multi-agent-task-orchestrator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Multi-Agent Task Orchestrator

多Agent任务编排器

Overview

概述

A production-tested pattern for coordinating multiple AI agents through a single orchestrator. Instead of letting agents work independently (and conflict), one orchestrator decomposes tasks, routes them to specialists, prevents duplicate work, and verifies results before marking anything done. Battle-tested across 10,000+ tasks over 6 months.

这是一种经过生产验证的模式，通过单个Orchestrator（编排器）协调多个AI Agent。不同于让Agent独立工作（并产生冲突），编排器会分解任务，将其分配给专业Agent，防止重复工作，并在标记任务完成前验证结果。该模式已在6个月内完成10000+任务的实战检验。

When to Use This Skill

何时使用该技能

Use when you have 3+ specialized agents that need to coordinate on complex tasks
Use when agents are doing duplicate or conflicting work
Use when you need audit trails showing who did what and when
Use when agent output quality is inconsistent and needs verification gates

当你拥有3个及以上需要协同完成复杂任务的专业Agent时使用
当Agent出现重复或冲突工作时使用
当你需要记录谁在何时完成了什么的审计轨迹时使用
当Agent输出质量不稳定，需要验证关卡时使用

How It Works

工作原理

Step 1: Define the Orchestrator Identity

步骤1：定义编排器身份

The orchestrator must know what it IS and what it IS NOT. This prevents it from doing work instead of delegating:

You are the Task Orchestrator. You NEVER do specialized work yourself.
You decompose tasks, delegate to the right agent, prevent conflicts,
and verify quality before marking anything done.

WHAT YOU ARE NOT:
- NOT a code writer — delegate to code agents
- NOT a researcher — delegate to research agents
- NOT a tester — delegate to test agents

This "NOT-block" pattern reduces task drift by ~35% in production.

编排器必须明确自己的职责边界，避免亲自执行任务而非委派：

You are the Task Orchestrator. You NEVER do specialized work yourself.
You decompose tasks, delegate to the right agent, prevent conflicts,
and verify quality before marking anything done.

WHAT YOU ARE NOT:
- NOT a code writer — delegate to code agents
- NOT a researcher — delegate to research agents
- NOT a tester — delegate to test agents

这种“禁止事项”模式在生产环境中可减少约35%的任务偏离。

Step 2: Build a Task Registry

步骤2：构建任务注册表

Before assigning work, check if anyone is already doing this task:

python

import sqlite3
from difflib import SequenceMatcher

def check_duplicate(description, threshold=0.55):
    conn = sqlite3.connect("task_registry.db")
    c = conn.cursor()
    c.execute("SELECT id, description, agent, status FROM tasks WHERE status IN ('pending', 'in_progress')")
    for row in c.fetchall():
        ratio = SequenceMatcher(None, description.lower(), row[1].lower()).ratio()
        if ratio >= threshold:
            return {"id": row[0], "description": row[1], "agent": row[2]}
    return None

分配任务前，检查是否已有Agent在执行该任务：

python

import sqlite3
from difflib import SequenceMatcher

def check_duplicate(description, threshold=0.55):
    conn = sqlite3.connect("task_registry.db")
    c = conn.cursor()
    c.execute("SELECT id, description, agent, status FROM tasks WHERE status IN ('pending', 'in_progress')")
    for row in c.fetchall():
        ratio = SequenceMatcher(None, description.lower(), row[1].lower()).ratio()
        if ratio >= threshold:
            return {"id": row[0], "description": row[1], "agent": row[2]}
    return None

Step 3: Route Tasks to Specialists

步骤3：将任务分配给专业Agent

Use keyword scoring to match tasks to the best agent:

python

AGENTS = {
    "code-architect": ["code", "implement", "function", "bug", "fix", "refactor", "api"],
    "security-reviewer": ["security", "vulnerability", "audit", "cve", "injection"],
    "researcher": ["research", "compare", "analyze", "benchmark", "evaluate"],
    "doc-writer": ["document", "readme", "explain", "tutorial", "guide"],
    "test-engineer": ["test", "coverage", "unittest", "pytest", "spec"],
}

def route_task(description):
    scores = {}
    for agent, keywords in AGENTS.items():
        scores[agent] = sum(1 for kw in keywords if kw in description.lower())
    return max(scores, key=scores.get) if max(scores.values()) > 0 else "code-architect"

使用关键词评分匹配最适合的Agent：

python

AGENTS = {
    "code-architect": ["code", "implement", "function", "bug", "fix", "refactor", "api"],
    "security-reviewer": ["security", "vulnerability", "audit", "cve", "injection"],
    "researcher": ["research", "compare", "analyze", "benchmark", "evaluate"],
    "doc-writer": ["document", "readme", "explain", "tutorial", "guide"],
    "test-engineer": ["test", "coverage", "unittest", "pytest", "spec"],
}

def route_task(description):
    scores = {}
    for agent, keywords in AGENTS.items():
        scores[agent] = sum(1 for kw in keywords if kw in description.lower())
    return max(scores, key=scores.get) if max(scores.values()) > 0 else "code-architect"

Step 4: Enforce Quality Gates

步骤4：执行质量关卡

Agent output is a CLAIM. Test output is EVIDENCE.

