deliberative-analysis

# Deliberative Analysis ## Overview Deliberative Analysis is a lightweight companion skill for Agent Arena. Use it to slow down reasoning, expand the option space, and decide whether a task should escalate to heterogeneous multi-agent debate. Core principle: **do not choose between A, B, and A+B until the framing itself has been challenged and at least one genuinely different alternative has been explored.** This skill is intentionally a thin wrapper. It does not duplicate Agent Arena's full multi-agent protocol. When external agents, evidence checks, or judging are needed, escalate to `agent-arena` with `deliberative_analysis` mode. ## When to Use Use this skill when the user asks for: - deeper analysis, - perspective shifts, - avoiding tunnel vision, - avoiding overconfidence, - escaping path dependence, - comparing A vs B vs A+B, - finding non-obvious alternatives, - reframing a design, experiment, architecture, product, or research decision. Also use it when you notice: - the current answer is converging too quickly, - all options are small variants of one idea, - the best proposal is just a compromise, - success criteria are unclear, - a hidden assumption controls the recommendation, - the problem may be framed incorrectly. Do not use this for: - simple factual lookups, - formatting or translation, - routine code review without design uncertainty, - cases where the user explicitly asked for a fast answer, - tasks already requiring full `agent-arena` orchestrat...