Essential command-line tools and system utilities.
マルチモデルコードレビュー。LLMがコードレビューを行った後、GitHub Copilot CLIに精査させて双方の視点を統合した最終レビューを提供。Use when user wants multi-model code review, second opinion, or wants to cross-check review findings with another AI. Triggers: "/multi-model-review", "マルチモデルレビュー", "複数モデルでレビュー", "セカンドオピニオン"
Use for investigation-heavy work. Prefer tool-driven evidence (search, logs, diffs) before changing code.
Code review assistance with linting, style checking, and best practices
Use when creating git commits or pull requests. Enforces conventional commit format and atomic change principles. Verified on Git 2.30+
Review and apply GitHub Copilot suggestions on pull requests. Trigger when reviewing PRs with Copilot suggestions.
Apply when committing code, creating branches, or preparing pull requests. Covers conventional commit format, branch naming, co-author attribution, and pre-commit checklist.
Review committed changes and create a pull request on GitHub. Use when the user wants to create a PR, requests pull request creation, or asks to open changes for review. Supports --japanese flag for Japanese PR descriptions, --base flag to specify target branch, and --update flag to update existing PR. Works with GitHub repositories using the github MCP server.
Create GitHub issues and PRs following contribution guidelines. Activate when user says 'contribute this', 'submit pr', 'open issue and pr', or wants to submit changes to upstream.
Automatically applies when drafting or revising documentation to enforce repository voice, clarity, and navigation patterns.
Creates git commits following project-specific conventional commit conventions for a Quartz blog (content, fix, style, build prefixes)
Generate conventional commit messages following git-cz style by default (emoji between type and subject). Automatically detects project configuration when present. Use when creating git commit messages with Conventional Commits specification. See references/config-detection.md for supported configurations.
Create well-structured git commits with conventional commit messages. Use when user wants to commit changes or asks about commit best practices.
Review code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality.
Perform comprehensive code reviews using OpenAI Codex CLI. This skill should be used when users request code reviews, want to analyze diffs/PRs, need security audits, performance analysis, or want automated code quality feedback. Supports reviewing staged changes, specific files, entire directories, or git diffs.
Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.
[PROJECT] file and directory structure conventions and enforcement
Execute refactoring safely with test-first verification following best practices. Takes refactoring discovery reports as input and performs incremental refactoring with continuous validation. Ensures tests stay green, captures metrics, and generates execution logs. Use after refactoring-discovery analysis to implement recommended improvements. (project, gitignored)
