What problem does it solve? AI agents generate code at high speed, and without disciplined version control, changes become unreviewable, irreversible, and hard to debug. This Skill enforces commit discipline, branching strategy, and history hygiene so every change stays manageable and recoverable. ## Core Features & Use Cases - Atomic Commit Discipline: Enforces small, single-purpose commits with conventional message types (feat, fix, refactor, test, docs, chore) and ~100-line change sizing. - Trunk-Based Branching: Guides short-lived feature branches (1-3 days), branch naming conventions, and feature flags over long-lived branches. - Parallel Work with Worktrees: Uses git worktrees so multiple agents work on separate branches simultaneously without interference. - Use Case: An agent implements a task creation feature across four commits (endpoint, form, integration, tests), each verified before committing, so a failing step can be reverted instantly with git reset without losing prior work. ## Quick Start Use the git-workflow-and-versioning skill to commit my current changes as atomic commits with descriptive conventional messages.