開發

Use when writing or reviewing Bash scripts to apply defensive programming patterns including strict mode, proper error handling, safe variable handling, argument parsing, and idempotent design. Ensures scripts are robust, maintainable, and production-ready.

Enforce test quality and prevent implementation shortcuts when writing or modifying code. Use when implementing features, fixing bugs, or refactoring code. Prevents test tampering (FP-1) and implementation shortcuts (FP-2).

Adds static typing to JavaScript with TypeScript including type annotations, interfaces, generics, and advanced type utilities. Use when setting up TypeScript projects, defining types, creating generic utilities, or debugging type errors.

This skill should be used when reviewing, auditing, or improving existing Claude Code skills to ensure they follow Anthropic best practices, have proper structure, use current domain-specific patterns, and include all necessary resources. It analyzes skill quality, identifies gaps, suggests improvements, and can automatically enhance skills with updated best practices. Trigger terms include review skill, audit skill, improve skill, enhance skill, update skill, check skill quality, skill best practices, fix skill, optimize skill, validate skill structure.

This skill should be used when translating a spec into code using parallel subagents. Use when the orchestrator invokes the implement phase or when executing a well-defined implementation plan.

Automated tooling and detection patterns for analyzing npm dependencies, unused packages, and dead code. Provides tool commands and what to look for—not how to structure output.

Expert front-end design critique, refinement, and polish for existing interfaces. Use this skill when the user asks for a design pass, visual polish, design critique, aesthetic improvements, or UI refinement on existing code or interfaces. Works with React artifacts, full websites, and any frontend framework. Generates colour palettes and typography from scratch. Focuses on visual aesthetics, micro-interactions, and avoiding generic AI aesthetics. Complementary to tech-building skills—use after functionality is built.

Build type-safe LLM applications with DSPy.rb - Ruby's programmatic prompt framework with signatures, modules, agents, and optimization

Use when animating notifications, toasts, alerts, snackbars, or system messages to grab attention appropriately

Document placement rules, visibility protocols, and timeline test (before-code vs after-code). Defines where documentation belongs (dev/docs/ vs coordination/), documentation-first PR protocol, and phase artifact placement. Critical for documentation organization and visibility.

Setup state management for React applications using Zustand, TanStack Query, and React Hook Form. Use when users need to manage client state, server state, or form state. Covers store patterns, caching strategies, and form validation.

Use when exploring Python project structure, finding virtualenv paths (python/pip/pytest), or locating package metadata (name, version, pyproject.toml).

Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies

Production-ready Cobra CLI patterns including command structure, flags (local and persistent), nested commands, PreRun/PostRun hooks, argument validation, and initialization patterns used by kubectl and hugo. Use when building Go CLIs, implementing Cobra commands, creating nested command structures, managing flags, validating arguments, or when user mentions Cobra, CLI development, command-line tools, kubectl patterns, or Go CLI frameworks.

Orchestrator for WebView UI mockup workflow - delegates design iteration to ui-design-agent and implementation scaffolding to ui-finalization-agent. Use when user mentions UI design, mockup, WebView interface, or requests 'design UI for [plugin]'.

cc-plugins 프로젝트 개발 가이드라인, 레퍼런스 패턴, 프로젝트 구조 조회. Use when Claude needs to (1) Look up development principles (P1-P4, DRY, KISS, YAGNI, SOLID), (2) Find reference patterns for Hooks/Agents/Commands creation, (3) Understand project structure and file locations, (4) Learn how to create Skills/Hooks/Agents/Commands, or (5) Delegate to claude-code-guide for official Claude Code documentation

Claude Code context window optimization strategies, JIT retrieval, progressive loading, memory file patterns, and cleanup practices. Use when optimizing context usage, managing large projects, or implementing efficient workflows.

Use this when user requests code review, pull request analysis, or quality assessment. Provides systematic 6-category checklist: functionality, security (OWASP), code quality (SOLID), performance, testing, and maintainability. Apply for PR reviews, security audits, or teaching code quality principles

Create, manage, and cleanup git worktrees with Claude Code agents across all projects. USE THIS SKILL when user says "create worktree", "spin up worktrees", "new worktree for X", "worktree status", "cleanup worktrees", or wants parallel development branches. Handles worktree creation, dependency installation, validation, agent launching in Ghostty, and global registry management.

Thorough code review for Rust/WebAssembly projects. Identifies bugs, securityissues, performance problems, and maintainability concerns. Provides actionablefeedback with specific suggestions.