decebals/claude-code-java

Reusable AI development infrastructure for Java projects, optimized for Claude Code

What it solves

It provides a standardized way to give AI agents domain-specific knowledge and structured workflows for Java development. It solves the problem of inconsistent AI assistance by providing a library of reusable "skills" that ensure the agent follows specific patterns for code reviews, architecture decisions, and framework-specific tasks (like Spring Boot or JPA).

How it works

The project consists of a collection of skills—structured markdown files that follow the open Agent Skills specification. These files provide the AI agent with the necessary context and instructions to perform specific tasks. Developers can install these skills into their projects using a CLI tool or setup scripts, allowing agents (specifically tested with Claude Code) to automatically load the relevant skill based on the user's prompt.

Who it’s for

Java developers using AI agents (such as Claude Code) who want high-quality, reproducible assistance for Maven-based projects, ranging from routine git commits to complex security audits and architecture reviews.

Highlights

  • 18 Specialized Skills: Covers workflows (git-commit, changelog), code quality (security audit, concurrency review), architecture (SOLID, design patterns), and frameworks (Spring Boot, JPA).
  • Spec Compliant: Follows the open Agent Skills specification and validates skills in CI to ensure compatibility.
  • Routing Validation: Includes scripts to test that the agent correctly selects the right skill based on the prompt description.
  • Token Efficiency: Designed to reduce the number of iterations and lower token usage compared to manual prompting.
  • Integration Ready: Includes templates for CLAUDE.md and MCP server configurations to streamline agent setup.

Related

  • Project
    michaelshimeles/skills

    A curated set of Claude Code agent skills that automate common development tasks—visual diff generation, service‑layer structuring, evidence‑driven UI testing, iterative Greptile review loops, work‑tree isolation, and prose clean‑up—plus a ready‑to‑drop workflow tying them together.

  • Project
    KKKKhazix/khazix-skills

    A collection of structured instruction sets for AI agents that provide specialized workflows for goal setting, disk cleanup, research, and writing, following the Agent Skills open standard.

  • Project
    mizchi/skills

    A collection of standardized, portable skills for AI coding agents, covering tasks from frontend review to cloud infrastructure, supported by an evaluation CLI for testing and iteration.

  • Project
    amd/skills

    AMD Skills is a catalog of reusable, agent‑compatible “skills” that encode AMD‑specific AI workflow knowledge (ROCm diagnostics, Quark quantisation, LLM serving on Instinct/EPYC, etc.). Install via the `skills` CLI (`npx skills add amd/skills`) or manually, then invoke the skills through coding assistants like Cursor, Claude Code, Codex or Gemini. Each skill bundles a `SKILL.md` description, optional scripts and references, enabling agents to automatically perform setup, optimisation and debugging steps for AMD hardware.

  • Project
    levnikolaevich/claude-code-skills

    A collection of standalone agent skills and plugins for Claude Code and OpenAI Codex that provide structured, professional engineering workflows across the entire software development lifecycle.