writing-artifacts

A production line: raw thoughts in, publishable artifact out. You orchestrate stations; each station's method lives in its own SKILL.md — read it at that stage, never work from memory of it.

Stage 0 — frame (one question round, then move)

Pin three things before writing anything: the SUBJECT (one sentence), the READER (who must understand it), and the OUTPUT FORMAT. Default format by destination: quick share → md · something the user will look at twice or show someone → html page or Artifact · visual metaphor / hero image needed → add an image stage. If the user already said the format, don't ask.

Reader preset — ELI5: "explain like I'm five", "dead simple", "完全外行" pins READER = knows nothing about the domain and FORMAT = Artifact carried by big pictures and few words. Simplify the language, never the facts: no jargon without a grounded term, no "simply/just/obviously".