测试中, 用户明确指定执行 merging-parallel-work 时候才执行, 其余情况一律不执行
/plugin marketplace add taptap/claude-plugins-marketplace/plugin install spec@taptap-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
当 implementing-from-task 判断需要并行执行时自动触发:
为每个独立模块创建 worktree:
# 主分支
git checkout -b feat-PROJ-12345-main
# 为每个模块创建 worktree
git worktree add ../worktree-module-a -b feat-PROJ-12345-module-a
git worktree add ../worktree-module-b -b feat-PROJ-12345-module-b
每个 worktree 对应一组独立任务:
各 agent 在各自 worktree 中独立工作:
按顺序合并各模块分支到主分支:
# 切换到主分支
git checkout feat-PROJ-12345-main
# 合并第一个模块
git merge feat-PROJ-12345-module-a
# 合并第二个模块
git merge feat-PROJ-12345-module-b
遇到冲突时的 AI 解决策略:
分析冲突类型
尝试自动解决
# 查看冲突文件
git diff --name-only --diff-filter=U
# 分析冲突内容
git diff
解决后验证
无法自动解决时
<<<NEEDS_HUMAN_REVIEW>>>合并完成后清理:
# 删除 worktree
git worktree remove ../worktree-module-a
git worktree remove ../worktree-module-b
# 删除临时分支
git branch -d feat-PROJ-12345-module-a
git branch -d feat-PROJ-12345-module-b
调用 /commit-push-pr 创建统一的 Merge Request。
合并完成后输出报告:
## 合并报告
### 合并的分支
- feat-PROJ-12345-module-a ✅
- feat-PROJ-12345-module-b ✅
### 冲突解决
| 文件 | 冲突类型 | 解决方式 |
|------|---------|---------|
| go.mod | 依赖版本 | 使用较新版本 |
| api/handler.go | Import | 合并去重 |
### 需要人工检查
- 无 / 或列出需要检查的文件
### 验证结果
- Lint: ✅
- Test: ✅
- Build: ✅
如果合并失败且无法自动解决:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.