| description | Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you. |
|---|---|
| argument-hint | [optional notes about you/your company to seed it] |
Set up the user's Skill Memory (pm-context.md).
- If
pm-context.mdalready exists at the project root, read it and offer to update it. Otherwise, base the structure ontemplates/pm-context.example.md. - Interview the user briefly to fill it in — ask only for what's missing, a few at a time, using any seed notes here: $ARGUMENTS. Cover: company/product, stage, primary audience, voice/tone & formatting defaults, the metrics that matter, key competitors + differentiator, and any hard constraints.
- Write a concise, concrete
pm-context.md(no filler). Keep each section to a few lines. - Confirm it's saved and explain the payoff: from now on, when running any skill or workflow recipe, read
pm-context.mdfirst and apply it — match the user's product, audience, and voice — so the first draft is tailored, not generic.
Going forward, treat pm-context.md (if present) as standing context for every skill in this library.