#138138th of 153 in Agent frameworks and SDKs

founder-skill

Eleven Claude skills that test a business idea before launch

Stars
4.1k
License
MIT
Last commit
Oct 2026
Language
Python
Stars, last 5 weeks+3,438
10 Oct 2026: 619 stars17 Oct 2026: 1,292 stars24 Oct 2026: 2,037 stars31 Oct 2026: 2,647 stars7 Nov 2026: 3,049 stars14 Nov 2026: 4,057 stars

619 on 10 Oct 20264,057 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

A set of eleven Claude skills (board, competitors, consumer panel, pricing, offer, CFO, marketing, brand, ops, launch, plan) that run in sequence and share files in a `founder/` folder. Four standard-library Python tools handle unit economics, persona dealing, Van Westendorp pricing and plan compilation. The consumer panel uses simulated buyer agents, and the README says to treat its buy rate as an upper bound.

Who it is for: Founders validating a business idea with Claude Code before spending money

Strengths

  • Python tools use only the standard library and make no network calls
  • Plan verdict is computed from the numbers, not written by the model
  • Same seed gives the same persona cards from the panel tool
  • Works as a Claude Code plugin, copied folders, or a pasted SKILL.md

Weaknesses

  • Simulated buyers lean agreeable, so panel buy rates overstate real demand
  • Sub-agents and Python tools need Claude Code; pasted SKILL.md loses both
  • Board lenses are summaries of three books, not the authors' own views
  • Output quality depends on user-supplied cost and customer inputs

What it needs

  • no GPU
  • Needs Claude (Claude Code for sub-agents), Python 3.8+
  • Models: Claude

Also in Agent frameworks and SDKs

See all 153
Also in Agent frameworks and SDKs
RankProjectScore
1ppt-masterAgent skill that turns documents into natively editable PowerPoint decks Live demo ↗ (opens in a new tab)78k starsMIT96 out of 100
2copilotkitReact and Angular SDK for adding agent chat and generative UI to apps38.8k starsMIT92 out of 100
3openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing30.7k starsMIT92 out of 100
#4mastraTypeScript framework for building AI agents, workflows and MCP servers29.6k starscustom license92 out of 100
#5browser-usePython library that lets an LLM agent control a web browser Live demo ↗ (opens in a new tab)121.4k starsMIT90 out of 100