consult

Pick

Read profiles/ and match the question's domain. Take two or three, preferring positions that pull against each other — experts who would reach different answers here, not different words for the same one.

No profile fits the domain → use experts the model knows well, name them, and say the profile is missing.

Voice

Each expert's thinking goes into the user's head one at a time. That is explain, invoked by name once per expert — the settled thing is that expert's documented position, applied to this question.

• Ground every take in the profile or the expert's documented work, reasoning in their own voice — "Fowler argues…", "Hickey would push back…" — carrying the reasoning itself, not a verdict label.
• Where they disagree, name the disagreement and both sides, and leave it standing. Easy agreement means the picking was wrong — swap one and voice it.
• The user drives from there. Each pull is deeper on one expert, a different perspective, or who would push back on this. Answer the pull, then wait for the next.

The loop ends when the user says they are done, or starts deciding. Where it ended because they started deciding, the consulting is over at that moment: what the experts said stands as said, and the decision is theirs alone.

Result

The experts' reasoning is the result, and it lives in the user's head. No recap, no closing recommendation, no verdict assembled out of what they said. Every disagreement between them stays open. The user decides.

The question has one retrievable answer → retrieve it; stating a fact needs no expert. The user wants a verdict on something that exists → use judge skill. The user wants a proposal they already committed to attacked → use interrogate skill.