メニュー
Apply when committing, branching, or opening a pull request. Conventional commit format, branch naming, PR scope.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | git-conventions |
| description | Apply when committing, branching, or opening a pull request. Conventional commit format, branch naming, PR scope. |
| license | MIT |
| version | 1.0.0 |
| tokens_target | 650 |
| triggers | ["git commit","branch","pull request"] |
| loads_after | [] |
| supersedes | [] |
Purpose: Consistent commit history, clean branches, no merge conflicts through discipline. Rules that work in teams of 2–20 developers.
<type>(<scope>): <description> — always lowercase, no period at the end.
feat, fix, refactor, test, docs, chore, perf, cifeat(auth): add JWT refresh token rotationadd feature not added feature or adds feature.fix(user-service): handle null email — not fix(backend).!. feat(api)!: remove deprecated v1 endpoints<type>/<ticket-id>-<short-description> — e.g. feat/PROJ-123-user-export.main.main or develop. Always through a pull request.main.git rebase -i before PR for clean commits. Squash WIP commits together.The agent automatically creates correct commit messages and branch names. No manual corrections, no discussions in review about formatting.
Git-versioned agent memory — agents that never make the same mistake twice.
Apply when generating ideas, exploring solution space, or facilitating divergent thinking before committing to an approach.
Apply when closing out a feature branch — pre-merge checklist, rebase, CI verification, cleanup, and post-merge steps.
Apply when writing or refactoring code. Generic rules to prevent the most common review comments — function length, naming, error handling, security, and tooling.
Apply when designing database schemas, writing migrations, or reviewing table structure. Covers naming, keys, indexes, constraints, nullability, and migration safety.
Apply when diagnosing a bug, reproducing a failure, or performing root cause analysis. Covers systematic isolation, binary search, logging strategy, and hypothesis-driven investigation.