eldermoraes/quarkus-agentic-scaffolding / skills/scaffold-project
scaffold-project
VerifiedScaffold Quarkus + LangChain4j projects end-to-end and add agentic components to existing ones — AI services, tools, agents and multi-agent workflows, RAG pipelines, MCP clients and servers (Model Context Protocol), guardrails, and embedding store setups. Use this whenever the user wants a new Quarkus + LangChain4j project or module created, or an agentic component added to an existing project in this stack, including a baseline pom.xml, application.properties, project layout, or starter classes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 20.9 KB |
| agents/openai.yaml | config | 669 B |
| templates/Agent.java.template | other | 28.4 KB |
| templates/AiService.java.template | other | 6.1 KB |
| templates/AiServiceTest.java.template | other | 6.2 KB |
| templates/ApplicationIT.java.template | other | 2.7 KB |
| templates/Guardrails.java.template | other | 4.5 KB |
| templates/McpClient.java.template | other | 2.5 KB |
| templates/McpServer.java.template | other | 2.6 KB |
| templates/RagSetup.java.template | other | 9.1 KB |
| templates/RestResource.java.template | other | 3.1 KB |
| templates/Tools.java.template | other | 2.3 KB |
| templates/application.properties.template | other | 12.6 KB |
| templates/pom.xml.template | other | 7.6 KB |
templates/pom.xml.template
View on GitHub<?xml version="1.0" encoding="UTF-8"?>
<!--
Quarkus + LangChain4j — DEPENDENCY REFERENCE (this is NOT a full pom.xml).
The project SHELL — the full pom.xml: the quarkus-bom + quarkus-langchain4j-bom platform BOMs,
the build plugins, the `-parameters` compiler flag (parameter-name retention), the `native`
profile, the test stack, and every version pin — is generated, already up to date, by the
Quarkus Agents MCP `quarkus_create` (the same codestart generator that powers code.quarkus.io).
It is intentionally NOT hand-maintained here: a pinned copy only drifts (in v0.5.0 the baseline
had already fallen behind the live platform).
So this file keeps only what a project generator does NOT give you: the extensions to ask
for (1), the non-extension dependencies (2) and the native-profile additions for Easy RAG (3).
The <project> element below only groups them; copy each part to the same place in the
generated pom.xml.
==========================================================================
1. Extensions to pass to quarkus_create (resolved against the current platform BOM)
==========================================================================
core: rest, rest-jackson, smallrye-openapi, websockets-next, langchain4j-ollama
agents: + langchain4j-agentic (declarative LangChain4j Agentic workflows)
RAG: + langchain4j-easy-rag (Easy RAG)
MCP client: + langchain4j-mcp (consume tools from remote MCP servers)
MCP server: + mcp-server-http (expose this app as an MCP server; stdio variant: mcp-server-stdio)
observability: + micrometer-registry-prometheus, opentelemetry (optional; see application.properties.template)
fault tolerance: + smallrye-fault-tolerance (optional; MicroProfile FT on AI-service methods)
error contract: + http-problem (optional; io.quarkiverse.httpproblem; RFC 9457 problem+json at the REST edge)
agent skills: + langchain4j-skills (optional; loads SKILL.md-format skills at runtime; status:preview)
All of the above are platform extensions: quarkus_create resolves them and the BOMs manage
their versions, so none of them belongs in the <dependencies> below and none takes a <version>.
(http-problem joined io.quarkus.platform:quarkus-bom in 3.38.0 — the extension's own README
still says otherwise, but the BOM on Maven Central is authoritative.)
quarkus-arc, quarkus-junit and rest-assured are pulled in automatically — do not list them.
==========================================================================
2. Non-extension dependencies the generator does NOT add — paste into <dependencies>
==========================================================================
Most live under the dev.langchain4j group (they are libraries, not Quarkus extensions); the
test-scoped eval artifact is a quarkiverse module the generator likewise omits. Neither
quarkus_create nor code.quarkus.io will add any of them, and their versions are managed by
quarkus-langchain4j-bom, so they take NO <version>. Add each only when its feature is used
(output guardrails, RAG embedding model, PDF parsing, AI-quality evals).
