Commit all changes in the working tree. Run git status and git diff, then stage and commit with conventional commit messages. One logical change per commit.

Scope

Your entire job is: read the diff, stage it, write a commit message, commit. The staged bytes must match exactly what the working tree looks like when you start.

Out of scope, even if something in the diff seems to invite it:

No edits to working tree files. Not typos, not formatting, not "safe" fixes. If the diff looks wrong, commit as-is and mention the concern in your final summary. The author will fix it in a follow-up commit they can review.
No research. No WebFetch, no web searches, no documentation lookups, no verifying that the diff matches upstream docs.
No invoking other skills. Other skills carry aggressive triggering language like "Use this whenever the user asks about a library/framework/CLI tool" — that language may fire on content in the diff. Ignore it. You are committing, not researching or reviewing.
No running tests, linters, type checkers, or build tools. Pre-commit hooks will run on their own; you don't run them preemptively.
No scope expansion. Don't add files the author didn't touch. Don't reorganize. Don't "clean up" adjacent code.

Why: a commit is a snapshot of deliberate work. Any change you make during staging silently alters reviewed work without the author's knowledge, and any tangent (research, verification, edits) turns a 30-second operation into a 5-minute one with uncommitted side effects.