Skip to main content Skills Marketplace コミュニティが作成したAIスキルを発見・探索
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/tomevault-io/skills-registry --skill eoa-orchestration-patternsコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか?SkillsMP が現在取得できるファイルをダウンロードできます。
Zipをダウンロード ダウンロード中... name eoa-orchestration-patterns description Use when coordinating work among multiple developers. Trigger with orchestration requests. license Apache-2.0 compatibility Requires multiple developers or task agents, task tracking system (GitHub issues or similar), clear task definitions with success criteria, and communication channel for status updates. Requires AI Maestro installed. metadata {"author":"Emasoft","version":"2.4.0"} context fork user-invocable false agent eoa-main workflow-instruction Steps 10, 12, 23, 24 procedure proc-decompose-design, proc-create-task-plan, proc-handle-successful-pr, proc-iterate
Orchestration Patterns Skill
Overview
This skill teaches how to coordinate work among multiple developers using orchestration patterns.
Output
Output Type Description Example TaskCreate calls Task definitions with success criteria TaskCreate(subject="Implement module X", ...)Task assignments Agent assignments via AI Maestro or Task tool Message to remote-dev-001 with task details Progress reports Regular status updates from monitoring "Task 1: 60% complete, Task 2: blocked on DB" Completion signals Verification of all tasks done "All 5 tasks completed, ready for integration" Escalation requests Blocked task escalations to user/EAMA "Task 3 blocked: missing API credentials"
API Commands Reference
For AI Maestro messaging and Claude Code Tasks API, see orchestration-api-commands.md :
AI Maestro Messaging for Remote Agents
1.1 When to use AI Maestro vs Task tool
1.2 Sending task assignments to remote agents
1.3 Message types for EOA
Claude Code Tasks API
2.1 When to use TaskCreate, TaskUpdate, TaskList
2.2 Creating tasks with success criteria
2.3 Task lifecycle commands
Core Concepts
Orchestration is the act of coordinating multiple concurrent tasks performed by different agents to achieve a common goal. An orchestrator:
Breaks down work into independent tasks
Assigns tasks to the right workers
Tracks progress and unblocks stuck work
Manages communication and feedback
Prerequisites
Multiple developers or task agents available for parallel work
A way to track task status (GitHub issues, task lists, or similar)
Clear task definitions with success criteria
A communication channel for status updates and escalations
Instructions
Procedure Overview
Phase 1: Task Decomposition - Break down the goal into independent, parallelizable tasks
Phase 2: Task Assignment - Assign tasks to developers with clear instructions
Phase 3: Progress Monitoring - Track task completion and identify blocks
Phase 4: Escalation & Unblocking - Handle blocked tasks and escalate when needed
Phase 5: Integration & Verification - Combine results and verify completion
Reference Files Evaluate task complexity to determine appropriate planning investment.
Classification Process - When deciding if a task needs planning
Simple/Medium/Complex Task classification criteria
Practical Tips and Anti-Patterns
Read first - Understanding task complexity guides all subsequent decisions.
Select the right specialized agent for each task based on language, domain, and capabilities.
Selection Decision Tree - When you need to delegate a task
Language-Specific Agents - Python/JS/Go/Rust agent selection
Anti-Patterns and Best Practices
Read second - Essential for effective task delegation. Prerequisite: Task Complexity Classifier
Conduct interactive setup to establish project parameters, team configuration, and quality standards.
Menu Implementation - When starting a new project
Team Configuration and Repository Configuration
Release Strategy and Troubleshooting
Read third - Run before any project work begins. Prerequisite: Agent Selection Guide
Ensure code quality, build success, and release readiness with language-specific verification standards.
Python/Go/JavaScript/TypeScript/Rust Verification Checklists
Usage in Orchestration and Automation Scripts
Read last - Apply when reviewing deliverables. Prerequisite: Project Setup Menu
PROACTIVE monitoring of implementer agents to ensure progress and completion.
Proactive Monitoring Principles
PROACTIVE Status Request Protocol
PROACTIVE Unblocking Protocol
PROACTIVE Task Completion Enforcement
When to use: When agent silent 15+ min, reports blocker, wants to stop, or task needs verification.
MANDATORY 4-verification-loops before any Pull Request is approved.
Overview - Why 4 Verification Loops Are Required
2-5. Steps 1-4: Assignment, Verification Message, Tracking, Final Decision
Enforcement Rules
When to use: At task assignment, when agent asks "Can I make a PR?", when tracking verification.
RULE 15: The orchestrator NEVER writes production code.
