← 开源
decebals

claude-code-java

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

AI EngineeringGive agent toolsGive agent knowledgeShell
在 GitHub 打开
增长势头
+224 小时新增 Star+0.3%
753
Star
154
Fork
+2
本周
1
贡献者
创建于 2026-01-30 · 更新于 2026-10-15 · 今日第 4138 名
主要开发者
decebals

decebals/claude-code-java 排名第 4,138,有 753 个星标。

同类别比较

decebals/claude-code-java 排名第 4,138,此处有 8 个同类条目;getagentseal/founder-playbook 排名第 4,136。

同类别比较
名称排名指标
codewithmukesh/dotnet-claude-kit4,128
语言:
C#
星标数:
765
分叉数:
173
简介:
Make Claude Code a .NET 10 Expert
zarazhangrui/beautiful-feishu-whiteboard4,130
语言:
Shell
星标数:
765
分叉数:
51
简介:
35 curated colour palette styles for building beautiful, editable Feishu / Lark (飞书) whiteboards. An agent skill.
WantongC/journal-adapt-writing-skill4,132
星标数:
761
分叉数:
46
getagentseal/founder-playbook4,136
星标数:
754
分叉数:
152
简介:
15 proven business books distilled into AI-native skills. Works with Claude Code, ChatGPT, Gemini, Cursor.
allenai/reward-bench4,140
语言:
Python
星标数:
748
分叉数:
104
简介:
RewardBench: the first evaluation tool for reward models.
keli-wen/agy-staff4,144
语言:
JavaScript
星标数:
744
分叉数:
54
简介:
Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code and OpenAI Codex.
Future-House/robin4,145
语言:
Python
星标数:
743
分叉数:
123
简介:
Robin: A multi-agent system for automating scientific discovery
AgentSmithers/x64DbgMCPServer4,150
语言:
C#
星标数:
735
分叉数:
105
简介:
x64DbgMCPServer made from c# with Claude, Windsurf and Cursor support
关键参数与规格
关键参数与规格
参数值
语言Shell
类别AI Engineering
子类别Give agent tools,Give agent knowledge
关键词Agent-ready APIs, Coding, MCP, System prompts
星标数753
分叉数154
贡献者1
创建日期2026-01-30
更新日期2026-10-15
1 天星标数2
7 天星标数2
排名4,138
上次排名6,486
排名变化2,348
7 天星标排名8,528
上次 7 天星标排名14,373
7 天星标排名变化5,845
总星标排名14,028
上次总星标排名14,030
总星标排名变化2
国家Romania
README 摘录

claude-code-java Agent Skills for Java projects, following the open Agent Skills specification *This project is not affiliated with Anthropic. A collection of reusable **skills** (structured markdown files that give an AI agent domain knowledge and workflows), plus project templates, MCP server configurations, and setup scripts. The skills follow the Agent Skills specification, an open format read by a growing number of agents. They are developed and tested with Claude Code, and every skill is validated against the spec

in CI. ** Java developers who want consistent, high-quality AI assistance for common tasks like code reviews, testing, commits, and architecture decisions. Routing is tested An agent picks a skill from its name and description and nothing else. With eighteen of them the descriptions compete, and the failure is quiet: the wrong skill loads and answers plausibly anyway, so nobody notices. runs a set of prompts against the same list an agent receives and reports where one lands somewhere other

than expected. It found a real defect the first time it ran: "this class does too much, split it" reached rather than . Sharpening three descriptions took the set from 17 of 18 prompts routed correctly to 20 of 20. Every skill has at least one case, enforced by so the cases cannot fall behind the skills. The check runs against any OpenAI-compatible endpoint, including a local model. Purpose AI-powered development workflows with focus on: **Token efficiency** - Designed for

fewer iterations and lower token usage **Reproducible patterns** - Reusable workflows across projects **Java ecosystem** - Tailored for Java/Maven development **Incremental adoption** - Start small, expand as needed Quick Start Skills only No clone, no setup script. Add to see the skills first, to install only some of them, to install at user level instead of the current project, or to get files instead of symlinks. For the skills plus generation, MCP configuration and project settings, continue below. Setup your Java project

