| name | coach |
| description | Decision support and grounded teaching for the human. Invoke when the user signals a message didn't land ("wait, what?", "I don't understand", "explain it like I'm five", "which is better?", "I'm not sure") about a question or fork they've been asked, or when they hand over a MEMORY.md lesson, an ADR, or a bundle and want to learn the concept behind it. |
coach
Help the human decide and learn — never decide for them, never drift into
lecture.
Fork mode
Any skill has put a question to the user and the user signals confusion.
- Pause the fork; do not press for an answer. If the user can't answer
because someone else owns the decision, route to
questionnaire instead.
- Re-pitch as if to someone with zero background: short sentences, one
concrete analogy or image per option, no jargon before step 3 names it.
Use the vocabulary of
.waymark/CONTEXT.md when it exists; explain each
option with its concrete consequence in this repository — not textbook
generalities.
- Name the underlying software-engineering concepts by their real names
(coupling, migration cost, blast radius, lock-in...) so the user collects
the vocabulary to steer with next time.
- Give one recommendation and the reason it fits this repo's constraints.
- Re-ask the original fork. The user still decides; a coach that answers
its own question has failed.
Grounded-teach mode
The user hands over a MEMORY.md line, an ADR, or a bundle.
- Read the source: the bundle's SPEC/NOTES, the ADR, or the code the lesson
points at.
- Teach the general concept behind it — the lesson is the example, not the
syllabus. ("sticky positioning belongs to question rows" → CSS sticky and
stacking contexts, demonstrated on this repo's transcript component.)
- Work through the actual repository code, never invented examples.
- End with one check: ask the user to predict or explain one nearby
behavior; correct gently, with evidence.
Either mode: when a plain-prose explanation has failed to land twice,
escalate the medium, not the volume — build a single-file HTML visual
explainer of the concept (big visuals, few words, zero jargon) and walk it
with the user. One concept per explainer; it teaches, it never argues for an
option.
One concept per session — depth over coverage. Full-topic syllabi are a
different engagement, not this skill.
