principle-never-block-on-the-human

What problem does it solve? Agents that pause to ask "should I do X?" on every reversible decision stall pipelines and make the human the bottleneck. This Skill encodes an operating principle: proceed on reversible work, present the result, and let the human course-correct asynchronously. ## Core Features & Use Cases - Proceed-then-present pattern: Do the work, show the result, and explain the reasoning instead of asking for permission first. - Clear boundaries: Irreversible actions (force-push, deleting production data, sending external messages) still require confirmation; reversible actions (writing code, editing notes, splitting tasks) proceed without blocking. - Async supervision model: Design 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 refactors a module and splits a large task into subtasks without pausing, then presents the diff for the human to review and adjust afterward. ## Quick Start Apply the never-block-on-the-human principle so the agent proceeds on reversible work and only asks for confirmation on irreversible actions.