This creates with symlinked skills, generates , and configures settings. ** Just copy or symlink the skills you want: 3. Use with Claude Code Available Skills (18) Skills are automatically loaded by Claude Code based on context. md for full documentation and docs/SCRIPTS. **Start Claude Code** in project directory 3. **Load skill** relevant to current task 4. **Execute workflow** with natural language 5. **Measure results** (tokens used, time saved) Success Metrics Track these to validate effectiveness: **Token reduction**: Track your improvement

vs manual workflows **Time savings**: Measure before/after per task **Reusability**: Number of projects using skills **Quality**: Code review feedback, test coverage Requirements An agent that reads Agent Skills. Contributing Skills are evolving based on real-world usage. Try them, open issues, share what works. Share token savings/improvements Documentation See docs/ for detailed guides: DESIGN_PRINCIPLES. md - Warning signs to watch for SKILL_GUIDELINES. md - How to create new skills RELEASING. md - Versioning and how a release is cut

License MIT License - Use freely, modify as needed.

常见问题

记录了多少星标和分叉?

decebals/claude-code-java 有 753 个星标和 154 个分叉。

仓库排名是多少?

decebals/claude-code-java 排名第 4,138。

记录的语言和类别是什么?

decebals/claude-code-java 有 753 个星标,语言为 Shell,类别为 AI Engineering。

哪个仓库排名最接近?

decebals/claude-code-java 与 getagentseal/founder-playbook 比较,后者排名第 4,136,有 754 个星标。

README

claude-code-java

Agent Skills for Java projects, following the open Agent Skills specification

This project is not affiliated with Anthropic.

What is this?

A collection of reusable skills (structured markdown files that give an AI agent domain knowledge and workflows), plus project templates, MCP server configurations, and setup scripts.

The skills follow the Agent Skills specification, an open format read by a growing number of agents. They are developed and tested with Claude Code, and every skill is validated against the spec in CI.

Who is this for? Java developers who want consistent, high-quality AI assistance for common tasks like code reviews, testing, commits, and architecture decisions.

Routing is tested

An agent picks a skill from its name and description and nothing else. With eighteen of them the descriptions compete, and the failure is quiet: the wrong skill loads and answers plausibly anyway, so nobody notices.

scripts/eval-routing.sh runs a set of prompts against the same list an agent receives and reports where one lands somewhere other than expected. It found a real defect the first time it ran: "this class does too much, split it" reached clean-code rather than solid-principles. Sharpening three descriptions took the set from 17 of 18 prompts routed correctly to 20 of 20.

Every skill has at least one case, enforced by scripts/validate-skills.sh so the cases cannot fall behind the skills. The check runs against any OpenAI-compatible endpoint, including a local model. See docs/SCRIPTS.md.

Purpose

AI-powered development workflows with focus on:

  • Token efficiency - Designed for fewer iterations and lower token usage
  • Reproducible patterns - Reusable workflows across projects
  • Java ecosystem - Tailored for Java/Maven development
  • Incremental adoption - Start small, expand as needed

Quick Start

Skills only

npx skills@latest add decebals/claude-code-java

No clone, no setup script. Add --list to see the skills first, --skill to install only some of them, --global to install at user level instead of the current project, or --copy to get files instead of symlinks.

For the skills plus CLAUDE.md generation, MCP configuration and project settings, continue below.

1. Clone this workspace

git clone https://github.com/decebals/claude-code-java.git ~/projects/claude-code-java
cd ~/projects/claude-code-java
chmod +x scripts/*.sh

2. Setup your Java project

./scripts/setup-project.sh ~/projects/your-java-project

This creates .claude/ with symlinked skills, generates CLAUDE.md, and configures settings.

Prefer manual setup? Just copy or symlink the skills you want:

mkdir -p your-project/.claude/skills

# Copy specific skills
cp -r ~/projects/claude-code-java/skills/java-code-review your-project/.claude/skills/

# Or symlink all skills
ln -s ~/projects/claude-code-java/skills/* your-project/.claude/skills/

3. Use with Claude Code

cd ~/projects/your-java-project
claude

# Skills load automatically based on context, or invoke directly:
> /git-commit
> /java-code-review

Available Skills (18)

Skills are automatically loaded by Claude Code based on context.

