Dispatching Parallel Agents by bobmatnyc/claude-mpm-skills
npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill 'Dispatching Parallel Agents'当多个不相关的故障同时发生时(不同的测试文件、不同的子系统、不同的错误),按顺序逐一调查会浪费时间。每个调查都是独立的,可以并行进行。
核心原则: 为每个独立的问题域分配一个智能体。让它们并发工作。
在面临以下情况时激活此技能:
不要用于以下情况:
One agent, one problem domain, one clear outcome.
Never overlap scopes. Never share state. Always integrate consciously.
问题必须真正独立 - 没有共享文件,没有相关的根本原因,修复之间没有依赖关系。
每个智能体获得狭窄的范围:一个测试文件、一个子系统、一个明确的目标。宽泛的任务会导致混乱。
每个智能体必须返回一个摘要:发现了什么、修复了什么、改变了什么。不允许静默修复。
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
不要盲目合并智能体的工作。审查摘要,检查冲突,运行完整测试套件,验证兼容性。
根据损坏的内容对故障进行分组:
File A tests: Tool approval flow
File B tests: Batch completion behavior
File C tests: Abort functionality
每个领域都是独立的 - 修复工具批准流程不会影响中止功能测试。
每个智能体获得:
→ agent-prompts.md 获取提示模板和示例
// In Claude Code / AI environment
Task("Fix agent-tool-abort.test.ts failures")
Task("Fix batch-completion-behavior.test.ts failures")
Task("Fix tool-approval-race-conditions.test.ts failures")
// All three run concurrently
→ coordination-patterns.md 获取调度策略
当智能体返回时:
→ troubleshooting.md 获取冲突解决方法
Multiple failures?
└→ Are they independent?
├→ NO (related) → Single agent investigates all
└→ YES → Can they work in parallel?
├→ NO (shared state) → Sequential agents
└→ YES → Parallel dispatch ✓
调度并行智能体时,请考虑以下互补技能(可在技能库中找到):
如果出现以下情况,请立即停止:
如有疑问: 从一个智能体开始,了解整体情况,如果确实独立,再进行调度。
先决条件: 对问题领域和测试结构的基本理解 互补: PM-Workflow技能用于协调多个智能体(参见技能库) 领域特定: 用于理解测试失败的测试技能(可在技能库中找到)
来自调试会话(2025-10-03):
→ examples.md 获取详细案例研究
每周安装量
0
代码仓库
GitHub 星标数
20
首次出现
1970年1月1日
安全审计
When multiple unrelated failures occur (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.
Activate this skill when facing:
Don't use when:
One agent, one problem domain, one clear outcome.
Never overlap scopes. Never share state. Always integrate consciously.
Problems must be truly independent - no shared files, no related root causes, no dependencies between fixes.
Each agent gets narrow scope: one test file, one subsystem, one clear goal. Broad tasks lead to confusion.
Every agent must return a summary: what was found, what was fixed, what changed. No silent fixes.
Don't blindly merge agent work. Review summaries, check conflicts, run full suite, verify compatibility.
Group failures by what's broken:
File A tests: Tool approval flow
File B tests: Batch completion behavior
File C tests: Abort functionality
Each domain is independent - fixing tool approval doesn't affect abort tests.
Each agent gets:
→ agent-prompts.md for prompt templates and examples
// In Claude Code / AI environment
Task("Fix agent-tool-abort.test.ts failures")
Task("Fix batch-completion-behavior.test.ts failures")
Task("Fix tool-approval-race-conditions.test.ts failures")
// All three run concurrently
→ coordination-patterns.md for dispatch strategies
When agents return:
→ troubleshooting.md for conflict resolution
Multiple failures?
└→ Are they independent?
├→ NO (related) → Single agent investigates all
└→ YES → Can they work in parallel?
├→ NO (shared state) → Sequential agents
└→ YES → Parallel dispatch ✓
When dispatching parallel agents, consider these complementary skills (available in the skill library):
STOP immediately if:
When in doubt: Start with one agent, understand the landscape, then dispatch if truly independent.
Prerequisite: Basic understanding of problem domains and test structure Complementary: PM-Workflow skill for coordinating multiple agents (see skill library) Domain-specific: Testing skills for understanding test failures (available in skill library)
From debugging session (2025-10-03):
→ examples.md for detailed case study
Weekly Installs
0
Repository
GitHub Stars
20
First Seen
Jan 1, 1970
Security Audits
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
60,400 周安装
Docnify自动化:通过Rube MCP和Composio工具包实现文档操作自动化
1 周安装
Docmosis自动化集成指南:通过Rube MCP与Composio实现文档生成自动化
1 周安装
Dictionary API自动化教程:通过Rube MCP和Composio实现词典API操作自动化
1 周安装
detrack-automation:自动化追踪技能,集成Claude AI提升开发效率
1 周安装
Demio自动化工具包:通过Rube MCP和Composio实现Demio操作自动化
1 周安装
Deel自动化工具:通过Rube MCP与Composio实现HR与薪资操作自动化
1 周安装