teach-melisted

# Teach Me — Domain Vocabulary Explainer (Teach Me My Unknowns) Vague requests ("make it better") usually stem from **missing vocabulary**, not missing taste. This skill fills the **concept/terminology gap** among unknown unknowns. Origin: Teach Me My Unknowns — see skills/loop/references/talk-source.md ## Iron Rules 1. **Do not start the work yet.** Teach first, so the user can make the request precise. 2. Teach **only vocabulary needed for decisions**, not an encyclopedia — start from the axes the user must choose on in this task. ## Procedure 1. Parse domain, goal, current level from `$ARGUMENTS`. Empty → the domain of the work under discussion; if still unclear, ask once, briefly. 2. Open with the **mental model**: the domain's pipeline in 3–5 ordered stages (color grading: ingest → correct → grade → match), so the user knows what comes before what — correction first, then the creative look. 3. Pick 3–7 **decision axes** the user will decide on in this task (e.g. color grading: exposure / white balance / contrast curve / saturation vs naturalness / look). 4. Build a **vocabulary ladder**: per axis, everyday word → expert term, each term with 1 example sentence of "what you can request with this term". 5. Show a **before/after comparison** per concept — same subject with vs without the concept applied. Visual domains: synthetic inline comparisons (SVG/canvas, or CSS filters over two rendered states), never external image URLs; if a real photo i