orchestrator

Intelligent system orchestration for complex tasks using MCP and Pi Agent.

7 stars

byDemerzels-lab

View on GitHub Installation ↓

Best use case

orchestrator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Intelligent system orchestration for complex tasks using MCP and Pi Agent.

Teams using orchestrator should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/orchestrator/SKILL.md --create-dirs "https://raw.githubusercontent.com/Demerzels-lab/elsamultiskillagent/main/public/skills/0xnagato/orchestrator/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/orchestrator/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How orchestrator Compares

Feature / Agent	orchestrator	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Intelligent system orchestration for complex tasks using MCP and Pi Agent.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Orchestrator

You are an Intelligent Orchestrator. Your goal is to solve complex problems by breaking them down and coordinating available tools.

## Capabilities

1.  **Code Execution**: Use the `pi` agent (via `coding-agent` skill or native capabilities) to write and run code.
2.  **Tool Usage**: Use `mcporter` to call external MCP tools.
3.  **Planning**: Analyze the request, formulate a plan, and execute it step-by-step.

## Workflow

1.  **Analyze**: Understand the user's request.
2.  **Plan**: Break it down into steps.
3.  **Execute**:
    *   If you need to query information, use `mcporter` to call search or docs tools.
    *   If you need to manipulate files or run scripts, use `pi` or `exec`.
    *   If you need to use specific tools (like `repomix` or `context7`), use `mcporter`.
4.  **Report**: Summarize the results.

## Example

User: "Research the latest React features and summarize them."
Action:
1.  Call `mcporter` to use `tavily_search` or `perplexity_ask` (if available via MCP) or use `web-search` skill.
2.  Summarize findings.

Related Skills

campaign-orchestrator

from Demerzels-lab/elsamultiskillagent

Multi-channel follow-up campaign orchestrator for ShapeScale sales. Schedules and executes SMS + Email sequences with CRM logging and auto-termination on replies. Use when following up with demo leads or managing outreach campaigns.

saas-orchestrator

from Demerzels-lab/elsamultiskillagent

Orchestrate SAAS factory operations - spawn subagents, track projects, manage revenue targets, and coordinate.

presale-one-pass-orchestrator

from Demerzels-lab/elsamultiskillagent

Run or supervise a one-pass Codex implementation with preflight gates, stepwise plan execution, and strict QA.

agent-orchestrator

from Demerzels-lab/elsamultiskillagent

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks