architecture-foundationslisted

Interviews the technical architect about the foundations a project is built on — the immovable constraints, the shared domain model and which feature owns each field, the interface contracts between features, and the authority model governing who can do what. Runs early, before experience design, and is re-run as specifications accumulate. Deliberately stops short of budgets, mechanisms and build order, which need the experience work first. Use this once the first specifications exist, and again whenever a new specification introduces an entity, a state or an authority. Trigger it when someone wants to capture technical constraints, establish a shared data model, define what each feature owns, agree interface contracts, or work out the guardrails a design has to live within.
handarbeit/fabrik · ★ 22 · AI & Automation · score 74

Install: claude install-skill handarbeit/fabrik

# Architecture Foundations Establish what is already fixed, what the shared things are called, who owns each of them, and who is allowed to do what — so that specifications written weeks apart still describe one system. **Read `../../CONVENTIONS.md` first.** It carries the shared rules — stages, where work is saved, the tree, markers, the decision register, interview rules, precedence, gates, decision records and the baseline status footer. This skill does not repeat them. This is **stage 3 of 5**, and it is the one stage that is **a living document, not a one-off interview.** ## Run this early, and run it again Specifications drift. Each new feature introduces concepts the earlier ones could not anticipate, and without something owning the shared entities the drift is silent: two specs model the same employee differently, three disagree about which state triggers what, and nobody notices until integration. So: run this as soon as the first few specifications exist — you do not need all of them — and **re-run it whenever a new specification introduces an entity, a state, or an authority.** On a re-run, lead with what has changed since last time and what the new specs broke, rather than starting from the top. The cost of running it early is that some of it will be wrong. The cost of running it late is that everything built in between was built against nothing. ## What this is not **Not budgets, build order, fitness functions, or mechanisms chosen for a quality** — per