CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

76

1.63x
Quality

63%

Does it follow best practices?

Impact

100%

1.63x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-agents-persistent-java/SKILL.md

The canonical home for this skill is azure-ai-agents-persistent-java in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%Weight 40%Scale 1-5

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

The body is a lean, code-first reference with clear sequencing and mostly executable examples, but it lacks explicit validation/feedback loops around the polling and destructive cleanup steps, capping workflow clarity. Progressive disclosure is adequate given the absence of bundle files.

Suggestions

Add an explicit validation/feedback loop to the run step: check for Failed/Cancelled/RequiresAction statuses in the polling code and show how to recover, not just QUEUED/IN_PROGRESS.

Add a pre-deletion validation checkpoint in the cleanup step (e.g. confirm the thread/run completed and list messages before deleting).

Declare `modelDeploymentName` (and any other undefined variables) in the snippets, or note they must be set, so the code is fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is mostly lean code-driven sections with brief intros and avoids explaining concepts Claude already knows; only minor trimmable padding remains, such as the repeated intro line and the vague 'When to Use' filler ('applicable to execute the workflow or actions described in the overview').

4 / 5

Actionability

Provides concrete, mostly executable Java examples for each workflow step (createAgent, createThread, createMessage, createRun, listMessages, cleanup, error handling), with only minor gaps such as the undeclared `modelDeploymentName` variable and an unclear createAgent argument order.

4 / 5

Workflow Clarity

The six-step core workflow is clearly sequenced, but validation checkpoints are implicit: the polling loop only handles QUEUED/IN_PROGRESS in code, and the destructive cleanup step (deleteThread/deleteAgent) has no validation, which caps workflow clarity at 3 per the rubric's destructive-operation rule.

3 / 5

Progressive Disclosure

Content is well-organized into clearly labeled sections with no nested references, and external pointers (Maven, GitHub) are tabulated; since no bundle files exist, all content is appropriately inline, with only minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

58%Weight 40%Scale 1-5

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 clearly states what the SDK does and names concrete domain objects, but it lacks an explicit 'when to use' trigger clause and leans on technical jargon over natural user phrasing. It is distinct but capped on completeness by the missing trigger guidance.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. 'Use when creating Azure AI agents in Java or managing persistent agent threads, messages, and runs').

Replace or supplement SDK jargon ('threads, messages, runs') with natural synonyms a user would say, such as 'conversations', 'chat history', or 'assistant'.

Include the Java file extension or package hint (e.g. 'com.azure') to strengthen trigger-term coverage for Java-specific queries.

DimensionReasoningScore

Specificity

Names the domain (Azure AI Agents Persistent SDK for Java) and lists several concrete operations and objects — 'creating and managing AI agents with threads, messages, runs, and tools' — but actions are object nouns rather than a fully comprehensive verb list, leaving minor coverage gaps.

4 / 5

Completeness

The 'what' is clearly stated ('Low-level SDK for creating and managing AI agents...'), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Contains relevant natural keywords like 'AI agents' and 'Azure AI Agents', but the rest ('threads, messages, runs, and tools') is SDK jargon, and common variations/synonyms (e.g. 'assistant', 'deploy agent') are absent.

3 / 5

Distinctiveness Conflict Risk

The combination of 'Azure', 'Java', and 'persistent agents' defines a fairly clear niche with minimal conflict risk, though it could overlap with other Azure AI or OpenAI-style agent skills.

4 / 5

Total

14

/

20

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.