After agent reports completion:
1. Were files actually modified? (git diff --stat)
2. Do tests pass? (npm test / pytest)
3. Were secrets introduced? (grep for API keys, tokens)
4. Did the build succeed? (npm run build)
5. Were only intended files touched? (scope check)

Mark done ONLY after ALL checks pass.

Agent的输出只是“声明”，测试输出才是“证据”。

Agent报告完成后：
1. 文件是否真的被修改？（执行git diff --stat）
2. 测试是否通过？（执行npm test / pytest）
3. 是否引入了敏感信息？（搜索API密钥、令牌）
4. 构建是否成功？（执行npm run build）
5. 是否只修改了目标文件？（范围检查）

只有所有检查通过后，才能标记任务完成。

Step 5: Run 30-Minute Heartbeats

步骤5：运行30分钟心跳监控

Every 30 minutes, ask:
1. "What have I DELEGATED in the last 30 minutes?"
2. If nothing → open the task backlog and assign the next task
3. Check for idle agents (no message in >30min on assigned task)
4. Relance idle agents or reassign their tasks

每30分钟执行以下检查：
1. “过去30分钟内我委派了哪些任务？”
2. 如果没有委派任务 → 打开任务待办列表并分配下一个任务
3. 检查是否有空闲Agent（分配任务后30分钟内无消息）
4. 提醒空闲Agent或重新分配其任务

Examples

示例

Example 1: Delegating a Code Task

示例1：委派代码任务

[ORCHESTRATOR -> code-architect] TASK: Add rate limiting to /api/users
SCOPE: src/middleware/rate-limit.ts only
VERIFICATION: npm test -- --grep "rate-limit"
DEADLINE: 30 minutes

[ORCHESTRATOR -> code-architect] TASK: Add rate limiting to /api/users
SCOPE: src/middleware/rate-limit.ts only
VERIFICATION: npm test -- --grep "rate-limit"
DEADLINE: 30 minutes

Example 2: Handling a Duplicate

示例2：处理重复任务

User asks: "Fix the login bug"
Registry check: Task #47 "Fix authentication bug" is IN_PROGRESS by security-reviewer
Decision: SKIP — similar task already assigned (78% match)
Action: Notify user of existing task, wait for completion

用户请求：“修复登录bug”
注册表检查：任务#47“修复认证bug”正在由security-reviewer执行
决策：跳过——已有相似任务分配（匹配度78%）
操作：通知用户已有任务，等待完成

Best Practices

最佳实践

Always define NOT-blocks for every agent (what they must refuse to do)
Use SQLite for the task registry (lightweight, no server needed)
Set similarity threshold at 55% for anti-duplication (lower = too many false positives)
Require evidence-based quality gates (not just agent claims)
Log every delegation with: task ID, agent, scope, deadline, verification command

始终为每个Agent定义禁止事项（必须拒绝执行的工作）
使用SQLite作为任务注册表（轻量，无需服务器）
将防重复的相似度阈值设置为55%（阈值过低会产生过多误判）
要求基于证据的质量关卡（而非仅依赖Agent的声明）
记录每次委派的信息：任务ID、Agent、范围、截止时间、验证命令

Common Pitfalls

常见陷阱

Problem: Orchestrator starts doing work instead of delegating Solution: Add explicit NOT-blocks and role boundaries
Problem: Two agents modify the same file simultaneously Solution: Task registry with file-level locking and queue system
Problem: Agent claims "done" without actual changes Solution: Quality gate checks git diff before accepting completion
Problem: Tasks pile up without progress Solution: 30-minute heartbeat catches stale assignments and reassigns

问题： 编排器亲自执行任务而非委派 解决方案： 添加明确的禁止事项和角色边界
问题： 两个Agent同时修改同一文件 解决方案： 任务注册表增加文件级锁定和队列系统
问题： Agent声称“完成”但未实际修改内容 解决方案： 质量关卡在接受完成前检查git diff
问题： 任务堆积无进展 解决方案： 30分钟心跳监控捕获停滞任务并重新分配

Related Skills

Limitations

局限性

Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

仅当任务明确符合上述描述的范围时使用该技能。
不要将输出视为环境特定验证、测试或专家评审的替代品。
如果缺少必要的输入、权限、安全边界或成功标准，请暂停并请求澄清。

multi-agent-task-orchestrator

Original

Translation

Multi-Agent Task Orchestrator

多Agent任务编排器

Overview

概述

When to Use This Skill

何时使用该技能

How It Works

工作原理

Step 1: Define the Orchestrator Identity

步骤1：定义编排器身份

Step 2: Build a Task Registry

步骤2：构建任务注册表

Step 3: Route Tasks to Specialists

步骤3：将任务分配给专业Agent

Step 4: Enforce Quality Gates

步骤4：执行质量关卡

Step 5: Run 30-Minute Heartbeats

步骤5：运行30分钟心跳监控

Examples

示例

Example 1: Delegating a Code Task

示例1：委派代码任务

Example 2: Handling a Duplicate

示例2：处理重复任务

Best Practices

最佳实践

Common Pitfalls

常见陷阱

Related Skills

相关技能

Limitations

局限性