onboardlisted

# /onboard — researcher taste interview The marquee onboarding skill. Produces a durable, agent-injectable record of *who* the researcher is, *what* they believe, *how* they judge work, and *what dead ends* they refuse to revisit. Sister to AGENTS.md. AGENTS.md says what to do in this repo. The `taste/` corpus says who this researcher is — installed per-repo today, with cross-repo portability planned (symlink `~/.rockie/taste/` → `<repo>/.rockie/taste/` is the recommended manual interim). ## When to run - **First-run** — SessionStart hook flags absence of `.rockie/taste/INDEX.md`; agent suggests `/onboard`. - **Explicit invocation** — user types `/onboard`. - **Refresh** — `/onboard --redo` rewrites everything; `/onboard --section <soul|style|methodology|dismissals>` refreshes one file. - **Deep mode** — `/onboard --deep` runs Tier 2 (20–30 min, voice-first laddering). Otherwise Tier 1 (5–7 questions, ~5 min). ## What the skill does 1. Loads `prompts/interviewer-tier1.md` (or `interviewer-tier2.md` if `--deep`) into the active agent's system context. 2. The agent runs the interview turn-by-turn following the prompt's phase-gated state machine. The user answers via text or `/voice tap`. 3. As the interview progresses, the agent writes intermediate state to `.rockie/taste/.draft.json` after every turn (so the session can be resumed if interrupted). 4. When coverage reaches the end-condition, the agent emits a summary round, asks the user to confirm