LLM 與 Agent

Use when writing or creating new Standard Operating Procedures (SOPs) for AI agents. Covers effective SOP writing, clarity principles, and actionable instruction design.

Reconcile workflow state files to ensure checkpoints are properly updated. Use when state files are out of sync, after subagent completion without handoff, when switching workflows, or when user runs /reconcile command.

Multi-agent parallel investigation for complex JUCE problems. Use when troubleshooting fails after Level 3, problems require novel research, or user requests /research command.

Use when writing SOPs that require precise requirement levels using RFC 2119 constraint keywords (MUST, SHOULD, MAY). Covers proper usage of requirement keywords for deterministic agent behavior.

Validates audio plugins through automated tests, pluginval, or manual DAW testing. Use for MANUAL testing via /test command. Note - Automatic validation now built into workflow (validation-agent runs after each stage). This skill is for manual testing only, after bug fixes, or when user mentions test, validate, validation, pluginval, stability, automated tests, run tests, check plugin, or quality assurance.

This skill automates version bumping during the release process for the Claude Code Handbook monorepo. It should be used when the user requests to bump versions, prepare a release, or increment version numbers across the repository.

Orchestrates JUCE plugin implementation through stages 1-3 (Foundation, DSP, GUI) using subagent delegation with automatic validation after each stage. Use when implementing plugins after planning completes, or when resuming with /continue command. Invoked by /implement command.

Automates Navigator plugin updates. Detects current version, updates plugin, verifies installation, updates project CLAUDE.md, and validates new features. Auto-invoke when user mentions upgrading Navigator or getting new features.

System setup, tool information, and AI configuration management for development environments. Use when setting up new machines, explaining available tools (shell-config, ai-rules, wt), managing AI assistant configurations (Claude/Codex/Gemini/OpenCode), checking system configuration, or troubleshooting environment issues. Also triggers when working with configuration files (.json, .toml, .fish, .zsh, .bash), Brewfiles, or installation scripts. Example triggers: "Set up my development environment", "Install tools on new machine", "Configure AI assistant", "What tools do I have?", "Update my shell config", "Add MCP server to Claude", "Check system configuration"

Use it when the user asks to "ask gemini", "ask codex", or "ask in browser"

Install Navigator multi-Claude workflow orchestration scripts. Auto-invokes when user says "install multi-Claude workflows", "set up multi-Claude", or "enable parallel execution".

Update project CLAUDE.md to latest Navigator version, preserving customizations. Use when user says "update CLAUDE.md", "migrate to v3", or when detecting outdated Navigator configuration.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Build full-stack web applications powered by Google Gemini's Nano Banana & Nano Banana Pro image generation APIs. Use when creating Next.js image generators, editors, galleries, or any web app that integrates gemini-2.5-flash-image or gemini-3-pro-image-preview models. Covers React components, server actions, API routes, storage, rate limiting, and production deployment patterns.

Your approach to handling testing coverage. Use this skill when working on files where testing coverage comes into play.

Optimizes content for Generative Engine Optimization (GEO) to increase chances of being cited by AI systems like ChatGPT, Claude, Perplexity, and Google AI Overviews. Makes content AI-friendly while maintaining SEO value.

Create and configure Claude Code hooks for customizing agent behavior. Use when the user wants to (1) create a new hook, (2) configure automatic formatting, logging, or notifications, (3) add file protection or custom permissions, (4) set up pre/post tool execution actions, or (5) asks about hook events like PreToolUse, PostToolUse, Notification, etc.

Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode. Defines scale determination, document requirements, and stop points.

Frontend testing rules with Vitest, React Testing Library, and MSW. Includes coverage requirements, test design principles, and quality criteria. Use when writing frontend tests or reviewing test quality.

Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.