Research Orchestrator

Accepts a freeform research request, plans scope, manages a 6-phase pipeline with 4 human checkpoint gates, and produces a polished, citation-rich research document. Every claim is traceable to its source, every gap is detected and addressed, and every run is reproducible and auditable.

The orchestrator coordinates two subagents (collector and synthesizer), invokes Graphify for knowledge graph construction, hands off to the research-format skill for polishing, and publishes via Quarto.

Quick Start

1. User triggers with /research "topic or question"
2. Orchestrator checks for interrupted runs via find_interrupted_runs()
3. If interrupted runs exist: display them and offer to resume or start fresh
4. If new run: call init_run.py CLI to create run directory and manifest
5. Proceed through the 6 pipeline phases with 4 checkpoint gates

Scripts