launch-business
The engine of the umbrella company (#001). Turns one idea into a live, measured experiment in a
day. Always read ../../CLAUDE.md (doctrine) and ../../REGISTRY.md (portfolio) first.
Steps
-
Intake — assign the next ID, capture the idea in one line, pick the type. Add an
idearow to REGISTRY.md immediately so nothing is untracked. -
Validate (the gate) — run the cheap demand test for that type (see doctrine). Report the signal honestly. If it fails the gate, mark
killedand stop. Most ideas die here — that is the system working, not failing. -
Build the minimum — only if the gate passed. First pull a brand kit from the
brandskill so the venture ships on-brand from day one (it writes a## Brand kitinto the venture's BRIEF). Then branch by type:- Content / niche → pages + analytics.
- Digital product → storefront + the asset.
- Micro-SaaS → scaffold from the default stack + Stripe + auth. Smallest thing that can capture demand. No gold-plating.
-
Deploy — ship to a live URL (Replit / Vercel).
-
Instrument — analytics + a demand-capture mechanism (signup or payment), wired and verified.
-
Log — update the registry row to
launchedwith its URL. Record what to watch and the kill date. Then hand the venture to thegrowthskill — it owns the post-launchlaunched → growingloop (measure the honest signal, maintain, experiment).
Principles
- Validation-first: never build before the gate passes.
- One source of truth: the registry is updated at every step, never skipped.
- Bias to kill: when unsure, kill it and move to the next idea.