Development
create-spring-boot-java-project - Claude MCP Skill
Create a new Spring Boot Java project (Maven or Gradle) from start.spring.io with sensible defaults for configuration, PostgreSQL, logging, security, testing and Docker. Use when asked to scaffold, bootstrap or generate a Spring Boot application. Detects existing project versions and never upgrades implicitly.
SEO Guide: Enhance your AI agent with the create-spring-boot-java-project tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to create a new spring boot java project (maven or gradle) from start.spring.io with sensible defaults ... Download and configure this skill to unlock new capabilities for your AI workflow.
Documentation
SKILL.md# Create a Spring Boot Java project
Scaffold a Spring Boot application with [start.spring.io](https://start.spring.io), then apply a small set of opinionated defaults. Out of scope for now: front-ends (Vue/React/Angular), cloud deployment (Azure), Git setup, CRaC and AOT images.
## Step 0: Detect before you create
- If the working directory already contains a `pom.xml` or `build.gradle(.kts)`, this is an **existing project**: do not regenerate it. Read its Spring Boot, Java and test-framework versions and follow them. **Never upgrade versions implicitly**; propose an upgrade and wait for the user's decision.
- Check the tools: `java -version` (JDK matching the chosen Java version), `docker --version` (needed for Testcontainers and Compose). On the default path (current Boot via start.spring.io) Maven/Gradle need not be installed: the generated wrapper is used. The Boot 3.5 fallback needs Maven or Gradle installed once to create the wrapper (see [versions.md](references/versions.md)).
- Ask only for what is missing: project name, group id, package, build tool (default **Maven**), dependencies (default: web, actuator, validation, devtools; add `data-jpa`, `postgresql`, `security`, `docker-compose`, `testcontainers` when a database or auth is needed).
## Step 1: Resolve versions
Follow [references/versions.md](references/versions.md): query `https://start.spring.io/metadata/client` at run time for the latest stable Spring Boot release, fall back to the documented pinned values if offline. Do not hardcode `latest` anywhere.
## Step 2: Generate the project
Use the start.spring.io HTTP API with explicit, pinned parameters (no piped installers). Replace the values in capitals.
Maven:
```bash
curl -fsS https://start.spring.io/starter.zip \
-d type=maven-project -d language=java -d packaging=jar \
-d bootVersion=BOOT_VERSION -d javaVersion=JAVA_VERSION \
-d groupId=com.example -d artifactId=demo -d name=demo \
-d packageName=com.example.demo -d baseDir=demo \
-d dependencies=web,actuator,validation,devtools \
-o demo.zip && unzip -q demo.zip && rm demo.zip
```
Gradle: same command with `-d type=gradle-project` (Groovy DSL) or `-d type=gradle-project-kotlin` (Kotlin DSL; the language stays `java`).
Inspect the result (`ls demo`, read the build file) and make sure the wrapper (`mvnw` or `gradlew`) is executable. Add `-d dependencies=...,data-jpa,postgresql,docker-compose,testcontainers` for a database project.
## Step 3: Apply the defaults
| Area | What to do | Reference |
|------|-----------|-----------|
| Boot 3 vs 4 differences | Starter names, Jackson 3, test modules | [references/spring-boot-4.md](references/spring-boot-4.md) |
| Configuration | `application.properties` or `.yml` (match the project), profiles, `@ConfigurationProperties`, secrets via environment | [references/configuration.md](references/configuration.md) |
| Database | PostgreSQL, Hibernate settings, Compose for dev, Testcontainers for tests | [references/database.md](references/database.md) |
| Logging | SLF4J, parameterized messages, levels, structured logging | [references/logging.md](references/logging.md) |
| Security | Spring Security basics, secure defaults, Problem Details | [references/security.md](references/security.md) |
| Docker | JVM image and GraalVM native image Dockerfiles | [references/docker.md](references/docker.md) |
| Testing | See the `spring-boot-testing` skill (slices, Testcontainers, Failsafe) | `skills/spring-boot-testing` |
| Best practices | See the `java-springboot` skill and `instructions/springboot.instructions.md` | `skills/java-springboot` |
Keep dotfiles minimal: a `.gitignore` covering `target/`, `build/`, `.gradle/`, IDE folders and `.env`; never commit `.env` (commit a `.env.sample`).
## Step 4: Verify
1. Build and test: `./mvnw verify` (Maven) or `./gradlew build` (Gradle).
2. Run: `./mvnw spring-boot:run` or `./gradlew bootRun`, then `curl -fsS localhost:8080/actuator/health` must return `{"status":"UP"}`.
3. Report the chosen versions and anything that was skipped or deferred.
## Provenance
Adapted from the Apache-2.0 skill [jdubois/dr-jskill](https://github.com/jdubois/dr-jskill); see [references/PROVENANCE.md](references/PROVENANCE.md).Signals
Information
- Repository
- github/awesome-copilot
- Author
- github
- Last Sync
- 11/2/2026
- Repo Updated
- 11/2/2026
- Created
- 2/25/2026
Reviews (0)
No reviews yet. Be the first to review this skill!
Related Skills
CLAUDE
Claude-Mem: AI Development Instructions
cursorrules
CrewAI Development Rules
firecrawl-build-onboarding
Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.
firecrawl-build
Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.
Related Guides
Bear Notes Claude Skill: Your AI-Powered Note-Taking Assistant
Learn how to use the bear-notes Claude skill. Complete guide with installation instructions and examples.
Mastering tmux with Claude: A Complete Guide to the tmux Claude Skill
Learn how to use the tmux Claude skill. Complete guide with installation instructions and examples.
OpenAI Whisper API Claude Skill: Complete Guide to AI-Powered Audio Transcription
Learn how to use the openai-whisper-api Claude skill. Complete guide with installation instructions and examples.