What problem does it solve? Large migrations, ambitious multi-part changes, and long autonomous runs lack a built-in playbook, so agents either under-plan or over-engineer. This Skill designs a rigorous, auditable workflow before any code is written, so a human can review the decision trail after stepping away. ## Core Features & Use Cases - Playbook Design: Frames the task with a falsifiable definition of done, quantified scope, and a rigor level scaled to risk, then decomposes work into atomic, independently-landable units sequenced riskiest-first. - Hypothesis Loop: Runs each unit as an experiment with a stated hypothesis, minimal change, and verification against the real artifact, producing VERIFIED, NOT VERIFIED, or INCONCLUSIVE verdicts. - Audit Trail: Logs every decision and unit in a canonical TSV via the show-me-your-work skill, with evidence links a reviewer can re-run. - Use Case: Migrating an API across dozens of call sites: the Skill frames the migration, builds a verification harness from the pre-change baseline, sequences the riskiest call sites first, and commits a decision log alongside the diff for PR review. ## Quick Start Ask the agent to figure out a plan for your large migration or multi-part change, for example by saying "figure it out: migrate our codebase from the old ORM to the new one across all services".