What problem does it solve? AI agents generate code at high speed, and without disciplined version control, changes accumulate into giant unreviewable commits, messy working trees, and releases with no clear version contract. This Skill enforces atomic commits, trunk-based branching, and semantic versioning so every change stays reviewable, revertable, and traceable. ## Core Features & Use Cases - Atomic Commit Discipline: Enforces one logical change per commit with conventional message types (feat, fix, refactor, test, docs, chore) and pre-commit hygiene checks for secrets, tests, and linting. - Trunk-Based Branching & Worktrees: Guides short-lived feature branches merged within 1-3 days, plus git worktree setups so multiple agents work in parallel without interference. - Release & Versioning Contract: Applies semantic versioning (MAJOR.MINOR.PATCH), annotated git tags as the source of truth, and human-readable changelogs grouped by impact. - Use Case: An agent finishes a feature across five incremental commits, splits a messy working tree into clean atomic commits, then cuts release v1.4.0 with a tag and a curated changelog entry. ## Quick Start Ask the agent to organize the current uncommitted changes into clean atomic commits with descriptive messages and prepare a semantic version bump with a changelog entry.