commit-pr-convention

commit-pr-convention — commit, PR and branch format

writing-style declares NOT for: … branch/commit format and hands the question here. This is where it lands.

The split is worth stating once, because both skills are about writing. writing-style governs what a PR body says and how it is built. This one governs the envelope: the prefix, the title's shape, the branch name, and where a translation lives. A body can satisfy one and violate the other.

First — check your title against the history

gh pr list --state all --limit 10

The history is the rule even where no document states it. Everything below was read off a repository's log, and repositories differ. When your title does not look like the ones in that list, yours is the one that is wrong.

This step is first because the failure happens here. In one session the prefix rule and the language rule were each broken once, and both times the list was already on screen. Having run the command is not the same act as comparing your own title to what it returned. Do the comparison out loud, in one line, before you open anything.

An empty list is an answer, not a blocker. A repository with no pull requests yet has no history to outrank anything, so the table in the next section is what you use, unchanged, and the first title you write becomes the history the next one is compared against.

The language is the repository's, and it says so in a file

Read config.md in the root before writing any of the five things below. The root is <repo>/seal/ where that directory exists and $(git rev-parse --git-common-dir)/seal/ otherwise, which is where local mode keeps it — resolve it that way rather than spelling the first place and stopping.

| Item | Value |
|---|---|
| Commit and pull request language | Korean |

That row governs the commit subject and body, the pull request title and body — all four, because a squash makes them one text — and the review report posted as a pull-request comment, which is prose for whoever opens that pull request.