a layered API reference section pointing to in-repo source files, OpenAPI specs, and external docs. Example file paths are clearly listed for deeper exploration. Navigation is one level deep and clearly signaled. | 3 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/deepgram-dotnet-sdk
- Commit
d0d6fee
- 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.