parallel-agent-dispatch
仓库创建 2026年3月12日最近提交 21 天前SkillHot 收录 20 天前
▸ 精选理由
把复杂工作拆成并行子任务,显著降低人工协调成本。
▸ 风险提示
可能生成大量并发任务,消耗资源或无意泄露上下文
这个 Skill 做什么
将多个独立任务分派给互不共享上下文的并行子代理处理。
当有两个及以上互不依赖的独立任务时,把它们分派给并行的子代理来做,每个子代理互不共享上下文。用在需要同时处理多块问题、提高吞吐量或并行修复时。特别在于精确构造每个子代理的指令与上下文,避免历史污染主会话。
▸ 展开 SKILL.md 英文原文
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Trigger on 'fix all these', 'handle in parallel', 'dispatch agents', or when identifying multiple independent problem domains.
0
Stars
0
Forks
16
仓库内 Skill
+0
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/huanlongAI/tzh-Harness/main/cowork-skills/parallel-agent-dispatch/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/huanlongAI/tzh-Harness/main/cowork-skills/parallel-agent-dispatch/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Dispatching Parallel Agents ## Overview You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work. When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel. **Core principle:** Dispatch one agent per independent problem domain. Let them work concurrently. ## When t
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有