git-commit

Use this workflow in order: preflight -> split plan -> classify -> compose -> commit/draft -> verify.

Decide the active change authority and output language before doing anything else:

• staged-only is the default. Respect the current index and treat unstaged or untracked files as context only.
• all-changes is allowed only when the user explicitly asks to include everything, such as "all changes", "所有改动", "全部改动", "不管有没有 stage", or "包括未跟踪文件". In this mode, the skill may rebuild the index from the full working tree and should treat any existing partial staging as intentionally overridden by the user.
• commit-language is detected, not fixed-default, because forcing one language fights repos (and users) whose history is already in the other. Resolve it in this order, then use it for scope, subject, body, and explanatory output:
  1. An explicit instruction in the user's message — "use English", "英文提交", "用中文", "中文提交", or the legacy phrase 请使用中文拆分提交所有的改动. Honor whichever language the user names.
  2. The dominant language of the user's current request message.
  3. The repository's own habit, sampled in Preflight from git log -n 20 --format=%s. Match what the repo already does so your commit doesn't read as an outlier.
  4. Fall back to English only when none of the above gives a clear signal. Language is orthogonal to emoji, [AI], and trailers: detecting Chinese never changes whether [AI] or agent trailers attach.
• agent-mode is on by default whenever this skill runs (the caller is an agent). It attaches Agent-Task / Agent-Model / Generated-By trailers and applies the Why-line rule for feat / fix / refactor / perf. It does not inject [AI] in the header. Pass --ai only when the user explicitly says "add [AI] tag", "加 AI 标记", "加上 [AI]", or equivalent. Turn agent-mode off when the user says "no AI tag", "不要 AI 标记", "不加 agent trailer", or equivalent.
• commit-channel is local git only. Create the commit with git commit -F <message-file> (or rtk git commit -F). Do not create commits through GitHub's web UI, Contents API, Git Data API, GraphQL createCommitOnBranch, gh api file-commit helpers, GitHub MCP create_or_update_file / push_files, or a platform GitHub App (Cursor Agent, Copilot, Grok[bot], Devin). Those channels make GitHub show "This commit was created on GitHub.com." and often "Committed via ". Do not pass git commit --trailer for Co-authored-by, Made-with, or "Committed via" text.
• Out of scope: git push, pull-request creation, git commit --amend, git rebase, and tags. When a request mixes those in, do only the commit work and name the rest as out of scope.

1. Preflight

1. Inspect git status --short first. Then inspect the active change set:
   • staged-only: git diff --staged --stat and git diff --staged
   • all-changes: git diff --stat, git diff, git diff --staged --stat, and git diff --staged If rtk is available, prefer rtk git status, rtk git diff --staged, and rtk git diff for model-visible inspection.
2. Explicitly note:
   • the active change authority (staged-only or all-changes)
   • staged changes ready to commit
   • unstaged changes that might make the index misleading
   • untracked files that are intentionally excluded vs accidentally forgotten
3. Branch immediately on preflight results:
   • staged-only + no staged changes: stop and tell the user to stage files first.
   • all-changes + no staged, unstaged, or untracked changes: stop and say there is nothing to commit.
   • The active change set exists but is obviously mixed and cannot be safely separated from inspection alone: do not improvise a commit. Output a split plan and stop.
   • The user explicitly asked only for commit text, a draft, or suggestions: continue through classification and composition, but do not run git commit.
4. Detect agent context (skip when user disabled agent-mode):
   • Resolve agent-model from the id of the model currently running this skill — read the runtime's own id (e.g. claude-fable-5 when that is the running model), never a model id copied from an example, which goes stale. This value is required.
   • Resolve agent-task by trying, in order: (a) explicit task ID or issue URL in the user message, (b) closes #N / refs #N mentioned by the user, (c) ticket ID extracted from the current branch name, (d) Agent-Task value from the previous commit on this branch, (e) fallback to unspecified.
   • Resolve agent-prompt-ref only when a stable prompt reference exists; otherwise leave empty.
   • Detect checkpoint-mode: triggered by user words such as checkpoint, 打个 checkpoint, 先存一下, WIP, [WIP], work in progress, 先提交一下，待会再整理.
5. Sample repository conventions so the skill adapts instead of imposing one repo's habits everywhere:
   • Language + style: read git log -n 20 --format=%s. Note the dominant subject language (this feeds commit-language step 3 in §0) and whether subjects carry gitmoji. History that already contains [AI] is informational only — do not copy [AI] into new commits unless the user opted in.
   • Config: if commitlint.config.*, .commitlintrc*, .czrc, .cz.*, .gitmessage, or a CONTRIBUTING commit section exists, treat its allowed type / scope list and length rules as authoritative over this skill's defaults. Pass a repo length rule to the composer via --max-header-width (§4) and a repo custom type via --type as-is (§4).
   • AI attribution: from the same git log sample plus CONTRIBUTING / AI-policy files, note whether the repo already has an AI attribution convention such as Assisted-by: or Generated-by: trailers. If it does, the repo convention wins over this skill's private trailer scheme — see §3.4 and references/agent-workflow.md. Do not treat host/client badges (Co-authored-by: Cursor, Made-with: Cursor, "Committed via …") as a repo convention to copy.
   • When no signal exists, fall back to this skill's defaults: emoji on, agent trailers on, [AI] off, local git commit -F only, scope from the changed path.
6. Safety scan the active change set's file list (git diff --staged --name-only, plus untracked paths in all-changes). If it includes likely secrets (.env, *.pem, *.key, id_rsa, id_ed25519, *.p12, *.keystore) or large/binary blobs (> ~1 MB), do not commit silently. Surface each risky path with its staged/untracked/tracked state, size when practical, and why it is risky. For large files, ask the user to decide per path before staging or committing: intentionally commit it, leave it untracked, add or adjust a .gitignore pattern, or move it to Git LFS / external artifact storage. Do not treat all-changes as permission to sweep every large file into history. "Safely orchestrate" means catching leaked secrets and accidental artifacts before they enter history, not only splitting commits cleanly.