What problem does it solve? Running a full plan review normally means invoking three separate review skills and answering 15-30 intermediate questions. This Skill executes the entire review gauntlet in one command, auto-deciding routine questions with six decision principles and surfacing only genuine taste decisions at a final approval gate. ## Core Features & Use Cases - Sequential Review Pipeline: Loads the CEO, design, and engineering review skills from disk and runs them in strict order at full depth, with phase-transition summaries between each stage. - Six Decision Principles: Auto-answers intermediate questions using completeness, boil-the-lake scope expansion, pragmatism, DRY, explicit-over-clever, and bias-toward-action rules, with every decision logged to an audit trail. - Taste Decision Gate: Classifies decisions as mechanical or taste-based, surfacing close approaches, borderline scope, and codex disagreements for human approval at the end. - Use Case: You have a draft implementation plan on a feature branch and want it fully reviewed for strategy, UI/UX, and architecture without babysitting each review — invoke the pipeline and only weigh in on the handful of judgment calls that remain. ## Quick Start Ask the AI to run autoplan on the current plan file to execute the full CEO, design, and engineering review pipeline with automatic decisions.
