principle-never-block-on-the-human

What problem does it solve? Agents that stop to ask "should I do X?" on every reversible decision stall the pipeline and turn the human into a bottleneck. This Skill defines an execution principle so agents make reasonable decisions, proceed, and let the human course-correct after the fact. ## Core Features & Use Cases - Proceed-then-present pattern: Do the work, show the result, and explain the reasoning instead of asking for permission first. - Reversibility boundaries: Distinguishes reversible actions (write code, edit notes, split tasks) from irreversible ones (force-push, delete production data, send external messages) that still require confirmation. - Async supervision model: Designs workflows for review-after-the-fact so the human reviews plans, diffs, and changes on their own schedule. - Use Case: During an autonomous coding session, the agent needs to refactor a module. Instead of pausing to ask, it applies the refactor, logs the decision, and presents the diff for later review. ## Quick Start Apply the never-block-on-the-human principle and proceed with this reversible task without asking for confirmation first.