What problem does it solve? Running a full plan review gauntlet normally means answering 15-30 intermediate questions across CEO, design, and engineering reviews. This Skill automates those intermediate decisions using 6 decision principles, so a rough plan goes in and a fully reviewed plan comes out with one command. ## Core Features & Use Cases - Sequential Review Pipeline: Loads the plan-ceo-review, plan-design-review, and plan-eng-review skill files from disk and executes them at full depth in strict order. - Auto-Decision Engine: Answers intermediate questions using 6 principles (completeness, boil lakes, pragmatic, DRY, explicit over clever, bias toward action) with an audit trail. - Taste Decision Gate: Surfaces close approaches, borderline scope, and codex disagreements at a final approval gate instead of interrupting mid-review. - Use Case: You have a plan file for a new feature and want the full review gauntlet without babysitting it. Invoke /autoplan, and it captures a restore point, runs all three review phases, logs every auto-decision, and presents only the judgment calls that need your input. ## Quick Start Ask the AI to run /autoplan on your current plan file to execute the full CEO, design, and engineering review pipeline with automatic decisions.
