What problem does it solve? Teams commit to product or architecture options without stress-testing the assumptions behind them, discovering fatal flaws only after months of investment. This Skill acts as an adversarial reviewer that attacks every option while it is still cheap to kill, exposing the premise that invalidates each path and the hidden costs nobody budgeted for. ## Core Features & Use Cases - Premortem Headlines: Generates 2-4 distinct failure headlines with different root causes, then asks the user which one scares them most to set severity ordering. - Per-Option Attack: For each option in options.md, identifies the single premise that kills it, a cheap experiment to test that premise, the hidden cost (anchored to concrete legacy files when applicable), and the point of no return. - Cross-Cutting Risk Register: Checks six transversal risk categories such as single-person dependency, regulatory obligations, third-party integrations, data migrations, auth changes, and undeclared availability commitments. - Use Case: After running the Explorer agent to map solution options for a legacy modernization, invoke the Challenger to produce a risks.md that forces the team to answer hard questions before the Arbiter scores the options. ## Quick Start Ask the agent to run the Challenger premortem on the current ideation session and generate the risks.md document attacking every option.
