Skills & Agents for Java

A curated collection of Skills and Agents designed for Java Enterprise development workflows.

Skills & Agents for Java

Stargazers over time

Stargazers over time

CI Builds

Goal

A curated and opinionated collection of Skills and Agents to be used in modern SDLC workflows for Java Enterprise development with your favorite AI Agent harness.

QUESTIONROLEAREASUPPORT
WHAT / WHENPO, BA, EA, SA, TLAgile & PlanningUser Stories, GitHub Issues & Jira
WHYEA, SL, TLArchitectureADRs & UML / C4 / ER Diagrams
HOWSA, TL, SWESpec-DrivenAI Plan mode & OpenSpec
HOWTL, SWEJava developmentBuild system based on Maven, Design, Coding, Testing, Observability, Refactoring & JMH Benchmarking, Performance testing with JMeter, Profiling with Async profiler/OpenJDK tools, Documentation, Spring Boot, Quarkus, Micronaut, OpenAPI, WireMock & AGENTS.md

Deliverables

The project generates a set of deliverables at the end of any iteration.

InventoryInstallationGetting Started
1. Skills for Javanpx skills add jabrena/cursor-rules-java --all --agent cursorSkills for Java
2. Agents for Java@003-agents-installation Install Agents in Cursor/ClaudeAgents for Java

⚠️ Note: If you continue using the System prompts/rules from this project, please review the article. Current System prompts/rules will be removed in the coming months.

Compatibility

This project is compatible with any tool that supports Skills, Agents, AGENTS.md, and MCP servers.

How to use them

The SDLC has evolved with this new wave of AI tooling, which enhances the software engineering process. While building this project, we identified three workflows: Prompting Engineering Workflow, Agent-driven Engineering Workflow, Pipelines Workflow.

Prompting Engineering Workflow

In this workflow, the software engineer interacts with models using User prompts. In an incremental way, you delegate a whole task or ask for help at specific points. You can use this project to refactor generated code, or delegate the task and attach a system prompt or Skills to it.

Agent-driven Engineering Workflow

Agents for Java Enterprise development were designed to help the software engineer in the implementation phase. The engineer defines solid Specs, and those specifications are delegated to Agents.

Pipelines Workflow

Adding AI tools to your pipeline can provide new opportunities to deliver more value (examples: automatic coding, code refactoring, continuous profiling, and others).

Further information here.

Limitations

Lack of determinism

From the outset, be aware that results from interactions with these Skills and agents are not deterministic because of how the models behave, but you can mitigate that with clear goals and validation checkpoints.

Not all models behave in the same way

Some interactive skills require Premium models for interactive use; otherwise they follow a fixed sequence of steps.

Limits of interactions with models

Models can generate code, but they cannot execute it against your local data. To bridge that gap, some Skills include scripts you run locally.

Contribute

See CONTRIBUTING.md for conventions, generator workflows, tests, and how to open a pull request.

Examples

The repository includes a collection of examples where you can explore what these Skills and workflows enable for Java.

Architecture Decision Records (ADR)

  • Review the ADR index for the complete list.

Changelog

Java JEPs from Java 8 onward

Java uses JEPs (JDK Enhancement Proposals) to describe new language and platform features. This repository tracks which JEPs could improve the Skills and guidance here.

Meetups, Conferences, Workshops & Articles

Codemotion / Madrid (2026/04/20 - 11:00 - 12:30)

W-JAX / Munich (2025/11/06 - 10:30 - 11:30)

Devoxx BE / Antwerp (2025/10/07 - 18:20 - 18:50)

Madrid Jug / Madrid (2025/05/06 - 19:00)

Blogs

References

Other developments

Powered by Cursor with ❤️ from Madrid