research

Synthesize multi-source research into briefs, reports, and decision matrices.

4|1|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/wyattowalsh/agents --skill research-wyattowalsh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/wyattowalsh/agents/tree/main/skills/research
Command: npx skills add https://github.com/wyattowalsh/agents --skill research-wyattowalsh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires brave-search, arxiv, context7, semantic-scholar, tavily, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill tackles complex questions that require synthesizing information from multiple sources, verifying facts, and understanding nuanced topics, saving you hours of manual investigation.

Core Features & Use Cases

  • Deep Investigation: Conduct thorough research on technical, academic, or market topics.
  • Fact-Checking: Verify specific claims against multiple reliable sources.
  • Comparison: Analyze and compare different options, technologies, or viewpoints.
  • Use Case: Use this Skill to investigate the state of the art in LLM agent architectures, getting a synthesized report with confidence scores and identified gaps.

Quick Start

Use the research skill to investigate the current best practices for LLM agent memory architectures.

Frequently Asked Questions about research

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

FAQPage Schema
How do I synthesize information from multiple sources for a comprehensive research report?

Multi-source research synthesis automatically classifies query complexity and uses a phased pipeline including triage, deep dive, and cross-validation to generate reports with confidence scoring and reduce hallucination.

What is the best way to fact-check claims and verify information across academic papers?

Fact-checking specific claims is achieved by cross-validating information across multiple reliable sources like Semantic Scholar and arXiv, synthesizing the findings to ensure accuracy and identify knowledge gaps.

Can I retrieve technical papers and compare viewpoints using automated information retrieval?

Automated information retrieval supports deep investigation into technical or academic topics, allowing you to analyze and compare different options, technologies, or viewpoints using a structured research pipeline.

How does confidence scoring work in multi-source knowledge discovery?

Confidence scoring in knowledge discovery evaluates the reliability of synthesized information by cross-validating facts across various tools and sources during the research pipeline's synthesis phase.

What output formats are available when synthesizing deep dive investigation results?

Investigation results can be outputted in multiple formats including briefs, comprehensive reports, bibliographies, and decision matrices depending on your specific research synthesis needs.

Do I need specific search and retrieval tools to perform deep multi-source research?

Deep multi-source research requires integration with tools like brave-search, arxiv, context7, semantic-scholar, and tavily to execute the phased pipeline and retrieve information from various sources.