dispatch-agents
Use when you have 2+ independent tasks with no shared state — dispatches parallel subagents for each task.
它会碰到什么
扫了多少1 个文本文件，1 KB
它会碰到什么不碰外部（只输出文字）
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0
这一栏是扫描器报的事实，不是结论。命中多不等于有毒（安全工具、规则库、示例脚本本来就会包含危险写法），命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系，需要你自己看。
技能内容
Dispatching Parallel Agents
When to Use
- Tasks are truly independent (no shared files, no sequential dependency)
- Each task is well-defined with clear success criteria
- 2-5 tasks in parallel (more than 5 becomes hard to review)
Process
- List all tasks and confirm independence
- For each task, write a self-contained prompt including:
- Full context (don't assume agent knows anything)
- Exact files to touch
- Success criteria
- How to verify
- Dispatch all agents simultaneously using the Agent tool
- Collect results and merge
- Run verification across all changes together
- Invoke
requesting-code-reviewto dispatch thecode-revieweragent on merged result, then handle findings viareceiving-code-review
Safety
Never dispatch agents for tasks involving shared state — race conditions and conflicts will waste more time than sequential execution saves.
想直接用这个技能？
本站把开放许可（MIT / Apache 等）的技能按仓库打包整理到网盘，点一下转存到你自己的网盘，不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接，不打包。
它属于哪个仓库
星标★ 1,027
本站分层T1
该仓技能数1910
原文件路径
plugins/yimwoo/hotl-plugin/skills/dispatch-agents/SKILL.md