本文へ移動
cccskills
無料GitHub で公開

gh-commit

Review git changes and split them into semantic commits with clear messages. Use when the user asks to commit work, clean up local history, or group a mixed diff into logical commits. Do not commit on main or master unless the user explicitly asks.

日本語の概要は準備中です。原文の説明を表示しています。

jxnl/personal-monorepo-templateスター 573(GitHub 573 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(2)

  • SKILL.md2.2 KB
  • agents/openai.yaml198 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

GH Commit

Goal

Turn the current working tree into a small set of clean commits without mixing unrelated changes.

Workflow

  1. Verify git context.
  • Run git rev-parse --show-toplevel and git status -sb.
  • Read the branch with git branch --show-current.
  • If the branch is main or master, stop and ask the user to switch/create a branch (recommend codex/...) unless they explicitly asked to commit on that branch.
  1. Inspect all changes before staging anything.
  • Run git diff --stat and git diff --cached --stat.
  • List untracked files with git ls-files --others --exclude-standard.
  • Read actual hunks with git diff and git diff --cached.
  • Include untracked files in the review (read them if needed) so commit grouping decisions cover the full diff.
  1. Propose semantic commit groups.
  • Group by intent, not just file type (for example: bug fix, refactor, tests, docs).
  • Keep user-authored unrelated work separate.
  • Call out any files that need partial staging because they contain mixed concerns.
  1. Create each commit group.
  • Stage only the files or hunks for that group (git add <paths> or git add -p).
  • Verify exactly what is staged with git diff --cached --stat and git diff --cached.
  • Commit with a concise imperative message.
  • Prefer type(scope): summary when the change has an obvious type/scope; otherwise use a clear plain-English summary.
  1. Repeat until done.
  • After each commit, re-check git status -sb.
  • Continue until all intended changes are committed or intentionally left uncommitted.
  1. Report the result.
  • List the commit SHAs and messages in order.
  • Note any remaining staged/unstaged/untracked files.

Safety Rules

  • Avoid git add -A unless the entire remaining diff belongs in one commit.
  • Use partial staging when a file mixes multiple concerns.
  • Do not rewrite or discard user changes unless explicitly asked.
  • If grouping is ambiguous, ask before committing.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

assistant

無料

Meet or work with Assistant, the user's relaxed ongoing work support. Use when the user invokes Assistant, starts or resumes an Assistant chat, asks what they should know, wants proactive work awareness, asks for reply drafts, asks to keep an eye on work, or needs follow-up/check-in help. On first contact, start with exactly "Hi, I'm your assistant." then decide whether onboarding is brand new, partial, or already established.

日本語の概要は準備中です。原文の説明を表示しています。

jxnl/personal-monorepo-template5732026年6月23日 更新

Audit, de-slop, parameterize, modularize, or safely clean up AI-generated or AI-shaped backend/general code. Use for Python, TypeScript, or other implementation diffs that may contain duplicate helpers, fixture hacks, hard-coded test data, over-defensive control flow, broad exception wrappers, config-bag or boolean-mode soup, speculative scaffolding, hallucinated APIs/dependencies, local-idiom drift, brittle tests, or maintainability/safety/performance gaps after a feature, bugfix, prototype, or agent pass.

日本語の概要は準備中です。原文の説明を表示しています。

jxnl/personal-monorepo-template5732026年6月23日 更新

Audit AI-generated, AI-shaped, or AI-looking frontend code, UI screenshots, and design diffs. Use for prompts like "audit AI frontend", "de-slop UI", "componentize this screen", "parameterize this React/Tailwind/shadcn UI", "make it responsive/accessible", or "review design-system drift"; check component APIs, reusable props/data models, modular composition, shared primitives/tokens, responsive resilience, accessibility, copy quality, hard-coded fixture screens, one-off CSS piles, and generic cards/gradients/fonts.

日本語の概要は準備中です。原文の説明を表示しています。

jxnl/personal-monorepo-template5732026年6月23日 更新

Audit pasted chatbot output, AI-cleanup diffs, wiki drafts, Markdown/MDX/docs, and source-backed articles for generic AI fluff, LLM writing tells, weak audience model, lack of theory of mind, inflated significance, vague attribution, leaked tokens, placeholders, broken markup, fabricated or mismatched citations, and detector false positives. Use for requests like "AI writing audit", "check for AI slop", "find writing fluff", "does this sound like ChatGPT", "cleanup LLM tells", "make this less generic", "verify these citations", "detector flagged this", or text containing turn0search0, oaicite, oai_citation, contentReference, utm_source=chatgpt.com, malformed references, or wrong target-format markup.

日本語の概要は準備中です。原文の説明を表示しています。

jxnl/personal-monorepo-template5732026年6月23日 更新

Help address review/issue comments on the open GitHub PR for the current branch using `oai_gh` or `gh`; verify auth first and prompt the user to authenticate if not logged in.

日本語の概要は準備中です。原文の説明を表示しています。

jxnl/personal-monorepo-template5732026年6月23日 更新

gh-fix-ci

無料

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `oai_gh` or `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

日本語の概要は準備中です。原文の説明を表示しています。

jxnl/personal-monorepo-template5732026年6月23日 更新

jxnl のスキルをすべて見る

このスキルの問題を報告する