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 release. This Skill enforces atomic commits, short-lived branches, semantic versioning, and curated changelogs so every change stays manageable and traceable. ## Core Features & Use Cases - Commit Discipline: Enforces atomic commits with conventional message types (feat, fix, refactor, test, docs, chore) that explain the why behind each change. - Branching & Worktrees: Guides trunk-based development with short-lived feature branches and git worktrees for parallel AI agent work. - Release & Versioning: 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 completes a feature across several commits, then you ask it to cut a release — it determines the correct version bump, tags v1.4.0, and writes a changelog entry grouped by Added/Fixed/Deprecated. ## Quick Start Use the git-workflow-and-versioning skill to review my uncommitted changes, split them into atomic commits with proper messages, and prepare a semver release tag with a changelog entry.