What problem does it solve? Unverified claims and reflexive agreement let weak assumptions slip into pitches, deliverables, and evidence packages where they fail under scrutiny. This Skill forces every claim through a structured challenge protocol before it ships. ## Core Features & Use Cases - Structured Claim Challenge: A four-step protocol that names the claim, demands verifiable evidence, identifies failure conditions, and anticipates a competent reviewer's objections. - Three-Verdict System: Each claim is ruled HOLDS, UNGROUNDED, or WRONG, with specific guidance on what evidence would ground an ungrounded claim. - Reflexive Agreement Audit: A self-check step that catches agreement made because something sounded right rather than because it was verified. - Use Case: Before sending a pitch claiming a framework reduces formatting failures by 30%, run the protocol to verify the number is citable, name the conditions under which it fails, and confirm it survives a rigorous reviewer's first question. ## Quick Start Ask the AI to stress test this claim or plan using the no-man protocol before it goes into the deliverable.
