# Business Brainstorm

When you want to pressure-test a potential new business, product, or side project...

- Repository: https://github.com/coreyhaines31/makerskills (880 stars)
- Category: Testing
- License: MIT
- Last updated: 2026-10-26
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add coreyhaines31/makerskills --skill business-brainstorm -g -a claude-code -y`
Codex: `npx skills add coreyhaines31/makerskills --skill business-brainstorm -g -a codex -y`
Cursor: `npx skills add coreyhaines31/makerskills --skill business-brainstorm -g -a cursor -y`
Gemini CLI: `npx skills add coreyhaines31/makerskills --skill business-brainstorm -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add coreyhaines31/makerskills`

## Description

When you want to pressure-test a potential new business, product, or side project against the serial-founder filter. Not \"marketing ideas for a product\" (that's marketing-skills:marketing-ideas), this is \"should this business exist + can you win it.\" Runs the idea through a structured framework (problem, audience, wedge, monetization, moat, portfolio fit, distribution, energy fit, opportunity cost), checks domain availability via /domain, optionally triggers /deep-research for market validation, and outputs a viability brief: build / sleep on it / pass. Archives every idea to ~/.config/makerskills/business-brainstorm/archive/ so past work is searchable. Triggers on \"/business-brainstorm,\" \"/brainstorm,\" \"new business idea,\" \"should I build X,\" \"pressure test this idea,\" \"validate this idea,\" \"is X a good business,\" \"what about a [type] for [audience].\

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# /business-brainstorm, Pressure-test a business idea

Takes a vague idea, runs it through the user's filter, and outputs a structured viability brief. Composes with `deep-research` (for market) and `/domain` (for naming).

## Step 1, Capture the idea

Get from the user:
- The idea in 1, 2 sentences (the *what*)
- The reason it's on their mind (the *why now*)
- Any starting context (a chat where this came up, a tweet that inspired it, a problem they've hit)

**Resume first.** Look in the archive dir (Step 7) for files whose first line starts with `<!-- in-progress`. If one matches this idea, offer to pick it up: read it, keep every settled score, and continue from the next unscored dimension.

If they point at a past chat / doc, load it first. Memory has `project_*.md` files for in-flight projects, check there before assuming the idea is brand-new.

If the idea is too vague to score, ask 1, 2 clarifying questions and stop. Don't pad the brief with assumptions.

Two more cases where scoring would be theater:
- **Validation-seeking** ("just tell me it's good," "hype me up"), name it kindly: *"I'll run it, but a brief that can't say Pass is worthless. Still in?"* Proceed only on those terms.
- **Already committed** (built, launched, money spent), this isn't "should it exist" anymore. Offer `decide` for the next call (keep going / pivot / stop) instead.

## Step 2, Load the framework + personal overlay

Read `references/framework.md`, the user's filter. Apply each dimension in order.

Also try to load `${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/business-brainstorm/portfolio.local.md` if it exists, this is where the user lists their real in-flight businesses, properties, audiences, and partners. When present, use it for the "portfolio fit," "distribution," and "opportunity cost" dimensions instead of asking the user to name each one.

## Step 3, Score each dimension

The rest: https://github.com/coreyhaines31/makerskills/blob/HEAD/skills/business-brainstorm/SKILL.md