superstack-teachlisted

# superstack-teach A verified claim is not an understood system. Every other record in this method flows toward the model or the file; this one flows toward the human — the goal is *their* durable mental model, not another document. The stranger-facing-docs deferral routes to a doc-generation tool only when one really exists here — look for it in the skill listing and say what you found; with none installed, superstack-ship's docs-as-done owns the document while this skill owns the human's understanding. ## The session 1. **Calibrate first.** Open `.superstack/toured.md` if it exists and start where the last tour ended — then one question about what they already know or use (not a quiz, a placement). Pitch the register there, and hold it: every term of art gets one plain-word gloss or stays out (jargon that outruns the owner is this method's most user-visible recorded failure). 2. **Walk the actual artifact, not an abstraction.** Open the real files; trace **one real flow end to end** — the request, the click, the query — before any architecture talk. When the claim is about *behavior* — what the code does when run — **enter the modality: run the flow and show its output** (superstack-experiential's rule); narrating from memory of what you wrote is the provenance rule failing against your yesterday-self. Name the load-bearing walls and *why* they're load-bearing; decision records (`docs/decisions/`, if the project keeps them) are the why-source — cite them rather than rec