exploration-orchestrator

Name: exploration-orchestrator
Availability: InStock
Author: dylan-conlin

Decompose complex questions into parallel subproblems and synthesize unified analyses.

Updated Aug 27, 2026

Search Tags:#iteration #synthesis #orchestrator #parallel-workflow #judgment #subproblems #ai-exploration

Ready to run

npx skills add https://github.com/dylan-conlin/orch-go --skill exploration-orchestrator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: exploration-orchestrator
Source: https://github.com/dylan-conlin/orch-go/tree/main/skills/src/meta/exploration-orchestrator
Command: npx skills add https://github.com/dylan-conlin/orch-go --skill exploration-orchestrator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate large, multi-step AI investigations by decomposing questions, spawning parallel workers, judging findings, and synthesizing a unified analysis, without performing the investigations itself.

Core Features & Use Cases

Decomposition of complex questions into independent subproblems
Parallel spawning of workers with controlled breadth and depth
Phase-driven coordination: spawn, wait, judge, iterate, and synthesize
Iteration handling for critical gaps to improve coverage
Safe, non-destructive orchestration that avoids code execution within the orchestrator

Quick Start

Provide a complex question and configuration, then invoke the orchestrator to begin decomposition and coordination.

Frequently Asked Questions about exploration-orchestrator

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

FAQPage Schema

How do I decompose complex questions into parallel subproblems for AI exploration?▼

Parallel AI exploration decomposes complex questions into independent subproblems by spawning multiple workers concurrently. The orchestrator coordinates phase-driven workflows spanning decomposition, spawning, waiting, judging, iteration, and final synthesis to produce a unified analysis.

What is iterative re-exploration with judge feedback in multi-model AI workflows?▼

Iterative re-exploration with judge feedback is a workflow mechanism where evaluated findings trigger targeted re-spawning of workers to fill critical coverage gaps. This phase-driven coordination repeats until sufficient breadth and depth are achieved before final synthesis.

How do I orchestrate parallel AI workers to synthesize a unified analysis?▼

To orchestrate parallel AI workers, invoke the orchestrator with a complex question and configuration. It handles decomposition, spawns workers with controlled breadth and depth, judges findings, iterates on gaps, and synthesizes results into a unified analysis without executing code.

Can I use this orchestrator to execute code during multi-step AI investigations?▼

No, this orchestrator cannot execute code during multi-step AI investigations. It operates under safety constraints as a non-destructive coordination layer, strictly managing decomposition, spawning, judging, iteration, and synthesis without performing code execution.

When do I need parallel orchestration for multi-model AI exploration tasks?▼

You need parallel orchestration for multi-model AI exploration tasks when questions are too complex for a single pass and require controlled breadth, iterative re-exploration, and judge feedback to ensure comprehensive coverage before synthesizing a unified analysis.