القائمة
Multi-agent workspace collaboration via git worktrees. Use when managing parallel agents in the same repo, creating isolated workspaces, coordinating merge between agent branches, or running Best-of-N parallel execution.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
| name | worktree |
| description | Multi-agent workspace collaboration via git worktrees. Use when managing parallel agents in the same repo, creating isolated workspaces, coordinating merge between agent branches, or running Best-of-N parallel execution. |
当多个 Agent 在同一个 Git 仓库中并行工作时，使用 git worktree 创建隔离的工作目录，避免文件冲突。
支持三种场景：对等 Session 自动检测、SubAgent 模式、Best-of-N 并行执行。
| 概念 | 说明 |
|---|---|
| 主工作区 | 原始仓库目录，第一个 Agent 直接使用 |
| Worktree | 独立工作目录，链接到主仓库 .git 对象库 |
| 对等发现 | 新 Agent 启动时检测到同伴后自动创建 worktree |
| 合并协调 | Agent 完成后通过 SendMessage 通知同伴协商合并 |
当你被启动时，Worktree 工具会自动检测当前仓库是否有其他 Agent 在工作：
主 Agent 为子 Agent 创建 worktree：
# 创建 worktree
git worktree add ../.xbot-worktrees/<agent-id> -b agent/<agent-id>/<timestamp>
# 创建 SubAgent 时传递 worktree 路径作为 parent_cwd
子 Agent 在 worktree 中独立工作，完成后主 Agent 合并。
对同一任务并行尝试多个方案，选最优结果：
操作步骤：
# Agent 为每个 Best-of-N 实例调用 Worktree tool
Worktree(action="init", role="bestof", instance="bestof-1", task="实现用户登录")
Worktree(action="init", role="bestof", instance="bestof-2", task="实现用户登录")
Worktree(action="init", role="bestof", instance="bestof-3", task="实现用户登录")
SubAgent(task="实现用户登录功能...", role="implementer", instance="bestof-1", interactive=true)
SubAgent(task="实现用户登录功能...", role="implementer", instance="bestof-2", interactive=true)
SubAgent(task="实现用户登录功能...", role="implementer", instance="bestof-3", interactive=true)
所有 Agent 完成后，收集结果对比：
向用户展示对比结果，用户选择最佳方案
合并选中方案的分支：git merge --no-ff agent/bestof/bestof-N/<task>
清理未选中的 worktree：Worktree(action="cleanup")
Agent 之间通过 SendMessage 使用结构化 JSON 报文：
{
"protocol": "xbot.merge-coordination.v1",
"type": "ready | conflict-proposal | accept | escalate",
"agent": {"id": "...", "branch": "...", "worktree": "..."},
"payload": {
"files": ["src/auth/login.go"],
"diff_brief": "重构了 JWT 验证逻辑",
"conflicts": [{"file": "...", "line_range": "42-67"}],
"proposed_resolution": "...",
"rationale": "..."
}
}
| 冲突类型 | 处理方式 |
|---|---|
| 文件无重叠 | 自动合并 |
| 测试文件冲突 | tester 版本优先 |
| 源码文本冲突 Agent 达成一致 | 协商解决 |
| 3 轮协商无果或语义冲突 | 提交用户仲裁 |
主 Agent 执行 git merge --no-ff <branch>，保留每个 Agent 工作为独立 merge commit。
# 提交更改
git add -A && git commit -m "Agent work completed"
# 切回主工作区后删除 worktree
git worktree remove ../.xbot-worktrees/<agent-id> --force
git branch -d agent/<agent-id>/<timestamp>
{repo}/../.xbot-worktrees/استنادا إلى تصنيف SOC المهني
Manage SubAgent roles: create, view, modify, delete, or install agent definitions. MUST activate when user asks to create/edit/view/inspect any agent, install agents from external sources, or when you need to look at agent files under ~/.xbot/agents/. Agents are universal — install whatever the user needs.
Create, modify, and manage xbot plugins. Use when the user asks to create a plugin, set up script plugins, configure widgets, register custom tools via plugins, or create channel plugins.
Create, update, delete, or install skills. Use when the user asks to create a new skill, modify an existing skill, install/import a skill from external sources (GitHub, URLs), package scripts/assets into a skill, or discusses skill design and structure. Skills are universal agent capabilities — install whatever the user wants.
Guide for AI to configure xbot TUI, themes, subscriptions, and settings. Activate when the user asks to customize the TUI appearance, create themes, manage LLM subscriptions, or make bulk configuration changes.
Build implementation plans for complex tasks. Use when the user asks to plan, design an approach, or think through a task before coding. Also activate for large refactorings, multi-file changes, or when the user says 'plan first' or '/plan'.
Post-development cleanup: update AGENTS.md and docs/agent/ knowledge files to reflect code changes. MUST activate before git commit (or when user asks to commit/push). Also activate after any code modification that adds/removes files, changes architecture, or modifies core behavior.
