What problem does it solve? AI agents generate code at high speed, and without disciplined version control, changes become unreviewable, hard to revert, and risky to merge. This Skill enforces atomic commits, short-lived branches, and clean history so every change stays manageable and reversible. ## Core Features & Use Cases - Atomic Commit Discipline: Enforces one logical change per commit with conventional message types (feat, fix, refactor, test, docs, chore) and a target size of roughly 100 lines per change. - Trunk-Based Branching Strategy: Keeps main always deployable with short-lived feature branches merged within 1-3 days, plus naming conventions like feature/task-creation and fix/duplicate-tasks. - Parallel Work with Git Worktrees: Runs multiple agents on separate branches simultaneously using git worktree, isolating experiments without branch switching. - Use Case: An AI agent implements a feature in slices, committing each tested increment with a descriptive message, so a broken change can be reverted instantly with git reset --hard HEAD without losing prior work. ## Quick Start Ask the agent to commit the current changes as atomic commits with conventional messages on a short-lived feature branch branched from main.