generating-smart-commits
について
このClaudeスキルは、ステージングされたgit変更を分析して、従来のコミットメッセージを自動生成します。適切なコミットタイプ(feat、fix、docs)を決定し、破壊的変更を識別し、標準的な規約に従って出力をフォーマットします。ステージングされたコード変更に対してAI支援によるコミットメッセージ生成が必要な場合にご利用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/jeremylongshore/claude-code-plugins-plusgit clone https://github.com/jeremylongshore/claude-code-plugins-plus.git ~/.claude/skills/generating-smart-commits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
Prerequisites
Before using this skill, ensure:
- Git repository is initialized in {baseDir}
- Changes are staged using
git add - User has permission to create commits
- Git user name and email are configured
Instructions
- Analyze Staged Changes: Examine git diff output to understand modifications
- Determine Commit Type: Classify changes as feat, fix, docs, style, refactor, test, or chore
- Identify Scope: Extract affected module or component from file paths
- Detect Breaking Changes: Look for API changes, removed features, or incompatible modifications
- Format Message: Construct message following pattern:
type(scope): description - Present for Review: Show generated message and ask for confirmation before committing
Output
Generates conventional commit messages in this format:
type(scope): brief description
- Detailed explanation of changes
- Why the change was necessary
- Impact on existing functionality
BREAKING CHANGE: description if applicable
Examples:
feat(auth): implement JWT authentication middlewarefix(api): resolve null pointer exception in user endpointdocs(readme): update installation instructions
Error Handling
Common issues and solutions:
No Staged Changes
- Error: "No changes staged for commit"
- Solution: Stage files using
git add <files>before generating commit message
Git Not Initialized
- Error: "Not a git repository"
- Solution: Initialize git with
git initor navigate to repository root
Uncommitted Changes
- Warning: "Unstaged changes detected"
- Solution: Stage relevant changes or use
git stashfor unrelated modifications
Invalid Commit Format
- Error: "Generated message doesn't follow conventional format"
- Solution: Review and manually adjust type, scope, or description
Resources
- Conventional Commits specification: https://www.conventionalcommits.org/
- Git commit best practices documentation
- Repository commit history for style consistency
- Project-specific commit guidelines in {baseDir}/CONTRIBUTING.md
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
Algorithmic Art Generation
メタThis skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.
