light-orchestration

Determine whether to execute a task directly or decompose it into a bounded multi-agent plan.

1|Updated Apr 13, 2026

Search Tags:#workflow #planning #decision #multi-agent #orchestration #subtasks

Ready to run

npx skills add https://github.com/t-uda/skills --skill light-orchestration

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: light-orchestration
Source: https://github.com/t-uda/skills/tree/main/skills/light-orchestration
Command: npx skills add https://github.com/t-uda/skills --skill light-orchestration

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Light orchestration helps an orchestrator decide between direct execution and a minimal, tightly bounded multi-agent split, producing bounded subtask contracts when a split is justified.

Core Features & Use Cases

Provides guidance on whether to run tasks in SINGLE_AGENT mode or orchestrate a small multi-agent plan.
Produces concise subtask contracts when orchestration is appropriate, without dispatching automatically.
Supports clear boundaries and minimal handoff overhead for lightweight, bounded tasks.

Quick Start

Provide a task description and context, then ask the skill to determine a SINGLE_AGENT or ORCHESTRATE plan and return a structured decision.

Frequently Asked Questions about light-orchestration

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

FAQPage Schema

When should I decompose a task into a multi-agent workflow instead of executing it directly?▼

Use multi-agent orchestration when a task benefits from limited parallelism and offers a clear cost or risk advantage over direct execution. The skill defaults to single-agent mode unless splitting the task provides bounded benefits that justify the handoff overhead.

How do I decide between single-agent execution and a multi-agent plan for complex subtasks?▼

Deciding between single-agent execution and a multi-agent plan requires evaluating task constraints and known decisions against current context. The skill analyzes these inputs to produce a formal decision, preferring direct execution unless orchestration yields a measurable advantage.

What inputs do I need to generate multi-agent subtask contracts?▼

Generating multi-agent subtask contracts requires a task description, current context, constraints, and known decisions. Providing these inputs allows the skill to output a formal decision along with an optional bounded decomposition and next steps for the orchestrator.

Does this skill automatically dispatch subtasks to agents after planning?▼

No, the skill does not automatically dispatch subtasks to agents. It produces concise subtask contracts and next steps when orchestration is appropriate, leaving the actual dispatching and execution to the orchestrator.

What are the limitations of using lightweight orchestration for task planning?▼

Lightweight orchestration is limited to minimal, tightly bounded tasks with low handoff overhead. It is not designed for unbounded workflows, deliberately restricting decomposition to small multi-agent splits to maintain clear boundaries.