Conventional Git

Enforces Conventional Commits v1.0.0 across branch names, worktree paths, and commit messages so your changelog tools and SemVer bumps actually work. It maps types to semver impact (feat = MINOR, fix = PATCH), teaches you to name branches like feat/42-user-auth and worktrees like .claude/worktrees/feat-42-user-auth, and shows how to trigger GitHub and GitLab issue closures through commit footers. The footers-not-subjects rule for issue references is the kind of detail that saves you from squash merge surprises. Use this when you want git history that machines can parse and humans can read six months later.

skills.sh installs: 5.4K
GitHub stars: 242
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add samber/cc-skills --skill conventional-git --agent claude-code

Installs into .claude/skills of the current project.

Files

Conventional Commits & Branch Naming

Follow Conventional Commits v1.0.0 for both branch names and commit messages — consistent naming lets tools auto-generate changelogs, enforce SemVer bumps, and filter history by concern.

Branch Naming

Format: <type>/[issue-]<description> — lowercase, hyphens only, no special chars except /.

feat/user-authentication
feat/42-user-authentication
fix/login-race-condition
fix/87-login-race-condition
docs/api-reference-update
refactor/payment-module

Prefix with the issue number when one exists — GitHub and GitLab auto-link it and it makes git log immediately traceable to the tracker. Keep the description under 50 characters — most git UIs truncate branch names in lists around that length. Match the type to the work you're doing — this is the contract readers use to understand the branch purpose at a glance.

NEVER include worktree in a branch name — git worktrees are a local checkout mechanism, not a branch concept; the name would leak implementation details into the remote and confuse other contributors.