azure-ai-agents-persistent-dotnet

Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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

A highly actionable, well-sequenced SDK reference dominated by executable code with clear workflow steps and error handling. Its one weakness is progressive disclosure: everything is inlined in a single file rather than split into one-level-deep reference files.

Suggestions

Move the static reference material (Available Tools, Streaming Update Types, Key Types Reference) into a bundled REFERENCE.md and link to it from a concise overview, keeping the core workflow inline.

Trim the generic 'When to Use'/'Limitations' boilerplate or replace it with SDK-specific guidance that earns its tokens.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable code and reference tables, assuming Claude's competence without explaining basic SDK concepts; only minor generic filler in the closing 'When to Use'/'Limitations' sections.	3 / 3
Actionability	Provides fully executable, copy-paste-ready C# across nine workflow steps plus install commands, env vars, and concrete error-handling examples.	3 / 3
Workflow Clarity	Nine clearly numbered, sequenced steps with a polling loop that acts as a status-checkpoint feedback loop and a dedicated error-handling section for recovery.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is monolithic — large reference tables (Available Tools, Streaming Update Types, Key Types) and all nine examples live inline with no split-out bundle files.	2 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, well-scoped description that names concrete actions and natural trigger terms for the .NET Azure AI Agents domain. Its main weakness is the missing 'Use when…' trigger guidance, which caps completeness at 2.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when creating or managing persistent Azure AI agents, threads, messages, runs, or tool integrations in .NET.'

Dimension	Reasoning	Score
Specificity	Lists concrete actions and artifacts — 'creating and managing AI agents with threads, messages, runs, and tools' — naming the domain (Azure AI Agents Persistent SDK for .NET).	3 / 3
Completeness	Clearly answers 'what' (creating/managing agents with threads, messages, runs, tools) but lacks any 'Use when…' clause or explicit trigger guidance, capping completeness at 2.	2 / 3
Trigger Term Quality	Contains natural terms the target audience would say — 'Azure AI Agents', '.NET', 'threads, messages, runs, and tools' — giving good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The narrow 'Azure AI Agents Persistent SDK for .NET' framing carves a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Commit: f36337d

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.