orchestrator

Decompose complex requests and delegate sub-tasks to subagents.

34|2|Updated Aug 16, 2025

Search Tags:#code review #context management #workflow automation #subagents #orchestration #task delegation

Ready to run

npx skills add https://github.com/FilenCloudDienste/filen-ts --skill orchestrator-filenclouddienste

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: orchestrator
Source: https://github.com/FilenCloudDienste/filen-ts/tree/main/.claude/skills/orchestrator
Command: npx skills add https://github.com/FilenCloudDienste/filen-ts --skill orchestrator-filenclouddienste

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents large, noisy multi-step workflows by forcing complex tasks to be decomposed and delegated, keeping the main conversation focused on decisions and outcomes rather than tool chatter.

Core Features & Use Cases

Task decomposition and delegation: Breaks requests into discrete sub-tasks and sends them to subagents using the Task tool.
Context-window hygiene: Avoids dumping long tool outputs or full file contents into the main context by requiring subagents to summarize and return only what’s needed.
Practical execution guidance: Provides clear rules for when to delegate versus act directly, including for coding, research, edits, debugging, refactoring, reviews, and multi-step workflows.

Quick Start

When you give me a multi-step coding, research, or editing request, I will delegate the work to focused subagents and return a clean summary of what changed and the results.

Frequently Asked Questions about orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I keep my main context window clean during complex multi-step coding workflows?▼

To maintain context-window hygiene during multi-step coding workflows, you can decompose requests and delegate sub-tasks to subagents. This prevents large tool outputs and file dumps from polluting the main conversation, returning only clean summaries.

What is task decomposition and how does it work for delegating code reviews?▼

Task decomposition for code reviews involves breaking a large request into discrete sub-tasks and sending them to focused subagents. The subagents execute the review scoped to their prompt and synthesize their outputs into a single clean report.

When should I delegate work to subagents versus acting directly in my main context?▼

You should delegate work to subagents for multi-step workflows requiring sequential or parallel tool operations, such as debugging, refactoring, or research. Acting directly is better for simple decisions where heavy tool chatter and file dumps are not expected.

Can I use subagents for parallel file editing and research tasks without losing track of outputs?▼

Yes, you can use subagents for parallel file editing and research tasks. They execute the scoped work independently and return only the necessary synthesized results, ensuring you receive the final outputs without the raw tool noise.

What is the best way to automate complex refactoring workflows without cluttering the conversation?▼

The best way to automate complex refactoring workflows without clutter is to use an orchestration approach that delegates the work to subagents. This forces task decomposition and requires subagents to summarize results, keeping the main context focused on outcomes.