Pipzzter

Storeforge — AI skill for Claude Code

AI community

Multi-agent AI that turns a founder’s idea into an e-commerce launch plan, sourced products, and Shopify store code.

How to install Storeforge

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Pipzzter/storeforge and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Storeforge does

Multi-agent AI that turns a founder’s idea into an e-commerce launch plan, sourced products, and Shopify store code. Built with LangGraph, Claude, and Grok.

Alternatives in AI

  • LLM For Zotero — An open-sourced research agent system deeply rooted in your Zotero library 2.8k ★
  • Ooda Subagents — OODA Loop AI Agents - Observe, Orient, Decide, Act framework for systematic problem-solving 170 ★
  • Paperclip Vision — A Claude Code skill that interviews your founder and writes the constitution your AI company needs to run itse 77 ★

README

StoreForge AI logo

StoreForge AI

Type one prompt, get a store.

For founders turning an idea into an e-commerce business,
with AI-generated strategy, product sourcing, and Shopify store-creation code.

▶ Try the demo — no API keys required

What it does · Who it's for · Run it · Demo · How the AI works · Finished & not · How it's built · Tests


What it does

StoreForge AI turns a founder's five-question intake into a complete, dashboard-ready store plan: a 7-day go-to-market strategy, a curated line of profitable products, and the Shopify store-creation code to launch them. It is a multi-agent **LangGraph** backend that routes work across specialized AI agents, with per-agent model routing (Grok + Claude), automatic retry/fallback, Pydantic-validated output, and Postgres checkpointing so an interrupted run resumes from its last step. A small standalone frontend renders any run so you can *see* what the agents produced.

A founder answers five questions (niche, audience, price range, ad budget, product preference). The pipeline then runs:

START
  → parse_prompt   extract intent + build the task list
  → plan           7-day GTM strategy, revenue goals, competitors, ad channels   (Planner)
  → source         live web research → products with cost, margin, supplier      (Sourcer)
  → code           Shopify GraphQL mutations + storefront code                   (Coder)
  → market         [roadmap]
  → optimize + support   [roadmap, parallel]
  → validate_output   schema validation + budg