Workflow

Skill Trigger Examples
git-commit "commit these changes", "create commit"
changelog-generator "generate changelog", "what changed since release"
issue-triage "triage issues", "check open issues"

Code Quality

Skill Trigger Examples
java-code-review "review this code", "check this PR"
api-contract-review "review API", "check REST endpoints"
concurrency-review "check thread safety", "review async code"
performance-smell-detection "check performance", "find slow code"
test-quality "add tests", "improve coverage"
maven-dependency-audit "check dependencies", "audit deps"
security-audit "security review", "check OWASP", "vulnerabilities"

Architecture & Design

Skill Trigger Examples
architecture-review "review architecture", "check package structure"
solid-principles "check SOLID", "single responsibility"
design-patterns "use factory pattern", "implement strategy"
clean-code "clean this code", "refactor"

Framework & Data

Skill Trigger Examples
spring-boot-patterns "create controller", "Spring Boot help"
java-migration "upgrade to Java 21", "migrate from Java 8"
jpa-patterns "N+1 problem", "LazyInitializationException"
logging-patterns "add logging", "debug this flow", "analyze logs"

See skills/README.md for full documentation and docs/SCRIPTS.md for setup script options.

Project Structure

claude-code-java/
├── README.md                    # This file
├── LICENSE                      # MIT license
├── .gitignore                   # Git ignore rules
├── .claude/
│   └── skills/                  # 18 reusable skills (see Available Skills above)
├── docs/                        # Guidelines and best practices
│   ├── DESIGN_PRINCIPLES.md     # Core philosophy
│   ├── RED_FLAGS.md             # Warning signs to watch for
│   ├── SAFE_WORKFLOWS.md        # Step-by-step safe workflows
│   ├── SCRIPTS.md               # Scripts documentation
│   ├── SKILL_GUIDELINES.md      # How to create new skills
│   └── TESTING.md               # Testing strategy
├── templates/
│   ├── CLAUDE.md.template       # Template for projects
│   ├── mcp-config.json.template # MCP configuration template
│   ├── MCP_CONFIG.md.template   # MCP documentation template
│   └── settings.json.template   # Claude Code settings (pre-approved commands)
└── scripts/
    ├── setup-project.sh         # Full project setup (orchestrator)
    ├── link-skills.sh           # Symlink skills to project
    ├── generate-claude-md.sh    # Generate CLAUDE.md
    ├── configure-mcp.sh         # Configure MCP servers
    └── test-all.sh              # Run all tests

Typical Workflow

  1. Link skills to your Java project
  2. Start Claude Code in project directory
  3. Load skill relevant to current task
  4. Execute workflow with natural language
  5. Measure results (tokens used, time saved)

Success Metrics

Track these to validate effectiveness:

  • Token reduction: Track your improvement vs manual workflows
  • Time savings: Measure before/after per task
  • Reusability: Number of projects using skills
  • Quality: Code review feedback, test coverage

Requirements

  • An agent that reads Agent Skills. Developed and tested with the Claude Code CLI
  • Java 11+ projects (Java 17+ recommended)
  • Git for version control
  • Maven or Gradle build tool
  • (Optional) GitHub MCP server for issue management

What's Included

  • 18 skills (workflow, code quality, architecture, frameworks)
  • Setup automation scripts
  • Project templates
  • Agent Skills spec compliance, enforced in CI by scripts/validate-skills.sh and the reference validator

Used in automated code review

These skills are not just for code generation — they are also used as the single source of truth for automated code review via skill-review, a reusable GitHub Actions workflow that evaluates pull requests against the same skills that Claude Code uses during development.

Same skills. From generation to review. See skill-review-sandbox for a working example.

Contributing

Skills are evolving based on real-world usage. Try them, open issues, share what works.

  1. Try the skills in your projects
  2. Open issues for suggestions
  3. Share token savings/improvements

Documentation

See docs/ for detailed guides:

License

MIT License - Use freely, modify as needed.

排名相邻
同类项目