AgentScope Java

What it does

AgentScope Java provides concrete guidance and best-practice patterns for writing reactive, message-driven agents in Java using Project Reactor. The skill instructs the agent on non-blocking patterns, correct imports, hook and pipeline usage, testing with StepVerifier, tool definitions, and common pitfalls to avoid when integrating LLM models and tools in production Java services. It includes conventions for project setup (Maven), coding standards, and examples for building ReAct-style agents and toolkits.

When to use it

Use this skill when a user asks for Java code or guidance targeting the AgentScope framework, when they request reactive (Mono/Flux) examples, when they mention AgentScope, ReActAgent, Project Reactor, or need help converting blocking examples to non-blocking code. It's appropriate for production-ready agent design, hooking tools, and pipeline composition in Java 17+.

What's included

• Scripts: None detected (has_scripts=false)
• References: None detected (has_references=false)
• Instructions: Detailed coding rules (never use .block() in agent logic), project setup, dependency guidance, hook and pipeline patterns, testing examples, and security notes about API keys and MCP integration. The body contains runnable code examples for main() usage and testing patterns and enumerates prohibited practices.

Compatible agents

Designed for Claude Code and Cursor (per frontmatter). The guidance and examples are standard Java and applicable when generating code for Copilot/Codex-style environments as well.