What problem does it solve? AI-assisted coding produces changes at high speed, and without disciplined version control those changes become unreviewable, irreversible, and untraceable. This Skill enforces commit hygiene, branching discipline, and release versioning so every change stays manageable and every release carries a clear contract for consumers. ## Core Features & Use Cases - Atomic Commit Discipline: Enforces small, single-purpose commits with conventional message types (feat, fix, refactor, test, docs, chore) and pre-commit 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 parallel AI agents can work in isolated directories simultaneously. - Semantic Versioning & Changelogs: Defines MAJOR.MINOR.PATCH bump rules, annotated release tags as the source of truth, and human-readable changelogs grouped by Added/Changed/Fixed/Deprecated. - Use Case: An AI agent completes a feature across five commits, each tested and scoped; when cutting release v1.4.0, the version bump, annotated tag, and changelog entry are derived consistently so consumers know exactly what changed and whether upgrading is safe. ## Quick Start Ask the agent to commit the current changes following the git workflow skill, splitting them into atomic commits with conventional messages.