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.

Install with Tessl CLI

npx tessl i github:boisenoise/skills-collections --skill azure-ai-agents-persistent-dotnet

What are skills?

2.40x

Quality

60%

Does it follow best practices?

Impact

96%

2.40x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-azure-ai-agents-persistent-dotnet/SKILL.md

SKILL.md

Review

Evals

Discovery

32%

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 identifies the technology stack (Azure AI Agents, .NET) and lists key concepts (threads, messages, runs, tools), but lacks concrete action verbs and completely omits trigger guidance. The term 'Persistent SDK' is unclear and the description reads more like a library tagline than actionable skill guidance for Claude's skill selection.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user asks about Azure AI Agents, building conversational agents in C#/.NET, or working with the Azure.AI.Projects SDK'

Replace abstract concepts with concrete actions: 'Create AI agents, manage conversation threads, send and retrieve messages, execute agent runs, configure tools like code interpreter and file search'

Clarify what 'Persistent' means or remove it, and add natural user terms like 'C#', 'dotnet', 'Azure OpenAI agents', 'assistant API'

Dimension	Reasoning	Score
Specificity	Names the domain (Azure AI Agents SDK for .NET) and mentions some actions ('creating and managing AI agents with threads, messages, runs, and tools'), but these are somewhat abstract concepts rather than concrete user-facing actions like 'create agent', 'send message', 'execute run'.	2 / 3
Completeness	Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. There's no indication of when Claude should select this skill over others.	1 / 3
Trigger Term Quality	Includes relevant technical terms like 'Azure AI Agents', '.NET', 'SDK', 'threads', 'messages', 'runs', 'tools', but missing common variations users might say like 'Azure OpenAI', 'assistant API', 'C#', or 'dotnet'. The terms are more technical jargon than natural user language.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Azure AI Agents' and '.NET' provides some distinctiveness, but 'Persistent SDK' is unclear, and it could overlap with other Azure SDK skills or general AI agent skills. The 'Low-level SDK' qualifier helps somewhat but isn't a strong differentiator.	2 / 3
	Total	7 / 12 Passed

Implementation

87%

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

This is a high-quality SDK reference skill with excellent actionability and conciseness. The code examples are comprehensive and executable, covering authentication, core workflows, multiple tool types, and cleanup. The main weakness is the lack of explicit validation steps in the workflow, particularly for operations that could fail (file uploads, vector store creation) before dependent operations are attempted.

Suggestions

Add validation checkpoints after file upload and vector store creation (e.g., check file.Status or vectorStore.Status before proceeding)

Include error handling in the core workflow section, not just as a separate section at the end

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, providing executable code examples without explaining basic concepts Claude already knows. Every section serves a purpose with no padding or unnecessary context.	3 / 3
Actionability	All code examples are fully executable and copy-paste ready with proper imports, async/await patterns, and complete method calls. The examples cover the full workflow from authentication through cleanup.	3 / 3
Workflow Clarity	The numbered workflow steps are clear and sequential, but validation checkpoints are missing. For operations like file uploads and vector store creation, there's no explicit error checking or validation before proceeding to dependent steps.	2 / 3
Progressive Disclosure	Content is well-organized with clear sections progressing from installation to advanced features. Reference tables at the end provide quick lookups, and external links are clearly signaled for deeper exploration.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Reviewed: 1 day 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.