portaljs-architect

1# PortalJS — Architect
2 
3## Overview
4The advisory entry point for a PortalJS project. Before anything gets scaffolded, this
5skill works out what to build: given the kind of portal, the shape of the data, and its
6purpose, it fills six architecture slots (storage, catalog, compute, access, hosting,
7metadata), resolves two build-time knobs (per-dataset data tier and the portal-wide
8`DATA_QUERY` mode), and hands off to the concrete build skills. It decides; it does not
9build. When the brief is thin it interviews in short rounds and never dead-ends — every
10question has a sensible default, reachable by replying "use defaults."
11 
12## Prerequisites
13- A rough idea of the portal's purpose and data (exact numbers are not required — the
14  interview supplies defaults for anything missing).
15- Optional: local files or a directory of sample data to inspect for size and shape.
16- No PortalJS project needs to exist yet; this skill runs before scaffolding.
17 
18## Instructions
19The canonical, full step-by-step workflow lives in
20[`.claude/commands/portaljs-architect.md`](https://github.com/datopian/portaljs/blob/main/.claude/commands/portaljs-architect.md) —
21that file is the single source of truth. Follow it when executing this skill:
22 
231. Parse `$ARGUMENTS` for anything already specified, then interview for what's
24   missing, one round at a time: (1) what's being built, (2) what the data is,
25   (3) what it's for, (4) constraints. Accept "use defaults" at any point. Inspect
26…