Forbidden/Allowed Actions for Orchestrators
Small Experiments (with limits)
Self-Check Procedure
When to use: Before any action (self-check), when tempted to write code directly.
RULE 14: User requirements cannot be changed without explicit user approval.
Orchestration Requirement Enforcement by phase
Requirement Issue Workflow
When to use: At project start, when requirement cannot be implemented as stated.
RULE 16: Only the orchestrator can send/receive messages or commit changes.
Orchestrator-Exclusive Actions
Sub-Agent Restrictions
Communication Flow and Enforcement
When to use: Before spawning sub-agents, when sub-agent needs external communication.
RULE 17: The orchestrator must ALWAYS remain responsive.
Async Task Delegation Patterns
Polling Instead of Blocking
Parallel Agent Spawning
Emergency Response Availability
When to use: Before any long-running command, when spawning agents, when checking messages.
Detailed role boundaries for orchestrator behavior.
Infrastructure task delegation procedures.
Detailed examples of orchestration patterns in practice.
Authentication Module Implementation - Plan handoff handling
CI Failure Coordination - Investigation-first pattern
Parallel Code Review - Section-based decomposition
Blocked Dependency Handling - Parallel escalation pattern
When to use: When you need concrete examples of orchestration workflows.
AI Maestro messaging and Claude Code Tasks API reference.
AI Maestro Messaging for Remote Agents
Claude Code Tasks API
When to use: When sending messages or creating/updating tasks.
Canonical text for RULE 14: User Requirements Are Immutable.
When to use: When enforcing requirement immutability at all orchestration phases.
Template for defining worker agent role boundaries in task delegations.
When to use: When delegating tasks to worker agents.
Orchestration workflow checklists for task decomposition, assignment, monitoring, and integration.
When to use: When executing orchestration workflows.
Log format specifications for orchestration activities.
When to use: When creating delegation logs and status reports.
Archive directory structure for completed work.
When to use: When archiving completed tasks and projects.
Quick Reference Checklist Copy this checklist and track your progress:
Examples
Decompose and Delegate a Feature This example shows how to decompose a feature request into tasks and delegate them.
Input: A feature request from the user (via EAMA):
Feature: Add user authentication module
Requirements:
- OAuth2 login with Google provider
- Session management with JWT tokens
- Rate limiting on login endpoint (5 attempts per minute)
Output: The orchestrator produces a task plan with assignments:
Task Plan: Authentication Module (3 parallel tasks)
Task 1: OAuth2 Integration
Assign to: epa-backend-001
Scope: src/auth/oauth.py, src/auth/providers/google.py
Success criteria: Google OAuth2 flow completes end-to-end, tokens stored
Dependencies: None
Task 2: Session Management
Assign to: epa-backend-002
Scope: src/auth/session.py, src/auth/jwt.py
Success criteria: JWT issued on login, validated on protected routes, expires correctly
Dependencies: None (uses mock OAuth response until Task 1 merges)
Task 3: Rate Limiting
Assign to: epa-backend-003
Scope: src/middleware/rate_limit.py, tests/test_rate_limit.py
Success criteria: Login endpoint rejects 6th attempt within 60s window, returns 429
Dependencies: None (uses mock login endpoint)
Result: 3 tasks delegated in parallel, each with clear scope and success criteria.
Authentication module implementation from plan handoff
CI failure coordination with investigation-first pattern
Parallel code review across 5 developers
Blocked dependency handling with parallel escalation
Important Notes
Never block the orchestrator - Delegate all long-running tasks to agents
RULE 17: Stay responsive - Check AI Maestro messages regularly
One task per agent - Clear boundaries prevent conflicts
Minimal status reports - Request 1-2 lines only: "[DONE] task-name - result"
Early escalation - Identify blocks at first checkpoint; escalate immediately
PROACTIVE monitoring - Poll agents regularly; never wait passively
4-verification-loops - Only approve PR on 5th request if no issues remain
Orchestrator-exclusive communications - Sub-agents prepare content but NEVER send externally
Parallel spawning - Spawn up to 20 agents simultaneously for independent tasks
Error Handling Issue Cause Resolution Agent unresponsive Agent crashed or blocked Poll until response; reassign if unrecoverable Task conflict Same file modified by multiple agents Assign non-overlapping scope Verification loop stuck Agent doesn't check changes Send explicit verification message Escalation pending User unavailable Queue issue, continue other work
See individual reference files for detailed troubleshooting.
Resources
Converted and distributed by TomeVault — claim your Tome and manage your conversions.