Jakeschincariol/founder-skill

Eleven free Claude skills that test a business before you launch it: a board trained on Hormozi, Thiel and Jobs, a marketing director, a CFO, and a consumer panel of 100 buyer agents. Free, MIT.

What it solves

It helps entrepreneurs validate and test a business idea before launching it, reducing the risk of spending money on a failing concept. It provides a structured way to analyze market fit, pricing, unit economics, and operational risks using AI-driven simulations.

How it works

The project consists of eleven "skills" (specialized prompts and Python tools) designed for Claude. These skills work sequentially, reading and writing data to a local founder/ folder to build a comprehensive business plan. The process includes:

  • Strategic Analysis: A simulated board of directors scores the idea based on established business frameworks.
  • Market Research: A competitor scout maps existing rivals and their weaknesses using public sources.
  • Consumer Simulation: A "Consumer Panel" spins up 100 buyer agents with unique personas to test objections and buy rates.
  • Financial Modeling: Python tools calculate unit economics, break-even points, and year-one profit margins.
  • Execution Planning: Specialized roles create marketing campaigns, brand identities, operational routines, and launch schedules.

Who it’s for

Founders and entrepreneurs who want to stress-test their business hypotheses and create a data-backed launch plan without needing an expensive consultancy.

Highlights

  • Buyer Swarms: Simulates 100 distinct buyer agents to identify customer objections and test pricing.
  • Financial Rigor: Uses standard-library Python scripts for precise unit economics and Van Westendorp pricing analysis.
  • Framework-Driven: Applies logic from known business strategies (e.g., $100M Offers, Zero to One) via sub-agents.
  • Zero-Config: Requires no API keys or signups; it runs directly as Claude skills or via Python.

Related

  • Project
    Anil-matcha/open-agent-email

    Open Agent Email is a self‑hosted service that gives each AI agent a real email address and mailbox. It handles inbound SMTP, stores messages, and lets agents read, reply, forward, schedule, or request human approval before sending. Accessible via REST, Python/TypeScript SDKs, CLI, WebSocket, webhooks, and MCP. Features include per‑agent inboxes, thread view, SPF/DKIM/DMARC validation, prompt‑injection screening, approval gate, any SMTP relay, delivery tracking, signed webhooks, and a Next.js dashboard. Built with Python/FastAPI, SQLite/PostgreSQL, and Docker; Apache‑2.0 licensed.

  • Project
    ShenSeanChen/waku-agent

    A local-first personal AI assistant with a transparent, lightweight codebase that implements core agent pillars like memory, loops, and evaluation.

  • Project
    chatmcp/mcpso

    MCP Directory is an open-source web app that lists awesome MCP servers, offering a searchable catalog plus instructions to self-host your own instance via Next.js and Supabase.

  • Project
    Leanmcp/gateway-skills

    An AI gateway proxy that provides full visibility into the requests, file access, and token costs of AI coding agents like Claude Code.