agent-spec
Claude Code プラグインの agent 仕様知識。サブエージェントの正しい形式、フロントマター、tools/model/skills フィールドを提供。Use when creating, updating, or maintaining agents, understanding agent structure, or...
Skills matching the name, description or GitHub author.
Claude Code プラグインの agent 仕様知識。サブエージェントの正しい形式、フロントマター、tools/model/skills フィールドを提供。Use when creating, updating, or maintaining agents, understanding agent structure, or...
Claude Code プラグインの skill 仕様知識。スキルの正しい形式、フロントマター、description のベストプラクティスを提供。Use when creating, updating, or maintaining skills, understanding skill structure, or impleme...
Autonomous codebase improvement mode that continuously analyzes and fixes issues. Use when the user wants Claude to run in a self-directed loop to improve code quality, fix bugs, refactor, or make architectural...
Query Claude Code configuration, file locations, MCP settings, and official documentation. Use this skill proactively when the conversation involves: - Claude Code settings, configuration, config, settings - MC...
Activate when users ask about Claude Code installation, slash commands (/cook, /plan, /fix, /test, /docs, /design, /git), creating/managing Agent Skills, configuring MCP servers, setting up hooks/plugins, IDE i...
Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Use when creating Claude Code extension...
Iterative writing loop. Gemini 3 Pro writes, Claude Agent SDK reviews autonomously. Use for blog posts, docs, technical content needing quality iteration.
Build custom Model Context Protocol servers to extend Claude's capabilities
Complete guide to using Sequential Thinking MCP server with Claude Code
Build custom Model Context Protocol servers to extend Claude's capabilities
Complete guide to using Supabase MCP servers with Claude Code
Complete guide to using Serena MCP server for AI-powered code analysis with Claude Code
AI-assisted code generation workflows, prompting strategies, and best practices for working with Claude Code
Spawn and control external coding agents (Claude Code, Codex, OpenCode, Pi) for delegating tasks. Use when (1) user asks to run another coding agent, (2) delegating subtasks to a different AI tool, (3) running...
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 to...
Expert for Claude Code plugin and marketplace development. Use when creating, editing, or optimizing skills (SKILL.md), commands (*.md), agents, hooks (hooks.json), scripts, or plugin.json files. Ensures consis...
Optimizes this Claude Code marketplace using specialized sub-agents. Each agent is an expert for one element type (skills, commands, agents, hooks, mcp) and loads only relevant documentation. A marketplace agen...
Integrate Ralph with your project's existing CLAUDE.md files, skills, and agent preferences. Run after installing Ralph, or rerun anytime you add new skills/agents.
Use when user asks to "create a skill", "build a skill", or "design a skill". Guides through requirements, solution design, and implementation of token-efficient Claude Code skills.
ai-tools同期 - リポジトリと~/.claude/間の設定ファイル同期。to-local/from-local/diffモード。
This skill should be used for autonomous work on complex tasks with ZERO context required. Triggers include "start a loop", "work autonomously", "before I sleep", "take this and run with it", or when claude det...
This skill should be used when creating or refactoring Claude Code skills, guiding an interactive questionnaire, selecting an archetype (workflow/tool/domain), scaffolding from templates, and validating the res...
This skill should be used for autonomous work on complex tasks with ZERO context required. Triggers include "start a loop", "work autonomously", "before I sleep", "take this and run with it", or when claude det...
Create a new backend agent for the Claude Assistant Platform. Use when adding a new specialized agent, scaffolding an agent, or when the user says "create agent", "add agent", "new agent", or "scaffold agent".
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.