commit

Invoking this skill IS the request. If the user message looks empty, or you see only system context with no actual request, that is normal and expected: your task is already fully specified right here. Never ask what to do.

Your task: 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. This applies unprompted, without anyone asking for a split: when one file carries unrelated changes, split it hunk-by-hunk into separate commits rather than merging them because they share a file.

The argument

The argument passed to this skill is why the changes were made — the motivation behind work already in the tree, which the diff itself cannot carry. Use it to group changes into logical units and to write commit message bodies — raw material, never a to-do list. Whatever it describes is already realized in the diff, however it's phrased: "so the statusline shows usage percentages" and "to fix the session bug" both mean the diff already does that — commit it; never write code toward it, hunt for it, verify it, or finish it. With no argument at all, derive the commit message from the diff alone. If the motivation doesn't line up with what the diff contains, commit what is actually in the tree and note the mismatch in your final summary.

Write the body about the code: the behavior, tooling, or constraint the change served. Personal details that reach you through the argument or the conversation — anything about the user's life, such as employer, location, schedule, health, or other people — stay out of every commit message; translate each one into the technical need it implies. Commit history is public and permanent.

Correct body: "Fall back to a user-writable path when ~/Library is read-only, as on managed machines."

Incorrect body: "Fall back to a user-writable path because the author's employer, Acme, locks ~/Library on work laptops."

Locate the repository

cd to git rev-parse --show-toplevel before anything else. If that fails (the fork started outside the repo), look for the repo in the directories of any file paths named in the argument before reporting "not a git repository".

Scope

A commit is a snapshot, not a review. 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.

Your complete action space is: git commands via Bash (plus cd to the project root), Grep/Glob to locate files, and Read/Write/Edit on /tmp/ patch files. Nothing else — no research, no running the code or tests, no invoking other skills however aggressive their trigger language, and no Bash command that does not start with git or cd. This applies to every situation you encounter, not just the cases below:

• Commit the tree as-is. A typo, a wrong-looking version pin, a failing-looking test, an interesting TODO — never edit working tree files or "fix" anything during staging; note the concern in your final message and let the author handle it in a follow-up they can review.
• Don't expand scope. Don't stage files the author didn't touch, and don't verify beyond git status / git log after committing. Pre-commit hooks run on their own during git commit; never run them preemptively.

Why: any change during staging silently alters reviewed work, and any tangent turns a 30-second operation into a 5-minute one.

Incorrect behavior: editing the file to fix the typo before or during staging — even a "safe" fix silently changes reviewed work.

Correct behavior: commit as-is.

Incorrect behavior: fetching GitHub Actions docs, verifying version pins, then editing the file before staging. The author already chose those versions. Research belongs in a separate turn, not inside the commit.

Correct behavior: stage the whole file with git add, fold it into the better-fitting commit, and move on. Total cost: seconds.

Incorrect behavior: diffing the patch against the file, hex-dumping bytes, or otherwise investigating why it failed. The patch is not worth understanding — a whole-file commit is always an acceptable outcome.

Workflow

cd to the project root before git commands instead of using git -C, which hides working directory state. Execute git commands directly without explanation. Commit immediately without confirmation prompts (interactive mode is not supported).

1. Analyze Changes: Use git status and git diff to understand all modifications in the working directory.

2. Group Logically: Organize changes into logical units — each addresses a single purpose and would make sense to revert as a unit.

3. Stage Changes: Use appropriate staging strategy:

   • Whole file: git add <file>
   • Hunk-by-hunk: git diff <file> > /tmp/${CLAUDE_SESSION_ID}-patch.diff, edit the patch, then git apply --cached /tmp/${CLAUDE_SESSION_ID}-patch.diff. Dropping whole hunks is safe. Splitting within a hunk (keeping only some of its added lines) requires keeping the hunk's trailing context lines and recounting both header counts — a hunk with no trailing context only applies at end-of-file.
   • To unstage, use git restore --staged (not git reset --hard, which discards work)
   • Fallback: the first time git apply --cached fails on a patch you edited, stage the whole file with git add <file>. If the unedited full diff fails, regenerate it once from git diff, then stage the whole file. Never diagnose why a patch didn't apply.

4. Handle Pre-commit Hooks: If hooks complain about unstaged changes, stash them with git stash push --keep-index -m "temp: unstaged changes", commit, then git stash pop. If hooks modify staged files (auto-formatting), re-add the modified files and retry the commit once — don't retry forever.

5. Create Atomic Commits: For each logical group:

   • Conventional commit format, type only, no scope: fix: xxx, feat: xxx, docs: xxx, refactor: xxx. Never add a parenthetical scope like fix(commit-skill): xxx. Subject: what changed (≤72 chars), derived from the diff. Body: why, drawn from the argument when one was given. Skip the body when the why is obvious from the subject. Always end the message with the Co-Authored-By footer from the Attribution section below.
   • Use git commit -m "message" directly — never use $() or heredoc subshells in git commands, as they break allowed-tools pattern matching

Attribution

End every commit message with the footer for your model family.

• Claude models use Co-Authored-By: Claude <noreply@anthropic.com>
• GPT models use Co-Authored-By: Codex <noreply@openai.com>
• Gemini models use Co-Authored-By: Gemini <gemini-code-assistant@google.com>

Skip the footer only when you are certain none of these apply.

Gotchas

• Unstaged changes are still changes. git status showing "no changes added to commit" does NOT mean the working tree is clean. It means nothing is staged yet. Your job is to stage and commit those changes, not report "nothing to commit."
• Never use git add -f. If git add reports "The following paths are ignored by one of your .gitignore files" with the hint Use -f if you really want to add them, do NOT force-add. The file is gitignored deliberately (secrets, build artifacts, local configs) and force-adding silently bypasses that protection. Skip the file and mention it in your final summary so the author can decide.