Tools & Utilities
Essential command-line tools and system utilities.
update-test-snapshots
Regenerate test snapshot files after intentional markdown output changes. Use after modifying templates or rendering logic.
github-gist-api
GitHub Gist API を使用したコードを書く際に使用。Gist作成、GistHack URL変換、ky/zod を使った実装パターンを提供。
github-security-review
Analyze GitHub repository security alerts and generate remediation plans. Use when the user asks to review security alerts, fix vulnerabilities, check dependabot alerts, review code scanning issues, or address secret scanning findings for a GitHub repository. Triggers on requests mentioning GitHub security, repo security review, vulnerability remediation, or security audit.
spec-writing
Use during Phase 3 of spec creation to create specification document - searches codebase for reusable patterns, presents spec in validated 150-200 word sections, and saves complete specification following template structure
auto-build
プロジェクトタイプを自動検出してビルドを実行するスキル。コード変更後にビルドを提案、エラー発生時は修正案を提示。Node.js、Rust、Python、Go、Makefileプロジェクトに対応。
agent-config-maintenance
Refactor Codex configuration files and Agent Skills by splitting concerns, deduplicating instructions, and reorganizing guidance across AGENTS.md, project docs, and skills. Use when asked to clean up AGENTS.md, move instructions into skill bundles, or standardize agent setup rules.
code-conventions
프로젝트 코딩 컨벤션 (네이밍 규칙, 폴더 구조, 컴포넌트 패턴). 새 파일/컴포넌트 생성, 프로젝트 구조 질문 시 사용.
sync-from-vibe-workflow
Sync skills from claude-code-plugins vibe-workflow to this codex-workflow repo. Adapts Claude Code features to Codex equivalents. Use when vibe-workflow has updates to sync.
encrypt-backup
Encrypt folders using GPG for backup. Use when user wants to backup or encrypt sensitive directories.
refactoring
Safe code refactoring with test protection and incremental changes. Improves structure without changing behavior. Use when extracting methods, reducing duplication, or restructuring code.
refactoring-workflow
Complete refactoring workflow with tracking, validation, and cross-layer impact checklists. Integrates with beads for progress tracking and ensures no references to old names remain after refactoring.
discovery-first
Use pre-computed discovery files at .claude/state/ for codebase inventory questions. Triggers on component, hook, schema, form, type, inventory, what exists, list all, how many. Saves 90%+ tokens vs source scanning.
large-file-refactor
Use when Claude Code hits "File content exceeds maximum allowed tokens" error, or when files are too large to read. Helps analyze and break apart large files into smaller, focused modules.
design-implementation-reviewer
Use this agent when you need to verify that a UI implementation matches its Figma design specifications. This agent should be called after code has been written to implement a design, particularly after HTML/CSS/React components have been created or modified. The agent will visually compare the live implementation against the Figma design and provide detailed feedback on discrepancies.\n\nExamples:\n- <example>\n Context: The user has just implemented a new component based on a Figma design.\n user: "I've finished implementing the hero section based on the Figma design"\n assistant: "I'll review how well your implementation matches the Figma design."\n <commentary>\n Since UI implementation has been completed, use the design-implementation-reviewer agent to compare the live version with Figma.\n </commentary>\n </example>\n- <example>\n Context: After the general code agent has implemented design changes.\n user: "Update the button styles to match the new design system"\n assistant: "I've updated th
quick-start-to-code
Prepare development environment for immediate coding by orchestrating memory loading, context validation, and pre-flight checks all in one interaction. Eliminates the need for multiple manual slash commands (/memory-read, /standards-check, /arch-check) before starting work. Use when the user says "ready to code", "start coding", "let's implement", "begin development", "coding time", or needs to transition from planning directly to implementation without manual warm-up.
code-reviewer
Assists with code review by analyzing code changes for quality, best practices, security, and potential issues. Activates after implementing code features, bug fixes, or refactorings. Provides structured feedback with critical issues, suggestions, and positive highlights.
iterative-refinement
Execute iterative refinement workflows with validation loops until quality criteria are met. Use for test-fix cycles, code quality improvement, performance optimization, or any task requiring repeated action-validate-improve cycles.
layered-summary
Create hierarchical, bottom-up "layered summaries" by generating `AGENTS.md` files per directory in a subtree (e.g., `reth/crates/engine`). Deep directories summarize files and key APIs; parent directories roll up children. Use when you need a navigable architecture map and per-module responsibilities without code snippets, while ensuring no subfolders are missed via explicit coverage checklists.
code-search-selector
⚡ AUTO-INVOKE when user asks: 'audit', 'investigate', 'how does X work', 'find all', 'where is', 'trace', 'understand', 'map the codebase', 'comprehensive'. MUST run BEFORE Read/Glob when planning to read 3+ files. Prevents tool familiarity bias toward native tools.
typo3-rector
TYPO3 upgrade patterns using Rector, including automated refactoring rules and dual-version compatibility strategies for v13/v14.
implementation
Writes new features, refactors code, implements functionality following best practices
mcp-documentation-skill
DEPRECATED - This skill references MCP servers that no longer exist in the codebase. The CodebaseDocumentation server was archived during MCP cleanup. Use native file reading tools (view_file, grep_search) for documentation access.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
