idea-to-build
A multi-agent brainstorming methodology that takes a raw idea to a plan you can build — for founders, builders, and creators.
Turn a raw idea into a plan you can actually build — in about 30 minutes. Claude sub-agents research it, argue with it, and won't let you skip the hard parts; when it's done, it hands the whole thing to Claude Code ready to build.
Quick Start • See It in Action • How It Works • Profiles • Why This • Contribute
The Problem
Brainstorming with an LLM is shallow — and it dead-ends. You get an enthusiastic wall of text, and then nothing you can actually build from.
Ask any LLM — Claude, ChatGPT, Gemini, Grok — to brainstorm and you hit the same failure modes:
- ❌ Agreement, not pushback — it tells you why your idea is brilliant, not why it'll fail
- ❌ Fabricated market sizes and made-up statistics
- ❌ Generic SWOT lists that fit any business
- ❌ "5 great ideas!" — none of which are actually different
- ❌ No memory across sessions — you re-explain context every time
- ❌ And even a good brainstorm ends in a chat you have to translate into a plan, then into a build, by hand
This tool fixes those — and closes the loop to a build. The full version runs on Claude (Cowork, Claude Code, or the Claude CLI); a degraded standalone prompt (distributions/standalone-prompts/lite.md) works in any other LLM.
The Solution
A structured 6-phase brainstorm that takes a raw idea all the way to something you can build. Understand → Context → Generate → Deep Dive → Critique → Plan — each phase does the work most chats skip: real research with sources, genuinely different options, a ruthless critique that won't let you skip the premortem, and a plan with go/no-go gates.
Then the part that makes it idea-to-build: when the brainstorm is done, /scaffold turns the whole thing into a folder you open in Claude Code and build from — the chosen approach, the paths you rejected, the risks to watch, the gates. Idea in, buildable plan out.
"It found a flaw in my pivot that I'd been missing for three weeks." — early tester
👀 See It in Action
https://github.com/user-attachments/assets/7fa999e7-d4d8-4d67-b39e-ac2698c52ca6
Real sessions, each linked in full — strongest first. Most put one prompt through a normal chat vs. the methodology, side by side; one runs a single idea through all six profiles; the first is a complete start-to-finish run that ends in a buildable plan:
- Full run: medieval tycoon game — the whole method, Phase 1 → 6 →
/scaffold. A vague "tycoon game" comes out scoped, critiqued (GO with conditions), planned with a kill-switch, and handed off as a buildable folder. Start here — it's the idea→build arc end to end.
- Hyperliquid wallet — the deepest comparison: the full method through a trace-verified isolated Phase-5 critique. Read this to see the rigor.
- Personal health AI — the harder case: plain Claude was already competent, and the methodology still added strategy (beachhead, regulatory risk, an architectural blocker).
- Profiles in action — the same idea run through six profiles, showing how each asks different questions. Proof the profiles aren't cosmetic.
- Food delivery app — the "can it say no?" test (trace-verified): the cold critic returns NO-GO on the head-on idea, then GO-with-conditions on the pivot.
- AI support agent — another honest NO-GO: the methodology pushes back and recommends not building the idea.
- Stickman game — the simplest contrast: plain Claude builds instantly, the methodology stops to scope. A quick way to see the difference.
🚀 Quick Start
Four install paths — all available.
