Describe your app in plain English — Shipwright builds, tests, and deploys it autonomously via a 9-phase pipeline.

1 Skills

4 Commands

MIT License

$undefined undefined/undefined Pricing

Installation

Open Claude Code and run this command:

/plugin install shipwright@claude-code-plugins-plus

Use --global to install for all projects, or --project for current project only.

What It Does

Describe your app in plain English — Shipwright builds, tests, and deploys it autonomously via a 9-phase pipeline. Powered by product-agent on PyPI.

Skills (1)

shipwright-pipeline SKILL.md View full skill →

Autonomous app builder that converts plain-English descriptions into fully built, tested applications.

ReadWriteEditGrepGlobBash(pip:*)Bash(python:*)Bash(npm:*)Bash(npx:*)Bash(git:*)

Shipwright Pipeline

Overview

Shipwright converts a plain-English app description into a fully built, tested, and deployment-ready application. It delegates execution to product-agent, an autonomous 9-phase build engine available on PyPI.

Prerequisites

Python 3.10+ available in PATH.
product-agent installed (pip install product-agent).
Node.js 18+ for JavaScript/TypeScript stacks.

Supported Stacks

Next.js + Supabase — Full-stack with auth, database, and edge functions
Next.js + Prisma — Full-stack with type-safe ORM
SvelteKit — Lightweight full-stack with Svelte
Astro — Content-focused static and hybrid sites

Instructions

Gather the app description from the user. Ask clarifying questions if the description is vague.
Confirm the target stack. If none specified, recommend based on the app type:

Data-heavy with auth: Next.js + Supabase
API-first with complex models: Next.js + Prisma
Lightweight interactive: SvelteKit
Content or marketing site: Astro

Run product-agent with the app description and selected stack.
Monitor the 9-phase pipeline: Intake, Architecture, Scaffold, Implement, Test, Integrate, Polish, Validate, Ship.
Report results to the user including test summary and any warnings.

Output

A complete, buildable project directory with all source code, tests, and configuration.
A test report summarizing pass/fail counts.
Build verification output confirming the project compiles and starts.

Error Handling

If product-agent is not installed, prompt the user to install it with pip install product-agent.
If a phase fails, report the phase name, error message, and suggested fix.
If the selected stack is not supported, list available stacks and ask the user to choose.

Examples

Build a SaaS dashboard:


/shipwright-build Build a real-time analytics dashboard with user auth, team workspaces, and Stripe billing. Use Next.js + Supabase.

Add features to an existing project:


/shipwright-enhance Add dark mode toggle, export-to-CSV on all tables, and email notification preferences.

Scaffold a content site:


/shipwright-build Create a developer documentation site with search, versioned docs, and a blog. Use Astro.

Resources



      
      
          How It Works
          
Install the build engine:


pip install product-agent


Use the skills:


/shipwright-build — Build a new app from a plain-English description
/shipwright-enhance — Add features to an existing Shipwright project
/shipwright-stacks — List supported tech stacks
/shipwright-projects — List and manage existing Shipwright projects

        

      
      

      
      

      
      
  Ready to use shipwright?
  
    
    
        
        View on GitHub
      
  




      
      
          Related Plugins
          
            
                discovery-questionnaire
                Generate custom discovery questionnaires for AI agency prospects
              
                make-scenario-builder
                Create Make.com (Integromat) scenarios with AI assistance
              
                n8n-workflow-designer
                Design complex n8n workflows with AI assistance - loops, branching, error handling
              
                roi-calculator
                Calculate and present ROI for AI automation projects
              
                sow-generator
                Generate professional Statements of Work for AI projects
              
                tonone
                23-agent AI team for software teams: 15 engineering specialists (Apex, Forge, Relay, Spine, Flux, Warden, Vigil, Prism, Cortex, Touch, Volt, Atlas, Lens, Proof, Pave) + 8 product agents (Helm, Echo, Lumen, Draft, Form, Crest, Pitch, Surge) with a formal Helm→Apex handoff interface and 125 skills.
              
          
        

      
      
          Tags
          
            app-buildercode-generatorautonomous-agentpipelinenextjssupabasesveltekitastroai-agency