What problem does it solve? Large migrations, ambitious multi-part changes, and unattended long-running work often fit no predefined playbook, leaving engineers without a structured, auditable process. This Skill designs a bespoke workflow that scales rigor to the task and leaves a decision trail a human can review after stepping away. ## Core Features & Use Cases - Playbook Design: Frames the task with a falsifiable definition of done, quantified scope, and a rigor level, then decomposes work into atomic, independently-landable units sequenced riskiest-first. - Hypothesis Loop: Runs each unit as an experiment with a stated hypothesis, smallest change, and verification against the real artifact, producing VERIFIED, NOT VERIFIED, or INCONCLUSIVE verdicts. - Audit Trail: Logs decisions through the show-me-your-work skill and routes one-way-door design decisions through the architect skill. - Use Case: You need to migrate a large legacy subsystem with no existing playbook. Invoke this Skill to get a phased plan with verification harnesses, parallelization decisions, and a committed decision trail for PR review. ## Quick Start Ask the AI to figure out a plan for your large migration or multi-part change using the figure-it-out playbook.