Agent skill · Testing & QA

business-brainstorm

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/ma

coreyhaines31github.com/coreyhaines31GitHub ↗
claude-codeMIT
Install
npx skills add coreyhaines31/makerskills --skill business-brainstorm --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 7 KB
Bundled scripts: none
Version: 0.2.0
Path: skills/business-brainstorm/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 500

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# /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) 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. ## 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 t

What's inside
Steps it walks through
  1. Step 1 — Capture the idea
  2. Step 2 — Load the framework + personal overlay
  3. Step 3 — Score each dimension
  4. Step 4 — Trigger research where needed (optional)
  5. Step 5 — Check the .com
  6. Step 6 — Output the brief
  7. Step 7 — Archive
  8. Step 8 — Surface
  9. Composes with
  10. Notes on quality
Ships with 1 file
  • references/framework.md
More from makerskills
All skills →
About this skill
What does the business-brainstorm skill do?

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/ma

How do I install it?

Run `npx skills add coreyhaines31/makerskills --skill business-brainstorm --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From coreyhaines31/makerskills, a repository with 500 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going