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.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-ai-agents-persistent-java/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 content is highly actionable with executable Java covering the complete agent lifecycle and a clear sequenced workflow. Main gaps are the polling code not handling terminal failure states and generic footer boilerplate.

Suggestions

Extend the run-polling code to check and branch on terminal statuses (Failed, Cancelled, RequiresAction) so the workflow includes an explicit validation/feedback checkpoint rather than only looping on QUEUED/IN_PROGRESS.

Replace the generic 'When to Use'/'Limitations' boilerplate with skill-specific guidance, or remove it to tighten token efficiency.

DimensionReasoningScore

Conciseness

Mostly lean with executable code and no over-explanation of basics, but the generic 'When to Use'/'Limitations' footer boilerplate is padding that could be trimmed.

4 / 5

Actionability

Provides fully executable, copy-paste-ready Java covering the full workflow (client setup, agent/thread/message/run, polling, cleanup, error handling).

5 / 5

Workflow Clarity

Clear numbered 1–6 sequence with a polling loop, but the run code only handles QUEUED/IN_PROGRESS and does not validate or branch on terminal failure states (Failed, RequiresAction, Cancelled) despite Best Practices mentioning them.

4 / 5

Progressive Disclosure

Well-organized sections with external reference links; no bundle files present so structure is self-contained, though some bulk (e.g., full API surface) could be offloaded to a reference file.

4 / 5

Total

17

/

20

Passed

Description

75%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 with concrete capabilities and a distinct niche, but lacks an explicit 'Use when…' trigger clause, capping completeness at 3. Adding natural-language trigger phrases would raise trigger-term quality and completeness.

Suggestions

Add an explicit 'Use when…' clause naming the natural situations users would invoke this skill (e.g., 'Use when creating Azure AI agents, managing agent threads, or running agent tool calls in Java').

Include natural synonyms/variations users say beyond the technical terms (e.g., 'AI assistant', 'chat thread', 'agent run', 'tool calls') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions ('creating and managing AI agents with threads, messages, runs, and tools'), matching the comprehensive-coverage anchor.

5 / 5

Completeness

Has a clear 'what' but no 'Use when…' trigger clause; per the judging guideline a missing explicit trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Solid domain keywords ('AI agents', 'threads', 'messages', 'runs', 'tools') but missing common natural-language synonyms or file-extension-style triggers users would actually say.

4 / 5

Distinctiveness Conflict Risk

'Azure AI Agents Persistent SDK for Java' is a clear, specific niche with distinct triggers and minimal overlap with unrelated skills.

5 / 5

Total

17

/

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
sickn33/antigravity-awesome-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.