What problem does it solve? AI agents and developers generate code faster than they can organize it, leading to giant unreviewable commits, tangled branches, and releases with no clear version contract. This Skill enforces disciplined version control so every change stays reviewable, revertable, and traceable. ## Core Features & Use Cases - Atomic Commit Discipline: Enforces small, single-purpose commits with descriptive conventional messages (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 AI agents can work in parallel without conflicts. - Semantic Versioning & Releases: Defines MAJOR.MINOR.PATCH bump rules, annotated git tags as the source of truth, and human-readable changelogs grouped by Added/Changed/Fixed/Deprecated. - Use Case: An AI agent finishes a messy working session with mixed refactors and features; this Skill splits the work into clean atomic commits, writes proper messages, and prepares a tagged v1.4.0 release with a curated changelog entry. ## Quick Start Ask the agent to split the current uncommitted changes into atomic commits with conventional messages and prepare a semantic version release with a changelog entry.