azure-ai-agents-persistent-java

Azure AI Agents Persistent SDK for Java. 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-java

What are skills?

1.63x

Quality

60%

Does it follow best practices?

Impact

100%

1.63x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-azure-ai-agents-persistent-java/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, Java SDK) and lists SDK components, but lacks explicit trigger guidance for when to use this skill. The term 'Persistent SDK' is unclear and the description would benefit from concrete use cases and a 'Use when...' clause to help Claude distinguish this from other Azure or AI-related skills.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user needs to build AI agents with Azure in Java, work with the Azure AI Agent Service, or manage agent threads and conversations'

Clarify what 'Persistent SDK' means or remove the ambiguous term - specify if this refers to stateful conversations, data persistence, or something else

Add concrete actions users would request, such as 'create conversational agents', 'manage multi-turn conversations', or 'integrate Azure AI tools into Java applications'

Dimension	Reasoning	Score
Specificity	Names the domain (Azure AI Agents SDK for Java) and mentions some actions ('creating and managing AI agents with threads, messages, runs, and tools'), but these are somewhat abstract SDK concepts rather than concrete user-facing actions.	2 / 3
Completeness	Describes what it does (SDK for creating/managing AI agents) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'Azure', 'AI Agents', 'SDK', 'Java', 'threads', 'messages', 'runs', 'tools', but missing common variations users might say like 'Azure OpenAI', 'assistant API', or 'agent development'.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Azure', 'Java', and 'AI Agents' provides some distinctiveness, but 'Persistent SDK' is unclear and could overlap with other Azure or AI agent-related skills without clearer boundaries.	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 well-crafted skill with excellent conciseness and actionability. The code examples are complete and executable, and the structure flows logically from setup to usage. The main weakness is the polling loop in step 4 which doesn't demonstrate handling of error states (Failed, Cancelled, RequiresAction) despite the best practices section recommending it.

Suggestions

Expand the polling loop in step 4 to demonstrate handling of RequiresAction, Failed, and Cancelled statuses with appropriate error recovery or reporting

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, providing only necessary information without explaining concepts Claude already knows. Each section serves a clear purpose with no padding or unnecessary context.	3 / 3
Actionability	Provides fully executable Java code examples that are copy-paste ready, including Maven dependency, authentication setup, and complete workflow steps with concrete method calls and parameters.	3 / 3
Workflow Clarity	The 6-step workflow is clearly sequenced, but validation is limited. Step 4 polls for completion but only checks QUEUED/IN_PROGRESS statuses. Best practices mention handling RequiresAction/Failed/Cancelled but the code example doesn't demonstrate this error recovery pattern.	2 / 3
Progressive Disclosure	Well-organized with clear sections progressing from installation to authentication to workflow to best practices. Reference links are provided at the end for deeper exploration. Content is appropriately sized for a single file without needing external references.	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.