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)
Generate .editorconfig files for consistent coding styles across different editors and IDEs. Triggers on "create editorconfig", "generate editor config", "editorconfig for", "editor settings".
Analyze code changes and recommend appropriate documentation. Evaluates git diffs to determine if changes warrant README updates, inline doc additions, or dedicated documentation files. Triggers on: document changes, what should I document, doc writer, write docs for changes, documentation recommendation.
GitHub Copilot CLIを使用してコードレビューを実行する。Claude CodeからCopilotにレビューを依頼したい時に使用。トリガー：「Copilotにレビュー」「copilotでコードレビュー」「差分をCopilotでチェック」「Copilotにコードを見てもらう」「レビューをCopilotに依頼」
Core Go development patterns and idioms. Use for package design, code organization, configuration patterns, interface definitions, or when editing .go files. Triggers: package structure, dependency hierarchy, interface contracts, config transformation, encapsulation, layered organization, parameter encapsulation, modern Go idioms.
Your approach to handling global code style. Use this skill when working on files where global code style comes into play.
Review code changes using Codex CLI. Use this skill when the user wants to review implemented code, uncommitted changes, or specific commits using the codex review command. Triggers on requests like "review my changes with codex", "codex review", or "review this commit".
Use when working in Jeff's dotfiles repository to understand structure, naming patterns, branch strategy, and Claude Code integration
Discover refactoring opportunities by analyzing code for excessive responsibilities, tight coupling, low cohesion, and SOLID principle violations. Generate detailed reports with redesign proposals tailored to the project's architecture. Use when analyzing existing code modules for quality issues, before major refactoring, or to maintain code health. Performs module-by-module analysis on demand. (project, gitignored)
Use when the user asks for a code review of a PR/branch/diff/patch
Run comprehensive code quality checks including TypeScript typecheck, ESLint linting, Prettier formatting, and Markdown validation. Auto-fixes formatting issues in agent mode or provides read-only checks for CI pipelines. Use when: (1) Before committing code changes, (2) In CI/CD pipelines for automated quality gates, (3) After making significant code changes, (4) When preparing code for review, (5) When ensuring code meets quality standards, (6) For type checking, linting, formatting, and markdown validation, (7) In pre-commit hooks, or (8) For automated quality gates before merging. Triggers: finalize, code quality, typecheck, lint, format, check code, quality check, run checks, pre-commit, before commit, CI checks, validate code.
Reviews code for best practices, security vulnerabilities, and adherence to the project's style guide. It provides actionable feedback and refactoring suggestions.
Use when working in a repo with Codex CLI to plan, edit files safely, and suggest verification steps.
Comprehensive code review tool for Clean Code principles and project architecture. Supports single-file review (/review-code) and project-wide analysis (/review-code <directory>). Checks variable naming, function length, redundant comments, and generates actionable reports. Supports JavaScript, Python, and Java.
Codex CLIでレビュー・分析をする。trigger: 「codexにレビューして」「レビューして」「review my changes」
Write production-ready Go backends, CLIs, and APIs following modern best practices from top tier tech companies. Use this skill when creating or reviewing Go code for (1) backend services and APIs, (2) command-line tools, (3) code requiring proper error handling, concurrency, or testing patterns, (4) any Go development requiring adherence to established style guidelines. Includes comprehensive linting configuration and detailed style guide.
Remove AI-generated code slop from current branch. Identifies and removes inconsistent comments, over-defensive code patterns, and style mismatches introduced by AI. Use when: cleaning up AI-generated code, before committing AI changes, after code generation session.
Reviews a codebase for style consistency, patterns, idioms, and adherence to KISS, DRY, POLA, and YAGNI principles. Automatically detects languages/frameworks present and applies appropriate analysis. Use when performing code audits, before major refactoring, or to establish coding standards. Outputs timestamped findings to CODEBASE_REVIEW.md with actionable tasks.
Codex CLI（read-only）を用いて、レビュー→Claude Code修正→再レビュー（ok: true まで）を反復し収束させるレビューゲート。仕様書/SPEC/PRD/要件定義/設計、実装計画（PLANS.md等）の作成・更新直後、major step（>=5 files / 新規モジュール / 公開API / infra・config変更）完了後、および git commit / PR / merge / release 前に使用する。キーワード: Codexレビュー, codex review, レビューゲート.
This skill automatically detects when CLAUDE.md files need updates based on codebase analysis. It identifies new patterns, code violations, stale documentation, and anti-patterns, then proposes specific markdown diffs showing exactly what CLAUDE.md sections should be added, modified, or removed. When codebase architecture changes, new patterns emerge, or documented practices diverge from actual code, this skill analyzes the robo-trader project structure and generates actionable recommendations with confidence scores. Should be invoked after major feature completions, during code reviews, or as periodic maintenance scans.
Remove AI-generated code patterns ("slop") from a branch. Use when asked to clean up AI-generated code, remove slop, fix AI coding style issues, or make AI-written code look human-written. Triggers on phrases like "remove slop", "clean up AI code", "fix AI style", or "make this look human-written".
Automatic code quality and best practices analysis. Use proactively when files are modified, saved, or committed. Analyzes code style, patterns, potential bugs, and security basics. Triggers on file changes, git diff, code edits, quality mentions.
Use when you want Codex to invoke the local Gemini CLI (`gemini`) to generate/rewrite/summarize/review content (code, diffs, docs). The workflow runs `gemini` in one-shot or prompt-interactive mode, captures output, then lets Codex decide the next concrete actions (edits, tests, follow-up prompts).
