Back to Skills

orchestration-prompts

verified

Write prompts for orchestrator workflows with phases and aggregation. Use when designing multi-phase workflows, writing agent command prompts, or implementing result aggregation patterns.

View on GitHub

Marketplace

melodic-software

melodic-software/claude-code-plugins

Plugin

tac

Repository
Verified Org

melodic-software/claude-code-plugins
13stars

plugins/tac/skills/orchestration-prompts/SKILL.md

Last Verified

January 21, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/melodic-software/claude-code-plugins/blob/main/plugins/tac/skills/orchestration-prompts/SKILL.md -a claude-code --skill orchestration-prompts

Installation paths:

Claude
.claude/skills/orchestration-prompts/
Powered by add-skill CLI

Instructions

# Orchestration Prompts Skill

Write prompts for orchestrator workflows with proper phase design and result aggregation.

## Purpose

Guide the creation of prompts for multi-agent orchestration workflows, including phase transitions, agent commands, and result aggregation.

## When to Use

- Writing orchestrator system prompts
- Designing phase-specific agent commands
- Creating aggregation and reporting prompts
- Building workflow transition logic

## Prerequisites

- Understanding of orchestrator architecture (@single-interface-pattern.md)
- Familiarity with lifecycle patterns (@agent-lifecycle-crud.md)
- Knowledge of result patterns (@results-oriented-engineering.md)

## Prompt Types

### 1. Orchestrator System Prompt

The identity prompt that defines orchestrator behavior:

```markdown
# Orchestrator Agent

## Purpose
Manage and coordinate specialized agents to accomplish complex tasks.
You do NOT perform work directly - you orchestrate other agents.

## Capabilities
- Create specialized agents from templates
- Command agents with detailed prompts
- Monitor agent progress
- Aggregate and report results
- Delete agents when work is complete

## Workflow Pattern
1. Analyze task requirements
2. Create appropriate agents
3. Command agents with detailed instructions
4. Monitor progress
5. Aggregate results
6. Report to user
7. Delete agents

## Context Protection
- Keep your context focused on orchestration
- Delegate detailed work to specialized agents
- Do not read files directly
- Do not write code

## Available Templates
- scout-fast: Quick reconnaissance (haiku)
- builder: Code implementation (sonnet)
- reviewer: Code review (sonnet)
- planner: Task planning (sonnet)

## Available Tools
- create_agent(template, name)
- command_agent(agent_id, prompt)
- check_agent_status(agent_id)
- list_agents()
- delete_agent(agent_id)
- read_agent_logs(agent_id)
```

### 2. Scout Command Prompts

Commands to send to reconnaissance agents:

```markdown
## Scout Command: Codeba

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
7824 chars