harrisonhjohnson/productagent · /harnesses/loops/skills/launch-business/SKILL.md
000%

SKILL.md

Run the daily venture-launch pipeline for the umbrella company — validate an idea, branch by type (content site / digital product / micro-SaaS), build and deploy the minimum, instrument it, and log it to the registry. Use when launching a new venture, running "today's business", or turning an idea into a live experiment.

view on github ↗39 lines · markdown

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

  1. Intake — assign the next ID, capture the idea in one line, pick the type. Add an idea row to REGISTRY.md immediately so nothing is untracked.

  2. Validate (the gate) — run the cheap demand test for that type (see doctrine). Report the signal honestly. If it fails the gate, mark killed and stop. Most ideas die here — that is the system working, not failing.

  3. Build the minimum — only if the gate passed. First pull a brand kit from the brand skill so the venture ships on-brand from day one (it writes a ## Brand kit into 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.

  4. Deploy — ship to a live URL (Replit / Vercel).

  5. Instrument — analytics + a demand-capture mechanism (signup or payment), wired and verified.

  6. Log — update the registry row to launched with its URL. Record what to watch and the kill date. Then hand the venture to the growth skill — it owns the post-launch launched → growing loop (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.

FULL INDEX

flow-designflow-designwhat this folder doesA progressive design interview: one question per screen, ending in a clickable HTML prototype of a linear user journey (onboarding, checkout, wizard).global
SKILL.md74 lines
loopsloopswhat this folder doesGive an agent a goal, a budget, a cadence and a model. It works one bounded run at a time while you sleep, inside a fence, and hands you four plain sentences in the morning.system
skills05 items
launch-business01 items
SKILL.md39 lines
README.md178 lines
init.sh171 lines
install.sh144 lines
loops-spec.md244 lines
MACHINE.md161 lines
settings.json116 lines
prototype-swarmprototype-swarmwhat this folder doesCrawls a multi-screen HTML prototype for undefined click destinations and spawns one generator agent per missing screen, with a handoff packet written by the source screen, until the click graph is covered.global
SKILL.md162 lines
self-maintenanceself-maintenancewhat this folder doesThe one way an unattended run may touch its own loop registry, and the one place a "need from you" becomes a decision you settle with a single command instead of a paste.system
README.md126 lines
loopctl.py599 lines
loops_registry.py122 lines
pm-strategistpm-strategistwhat this folder doesA product and strategy advisor agent that blends three lenses (build taste, business structure, PM execution) and pressure-tests ideas instead of cheerleading.global
pm-strategist.md51 lines
todotodowhat this folder doesA TODO list for PMs in one markdown file, reachable from Claude Code and from Telegram: capture, see what's due, triage, and hand items to an agent that asks before it acts.system
README.md59 lines
rev-intel-harness ↗rev-intel-harnesswhat this folder doesA CSV of companies in, the people out: point your existing AI subscriptions at target accounts. Open source, MIT.external
karma ↗karmawhat this folder doesA personal knowledge graph over everything the loops write: seeds in, relationships out, so a month of night reports stays searchable. Open source, MIT.external
README.md68 lines