mofa-research

Plan search angles, execute parallel searches, and synthesize structured reports.

11|12|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mofa-research
Source: https://github.com/mofa-org/mofa-skills/tree/main/_unpublished/mofa-research
Command: npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

A DOT-based deep research pipeline that dynamically plans N search angles via LLM, executes them in parallel, then analyzes and synthesizes sequentially.

Core Features & Use Cases

  • Plan and generate 4-6 search angles tailored to the query
  • Launch multiple search workers in parallel and aggregate results
  • Analyze outputs across subtopics and synthesize a structured, citational report

Quick Start

Provide a topic to the deep research pipeline to generate a structured report.

Frequently Asked Questions about mofa-research

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

FAQPage Schema
How do I generate a structured research report across multiple sources?

To generate a structured research report, this pipeline dynamically plans 4-6 search angles via LLM, executes parallel searches across multiple sources, analyzes outputs by subtopic, and synthesizes a citational report sequentially.

Can I parallelize deep research queries for complex topic analysis?

Yes, you can parallelize deep research queries. The pipeline launches multiple search workers in parallel to gather cross-source citations, then aggregates and analyzes the results sequentially for comprehensive topic analysis.

What is LLM-driven planning for multi-angle exploration?

LLM-driven planning dynamically generates 4-6 tailored search angles for a given query, enabling multi-angle exploration. This approach ensures complex academic, policy, or product topics are covered thoroughly before parallel execution begins.

Does this deep research pipeline support citation management?

Yes, citation management is supported. The pipeline aggregates cross-source citations during parallel search and incorporates them into a synthesized, structured report for academic, policy, and product research contexts.

What is the best way to handle complex topics requiring cross-source citation gathering?

The best way to handle complex topics is using a DOT-based pipeline that combines LLM planning, parallel search workers, and sequential synthesis. This approach gathers cross-source citations and produces a robust, structured report.

Do I need any dependencies to run the parallel search and synthesis pipeline?

No external dependencies are required to run the parallel search and synthesis pipeline. You simply provide a topic, and the system handles the dynamic planning, parallel task execution, and structured report generation end-to-end.