Skip to content

eldermoraes/quarkus-agentic-scaffolding / skills/scaffold-project

scaffold-project

Verified

Scaffold 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.

templates/McpServer.java.template

View on GitHub
package org.acme.mcp;

import org.acme.tools.TicketTools;

import io.quarkiverse.mcp.server.Tool;
import io.quarkiverse.mcp.server.ToolArg;
import io.smallrye.common.annotation.RunOnVirtualThread;
import jakarta.inject.Inject;

/*
 * MCP server — offers this application's capabilities as MCP tools that an MCP-capable
 * agent (Claude Code, an IDE, another Quarkus app via quarkus-langchain4j-mcp) can call.
 * In production, restrict access to trusted, authorized clients — put the /mcp endpoint
 * behind the application's normal access layer (HTTP auth policies or a gateway).
 * Requires the mcp-server-http extension (io.quarkiverse.mcp — managed by the platform's
 * quarkus-mcp-server-bom, so NO version pin). Streamable HTTP endpoint: /mcp by default
 * (quarkus.mcp.server.http.root-path; see application.properties.template). Use the
 * mcp-server-stdio extension instead when a desktop client should spawn the app directly.
 *
 * Two different @Tool annotations exist in this stack — do not mix them up:
 *   io.quarkiverse.mcp.server.Tool   offers a method to REMOTE MCP clients (this file);
 *   dev.langchain4j.agent.tool.Tool  offers a method to the application's own AI services
 *                                    (Tools.java.template).
 * The MCP server extension (mcp-server-http or mcp-server-stdio) also publishes every
 * dev.langchain4j @Tool method as an MCP tool unless
 * quarkus.mcp.server.support-langchain4j-annotations=false. The properties baseline carries
 * that line, commented, in its MCP server block: uncomment it with the rest of the block
 * (build-time setting, unscoped). With it, the server serves only the methods in this file.
 * To offer a LangChain4j tool over MCP, opt in per method as below: an MCP @Tool that
 * delegates to the TicketTools bean, so one implementation backs both. Setting the property
 * to true instead publishes ALL LangChain4j tools of the application.
 *
 * The declaring type is turned into a CDI bean automatically; @Inject works as usual.
 * @Prompt and @Resource (same package) expose reusable prompts and data the same way.
 */
public class TriageMcpServer {

    @Inject
    TicketTools tickets;

    @Tool(description = "Looks up a customer's support context: plan and open-ticket count")
    @RunOnVirtualThread // blocking lookup: keep it off the event loop and off the worker pool
                        // (project conventions section 2)
    public String customerContext(
            @ToolArg(description = "The customer id") String customerId) {
        TicketTools.CustomerContext ctx = tickets.lookupCustomer(customerId);
        return "plan=%s openTickets=%d".formatted(ctx.plan(), ctx.openTickets());
    }
}
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 119kUpdated Claude CodeCodexVerifiedInstall
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: 118kUpdated Claude CodeCodexVerifiedInstall