critical

# Critical — Adversarial Pre-Mortem Challenge the proposed work as a hostile staff engineer would. Surface specific, grounded failure modes; force at least one steelmanned alternative; hand scoring to `/confidence`. > **Why this exists, in one paragraph.** > A single LLM "be honest" pass tends to confirm rather than challenge — naïve self-refine has been shown to amplify bias (Pride and Prejudice, ACL 2024) and to add no gains over self-consistency when the initial answer is already strong (SELF-[IN]CORRECT, AAAI). > External grounding plus a fixed taxonomy beats vague introspection (CRITIC framework). > This skill is the structured counter-pressure: one pass, hostile persona, mandatory citations, mandatory steelman, no self-scoring. ## Contents - [When to use](#when-to-use) - [Mode detection](#mode-detection) - [The persona contract](#the-persona-contract) - [External grounding rule](#external-grounding-rule) - [Taxonomy — `plan` mode](#taxonomy--plan-mode) - [Taxonomy — `code` mode](#taxonomy--code-mode) - [Taxonomy — `analysis` mode](#taxonomy--analysis-mode) - [Mandatory steelman alternative](#mandatory-steelman-alternative) - [Output format](#output-format) - [Composition with other skills](#composition-with-other-skills) - [Hard rules and non-goals](#hard-rules-and-non-goals) --- ## When to use | Use it | Don't use it | | ------------...