CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-openai-dotnet

Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.

57

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

This is a highly actionable, code-complete .NET SDK reference with strong executability and clean sectioning, but it is a long monolithic document with no progressive disclosure into bundle files and only modest workflow sequencing.

Suggestions

Move the Key Types Reference, Related SDKs, and detailed per-modality examples into separate reference files and link to them from a leaner overview to improve progressive disclosure.

Trim the generic "When to Use"/"Limitations" boilerplate and consolidate the three authentication examples to reduce token cost.

Add an explicit end-to-end workflow (e.g., authenticate → build client → call → handle errors → validate response) with a checkpoint to raise workflow clarity.

DimensionReasoningScore

Conciseness

The body is mostly efficient code-first reference with little concept padding, but at ~459 lines it includes redundant boilerplate ("When to Use"/"Limitations" generic text) and overlapping auth examples that could be tightened.

2 / 3

Actionability

It provides fully executable, copy-paste-ready C# across chat, embeddings, images, audio, tools, and error handling with concrete options and types, matching the executable-code anchor.

3 / 3

Workflow Clarity

Sections are well organized, but as a reference catalog there is no multi-step workflow with explicit validation checkpoints or feedback loops, so it sits at the steps-present-but-checkpoints-implicit level.

2 / 3

Progressive Disclosure

All content is inline in a single monolithic SKILL.md with no bundle files or one-level-deep references; it has section structure but material (type reference, related SDKs, full code examples) that could be split into separate files remains inline.

2 / 3

Total

9

/

12

Passed

Description

67%

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

The description is specific and distinctive, clearly naming the SDK and its concrete capabilities, but its trigger guidance reads as a capability list rather than natural when-to-use phrasing, leaving completeness and trigger-term quality at the mid level.

Suggestions

Rewrite the trigger clause to name natural user situations, e.g., "Use when working with Azure OpenAI or OpenAI APIs in .NET for chat, embeddings, DALL-E images, or Whisper audio."

Add common model/term variations users would actually say (GPT-4, GPT-4o, DALL-E, Whisper, text-embedding) to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — "chat completions, embeddings, image generation, audio transcription, and assistants" — rather than vague language, matching the multi-action anchor.

3 / 3

Completeness

It clearly states what ("Client library for Azure OpenAI and OpenAI services") but the "Use for..." clause enumerates capabilities rather than giving explicit when-to-use trigger situations, leaving the "when" only implied.

2 / 3

Trigger Term Quality

"Azure OpenAI SDK for .NET" and the capability names provide some relevant keywords, but it lacks common natural variations a user would say (e.g., "GPT-4," "DALL-E," "Whisper," ".NET OpenAI") and leans on capability jargon.

2 / 3

Distinctiveness Conflict Risk

"Azure OpenAI SDK for .NET" names a clear, narrow niche with distinct triggers unlikely to collide with unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
boisenoise/skills-collections
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.