Agent Playbook A collection of practical guides, prompts, and skills for AI Agents (Claude Code) English 简体中文 Overview This repository collects practical, public facing building blocks for AI agents: reusable skills, prompt patterns, workflow docs, and tooling for Claude Code, Codex, and Gemini. Everything in this repository is intended to stay portable and abstract. Private operating details, company specific workflows, and sensitive business context should live elsewhere. What you get Reusable skills with focused SKILL.md files and deeper references/ material Installation and lifecycle tooling through @codeharbor/agent playbook An MCP server for skill discovery Workflow docs for planning, self improvement, automation, and context design Design Principles The repository is evolving around a few portable agent design rules: Keep hard constraints always on, but keep them short Turn reusable methods into skills Keep detailed facts and examples retrievable from references and docs Persist long running task state outside chat so recovery is reliable Further reading: Context Layering for Agent Playbooks Skill Ecosystem References long task coordinator Who this is for Builders creating their own reusable agent skills Teams standardizing how agents plan, review, and recover work Power users who want local first tooling instead of SaaS heavy orchestration Installation Method 0: One Command Installer (PNPM/NPM) Sets up skills for Claude Code, Codex, and Gemini. It currently wires session logging and self improvement hooks for Claude Code, records an agent playbook metadata block for Codex, and prepares Gemini skill directories. [安装/使用命令见下方] Project only setup: [安装/使用命令见下方] Method 1: Symbolic Links (Recommended) Link the skills to your global skills directories: [安装/使用命令见下方] Example: [安装/使用命令见下方] Method 2: Copy Skills Copy the skills directly to your global skills directories: [安装/使用命令见下方] Method 3: Add to Project Specific Skills For project specific usage, create .claude/.co