autoscaffold-content

# ult-autoscaffold-content ## Overview `ult-repo-layout` can resolve *where* a project's What-L2 (requirements) and How-L2 (architecture/conventions) content should live without that content actually existing yet — a freshly-discovered repo, or a greenfield one, often has a real, confirmed path and nothing written there. This skill fills that gap: it writes real, honest, minimal starting content at the exact path `ult-repo-layout` already resolved, so the layer stops being an empty promise and starts being something a human can extend. For a small repo (or a genuinely small layer target), that's one overview file, same as Phase A — Step 4 has the exact small/large criteria. For a large repo — many independent, non-trivial subsystems under one target directory — one overview file undersells it, so Phase B adds a second path: enumerate modules, rank them by real dependency importance (not directory size) using `ult-codegraph`'s output when available, generate a per-module `CONTEXT.md` for the modules that matter, and persist progress in a state file so a second run resumes instead of restarting. Both paths write real, human-extensible content — Phase B doesn't replace Phase A's honesty standard, it scales it. This is **not** a subprocess the onboarding wizard (`ult-cep-wizard`) shells out to. Like `compiling-project-guidelines`, it's invoked directly by a human inside whichever coding agent they already have open — Claude Code, Copilot Chat, or otherwise. When the wizard's ...