MCP HubMCP Hub
スキル一覧に戻る

commit-prepare

majiayu000
更新日 Yesterday
20 閲覧
58
9
58
GitHubで表示
コミュニケーションgeneral

について

このClaudeスキルは、開発者が従来のコミットメッセージを作成するのを支援するため、gitの変更内容を分析します。コミット関連のフレーズで起動し、適切なコミットタイプ(feat、fix、docsなど)とスコープを自動的に判断します。スキルはgitコマンドを通じてステージング済み/未ステージングの変更を調査し、適切にフォーマットされたコミットメッセージを生成します。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/majiayu000/claude-skill-registry
Git クローン代替
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/commit-prepare

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Commit Preparation Skill

Automatically prepare commit messages following conventional commits standard.

Activation

This skill activates on keywords:

  • "commit", "prepare commit", "commit this"
  • "commit message", "write commit"
  • "stage and commit", "commit changes"
  • "what should I commit", "ready to commit"

Workflow

When activated, follow these steps:

1. Gather Context

Run these commands to understand what's being committed:

# See all changes
git status

# Staged changes (what will be committed)
git diff --cached --stat
git diff --cached

# Unstaged changes (won't be committed yet)
git diff --stat

2. Analyze Changes

Determine:

  • Type: feat, fix, docs, refactor, test, chore, perf, ci
  • Scope: Which component/module is affected (optional)
  • Breaking: Are there breaking changes?
  • What: What was changed
  • Why: Why was it changed (if not obvious)

3. Generate Commit Message

Follow conventional commits format:

<type>(<scope>): <subject>

<body>

<footer>

Type Reference

TypeWhen to UseExample
featNew featurefeat: add user authentication
fixBug fixfix: resolve null pointer in parser
docsDocumentation onlydocs: update API reference
refactorCode restructuringrefactor: extract validation logic
testAdding/fixing teststest: add unit tests for auth
perfPerformance improvementperf: optimize database queries
choreMaintenance, depschore: update dependencies
ciCI/CD changesci: add caching to workflow
styleFormatting onlystyle: fix indentation

Rules

  • Subject: Imperative mood ("add" not "added"), no period, max 50 chars
  • Body: Wrap at 72 chars, explain what and why (not how)
  • Footer: Breaking changes, issue references

4. Handle Staging

If there are unstaged changes, ask:

  • "Stage all changes?" (git add .)
  • "Stage specific files?" (list them)
  • "Review changes first?" (show diff)

5. Execute Commit

After user confirms the message:

git add <files>
git commit -m "<message>"

Important: Always use HEREDOC for multi-line commits:

git commit -m "$(cat <<'EOF'
feat: add user authentication

Implement OAuth2 flow with Google and GitHub providers.
Includes session management with secure cookies.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>
EOF
)"

6. Post-Commit

After successful commit:

  • Show git log -1 to confirm
  • Suggest git push if ready
  • Mention if more changes remain unstaged

Example Interactions

Simple Commit

User: "commit these changes"

Claude:

git status
git diff --cached

Looking at your staged changes:

  • Modified src/auth/oauth.py - added token refresh logic
  • Modified tests/test_auth.py - added refresh tests

Suggested commit:

feat(auth): add OAuth token refresh

Implement automatic token refresh when access token expires.
Includes retry logic with exponential backoff.

Shall I commit with this message?


Breaking Change

User: "ready to commit"

Claude: I see you've changed the API response format. This is a breaking change.

Suggested commit:

feat(api)!: change response envelope format

BREAKING CHANGE: API responses now use { data, meta, errors }
envelope instead of flat response. Clients must update parsing.

Migration: Update response handlers to access .data property.

This marks it as a breaking change with !. Proceed?


Multiple Logical Changes

User: "commit this"

Claude: I see changes to multiple unrelated areas:

  1. Bug fix in parser.py
  2. New feature in export.py
  3. Updated docs

Recommend splitting into separate commits:

  1. fix(parser): handle empty input gracefully
  2. feat(export): add CSV export option
  3. docs: update export documentation

Want me to help stage and commit each separately?

Attribution

Always include Claude attribution for AI-assisted commits:

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>

Safety Rules

  • Never use git commit --amend on pushed commits
  • Never skip hooks with --no-verify unless explicitly asked
  • Always show the commit message before executing
  • Check for secrets/credentials in staged files
  • Warn about large binary files

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/commit-prepare

関連スキル

algorithmic-art

メタ

This Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.

スキルを見る

subagent-driven-development

開発

This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.

スキルを見る

executing-plans

デザイン

Use the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.

スキルを見る

cost-optimization

その他

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

スキルを見る