==========================================================================
3. Native profile additions — paste into the generated `native` profile, Easy RAG projects only
==========================================================================
See the <profiles> part at the end of this file: its <dependencies> and <build> go into the
generated `native` profile; with them `mvn verify -Dnative` builds the executable and runs the
native integration tests with no extra argument.
-->
<project>
<dependencies>
<!-- agents: CompleteAnswerGuard extends dev.langchain4j.guardrails.JsonExtractorOutputGuardrail
(the copy in langchain4j-core is deprecated for removal and gone from LangChain4j 1.20) -->
<dependency>
<groupId>dev.langchain4j</groupId>
<artifactId>langchain4j-guardrails</artifactId>
</dependency>
<!-- RAG: in-process embedding model required by Easy RAG -->
<dependency>
<groupId>dev.langchain4j</groupId>
<artifactId>langchain4j-embeddings-bge-small-en-v15-q</artifactId>
</dependency>
<!-- RAG: add only if ingesting PDFs -->
<dependency>
<groupId>dev.langchain4j</groupId>
<artifactId>langchain4j-document-parser-apache-pdfbox</artifactId>
</dependency>
<!-- testing: AI-quality evals (Scorer/@EvaluationTest) -->
<dependency>
<groupId>io.quarkiverse.langchain4j</groupId>
<artifactId>quarkus-langchain4j-testing-evaluation-junit5</artifactId>
<scope>test</scope>
</dependency>
</dependencies>
<profiles>
<profile>
<id>native</id>
<!-- Easy RAG in a native build (add only with the easy-rag extension). Two parts:
1. The dependency re-declares Easy RAG for the native profile only, without the
Apache Tika document parser, which did not build natively as shipped (seen on
macOS arm64, GraalVM 25.0.2, platform 3.40.1.2; see RagSetup.java.template,
"NATIVE BUILDS"). LangChain4j then reads documents with its plain-text parser:
the native executable ingests text and Markdown, not PDF or Office files. The JVM
build keeps Tika. Each exclusion was shown necessary by a native build without it.
2. The failsafe configuration sets the two environment variables the native
executable needs to find its documents, because Easy RAG's classpath loader fails
in a native image: filesystem path type, and the absolute path of the project's
rag folder. The executable that `mvn verify -Dnative` starts inherits them. An
environment variable is passed as is, so a project path containing spaces works.
Outside the test, set the same two variables yourself (RagSetup.java.template). -->
<dependencies>
<dependency>
<groupId>io.quarkiverse.langchain4j</groupId>
<artifactId>quarkus-langchain4j-easy-rag</artifactId>
<exclusions>
<!-- the Tika parser itself: without this exclusion the build failed on
jakarta/mail/MessagingException -->
<exclusion>
<groupId>dev.langchain4j</groupId>
<artifactId>langchain4j-document-parser-apache-tika</artifactId>
</exclusion>
<!-- the parsers' build steps, which pull in the POI and AWT extensions: without
this exclusion the macOS build stopped on AWT -->
<exclusion>
<groupId>io.quarkiverse.langchain4j</groupId>
<artifactId>quarkus-langchain4j-parsers-base-deployment</artifactId>
</exclusion>
</exclusions>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<artifactId>maven-failsafe-plugin</artifactId>
<configuration>
<environmentVariables>
<QUARKUS_LANGCHAIN4J_EASY_RAG_PATH_TYPE>filesystem</QUARKUS_LANGCHAIN4J_EASY_RAG_PATH_TYPE>
<QUARKUS_LANGCHAIN4J_EASY_RAG_PATH>${project.basedir}/src/main/resources/rag</QUARKUS_LANGCHAIN4J_EASY_RAG_PATH>
</environmentVariables>
</configuration>
</plugin>
</plugins>
</build>
</profile>
</profiles>
</project>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |