research

Orchestrate multi-source research, adversarial fact-checking, and HTML report formatting.

Updated Jun 9, 2026

Search Tags:#fact-checking #research #parallel processing #report generation #structured output

Ready to run

npx skills add https://github.com/carllelandtaylor/facto --skill research-carllelandtaylor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research
Source: https://github.com/carllelandtaylor/facto/tree/main/plugins/facto/skills/research
Command: npx skills add https://github.com/carllelandtaylor/facto --skill research-carllelandtaylor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates multi-source research reports, handling parallel subagent operations, adversarial fact-checking, and formatting into HTML, significantly reducing the need for manual research.

Core Features & Use Cases

Multi-source Research: Automatically gathers and synthesizes information from various sources.
Adversarial Fact-checking: Includes a stage where parallel subagents verify findings for accuracy.
HTML Reporting: Outputs research in structured HTML reports, easy for further use.
Use Case: Imagine needing a detailed report on a technology trend. This Skill would conduct research, fact-check it, and generate an HTML report ready for publication.

Quick Start

Invoke the /facto:research command with your specific research question or topic.

Frequently Asked Questions about research

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

FAQPage Schema

How do I automate multi-source research and fact-checking into a structured report?▼

Automate multi-source research by using parallel subagents to gather information and perform adversarial fact-checking. This process synthesizes findings and formats the final validated output directly into a structured HTML report, ensuring deep investigation and high documentation standards without manual effort.

What is adversarial fact-checking in automated report generation?▼

Adversarial fact-checking in automated report generation is a validation stage where parallel subagents independently verify research findings for accuracy. This rigorous review mechanism ensures high-quality output by cross-examining synthesized data before formatting it into the final HTML documentation.

Can I generate structured HTML reports directly from parallel research tasks?▼

Yes, you can generate structured HTML reports directly from parallel research tasks. The system orchestrates multi-source investigation and adversarial fact-checking, automatically formatting the validated findings into structured HTML output ready for immediate use and publication.

Does automated research with parallel processing require manual data gathering?▼

No, automated research with parallel processing does not require manual data gathering. The system orchestrates complex multi-source research automatically, deploying parallel subagents to synthesize information and conduct adversarial fact-checking, significantly reducing the need for manual research.

What is the best way to format validated research findings into structured HTML?▼

The best way to format validated research findings into structured HTML is through an automated workflow that integrates adversarial fact-checking and report formatting. This ensures the HTML output adheres to rigorous documentation standards after parallel subagents review the data.

When should I use parallel subagents for complex research and investigation?▼

Use parallel subagents for complex research and investigation when targeting tasks requiring deep investigation, validation, and documentation. This approach is ideal for generating detailed reports on technology trends where multi-source synthesis and rigorous adversarial fact-checking are necessary.