Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Fullstack Shipkit

    1

    Claude Code skills for planning a project, scaffolding a Go + React + PostgreSQL stack, verifying it end to end, and turning vague frontend tweaks into precise changes.

    $14.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    fullstack-shipkit

    fullstack-shipkit

    Example session with this skill installed

    Grill me on a new project for a real-time inventory tracker using the standard stack.

    • Read your context and instructions
    • Compiled the fullstack-shipkit

    I will now interview you to refine the plan for the real-time inventory tracker. I'll recommend defaults based on the Go + React stack to speed things up.

    Question: How should the system handle inventory updates from multiple sources simultaneously?

    I recommend: using a worker pattern via RabbitMQ for all updates, with Postgres row-level locking during the final write. This prevents race conditions when two sources update the same SKU at once.

    Next steps

    1. Confirm the concurrency strategy or suggest an alternative.
    2. Define the core entities (Products, Warehouses, StockLogs).
    3. Generate the CLAUDE.md and MVP plan.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Building and maintaining a Go + React stack manually is slow and error-prone. This skill package automates the planning, scaffolding, and verification of high-performance monorepos using Go (Fiber) and React (Next.js or Vite).

    What it does

    • Project grilling conducts a relentless interview to surface edge cases and resolve dependencies before writing code.
    • Stack scaffolding generates a complete Go monorepo with PostgreSQL, Redis, RabbitMQ, and JWT authentication.
    • Visual interpretation translates vague frontend requests like "make it pop" into precise CSS or Tailwind changes based on your theme.
    • End-to-end verification runs real smoke tests, migration loops, and log audits to prove the scaffold actually works.

    How it works

    1. Plan a new feature or project using the grill-me command to generate a consolidated design document and CLAUDE.md.
    2. Scaffold the architecture using stack-go-next-postgres to set up Fiber handlers, sqlc repositories, and TypeScript types.
    3. Verify the health of the system with verify-scaffold to run builds, migrations, and API smoke tests.

    Frameworks & tools

    Go (Fiber), React (Next.js or Vite), PostgreSQL (pgx/sqlc), Redis, RabbitMQ, Tailwind CSS, Docker Compose, and JWT.

    Why this beats prompting it yourself

    Generic prompts often result in mismatched frontend/backend types or forgotten Docker configurations. This skill enforces a consistent, production-ready directory structure and ensures every decision is logged and verified against a running environment.

    Use cases

    • Start a new Go + React project with a pre-configured monorepo and infra.
    • Add a new feature by grilling the requirements and updating the API and frontend in one go.
    • Audit a project scaffold to ensure migrations and workers are functioning correctly.
    • Refine UI layouts using natural language that maps to your existing design system.

    Known limitations

    Requires Docker for infrastructure verification. Only supports Go and React/TypeScript variants as defined in the stack conventions.

    Requires Docker for infra verification. Only supports Go (Fiber) and React/TypeScript (Next.js/Vite) variants. Manual tool installation (goose, sqlc) may be needed for full verification.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 21 days ago

    Requires

    Claude Code
    Git
    Go
    Node.js
    npm
    PostgreSQL
    Docker
    Docker Compose

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files
    Environment Variables

    Fullstack Shipkit is designed for developers using AI coding agents to plan, scaffold, and validate full-stack applications. Optimized for Claude Code, with potential compatibility across other AI agents supporting the SKILL.md format. The toolkit follows an opinionated stack built around Go, React, TypeScript, PostgreSQL, and Docker. Some skills require a local development environment and installed dependencies. AI-generated code should be reviewed and tested before production deployment. This is the community edition. Future premium versions may include advanced automation, additional integrations, and enhanced development workflows. Open-source project: https://github.com/pedrobertao/fullstack-shipkit

    Listed21 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the heavy lifting of building Go (Fiber) and React monorepos by conducting requirement 'grilling' sessions, scaffolding the full infrastructure (Postgres, RabbitMQ, Redis), and performing end-to-end verification to ensure the generated code actually runs.

    The skill is designed to work with advanced LLMs like Claude 3.5 Sonnet or GPT-4o and requires a local environment with Docker installed to perform its infrastructure verification and smoke test sequences.

    You receive the full set of automated commands (including planning, scaffolding, and verification tools), a standardized production-ready directory structure, and the logic for maintaining consistent types between your Go backend and React frontend.

    Unlike generic prompts that often hallucinate API signatures or miss Docker configurations, this skill enforces a strict, verified architecture using sqlc for type-safe database queries and automated 'grilling' to resolve edge cases before code is even written.

    Yes, while it's optimized for new projects, you can use the 'grill-me' and 'verify-scaffold' commands to plan and audit new features or infrastructure additions within an existing monorepo that follows the skill's stack conventions.

    Currently, the skill is strictly optimized for Go (Fiber) and React (Next.js/Vite) with PostgreSQL and RabbitMQ; it does not support other languages like Python or different database engines like MongoDB at this time.

    New in Agents & Orchestration