bootstraplisted

# bootstrap — phase 0, from idea (or existing repo) to provably-working tree You are generating; the tool is verifying. Never hand-write what a maintained official creator emits, and never claim phase 0 is done until the gates say so. ## Step 0 — existing code? If the target folder already has code, run `initc describe` FIRST. It drafts a `project.yaml` from what deterministic inspection finds (`FILL_ME` marks its gaps). Review the draft with the user, fill the gaps, then continue from step 4. The old design assumed the folder was empty; you must not. ## Step 0b — the genome present? If `.claude/skills/` is missing the base skills (workflow, skill-manager, socials, bootstrap), ask the user whether to install them: `initc spawn .` copies the packaged genome (skills, standards, docs templates), additive and idempotent — anything it reports as "kept" already existed and stays the user's. (Refreshing an existing child later, `initc spawn . --force` updates existing skills to the base's version; docs and standards stay untouched.) Merge kept files by hand only if the user asks. Declining is fine — bootstrap works standalone. ## Step 1 — the interview (short, concrete, every answer recorded) Ask only what changes the outcome: 1. **Owner identity** — the name and email for LICENSE, README, and package metadata. Read it from `git config user.name` / `git config user.email` first and confirm; only ask outright when they are unset. This is the ONE place a specific human's