xu-xiang

Multi Execute — AI skill for Claude Code

AI community

执行 - 多模型协作执行 (Multi-Model Collaborative Execution).

How to install Multi Execute

Installs to ~/.claude/skills/xu-xiang-everything-claude-code-zh-multi-execute/SKILL.md

Terminal

mkdir -p ~/.claude/skills/xu-xiang-everything-claude-code-zh-multi-execute && curl -fsSL https://raw.githubusercontent.com/xu-xiang/everything-claude-code-zh/HEAD/commands/multi-execute.md -o ~/.claude/skills/xu-xiang-everything-claude-code-zh-multi-execute/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Multi Execute does

执行 - 多模型协作执行 (Multi-Model Collaborative Execution)

多模型协作执行 - 从方案获取原型 → Claude 重构并实现 → 多模型审计与交付。

$ARGUMENTS

核心协议 (Core Protocols)

语言协议 (Language Protocol)：与工具/模型交互时使用英语，与用户交流时使用用户的母语
代码主权 (Code Sovereignty)：外部模型 没有文件系统写入权限，所有修改均由 Claude 执行
粗糙原型重构 (Dirty Prototype Refactoring)：将 Codex/Gemini 的 Unified Diff 视为“粗糙原型”，必须重构为生产级代码
止损机制 (Stop-Loss Mechanism)：在当前阶段输出通过验证前，不得进入下一阶段
前提条件 (Prerequisite)：仅在用户对 /ccg:plan 的输出明确回复 "Y" 后执行（如果缺失，必须先确认）

Alternatives in AI

Oh My Claudecode — 32 specialized agents and 7 execution modes for Claude Code, with smart model routing and automatic paralleliz 10.9k ★
Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
Osaurus — Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cry 5.1k ★