research

Conduct systematic web research with multi-query searches and SCAR source evaluation.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/RedBeret/agent-skill-catalog --skill research-redberet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/RedBeret/agent-skill-catalog/tree/main/skills/research
Command: npx skills add https://github.com/RedBeret/agent-skill-catalog --skill research-redberet

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you conduct thorough and reliable web research by providing a structured process for defining questions, searching effectively, evaluating sources, verifying facts, and synthesizing information to prevent hallucinations and ensure trustworthy, cited outputs.

Core Features & Use Cases

  • Structured Research Process: Guides you through defining questions, broad searching, source evaluation, cross-verification, synthesis, and citation.
  • Advanced Search Strategies: Offers techniques like exact phrase matching, exclusion, site-scoping, filetype searches, and multi-query approaches.
  • Source Evaluation Frameworks: Utilizes the SCAR test (Source, Currency, Accuracy, Relevance) and bias indicators to assess source reliability.
  • Fact Verification: Employs the two-source rule and version sensitivity checks to ensure accuracy.
  • Hallucination Prevention: Provides strict rules to avoid inventing information, URLs, or statistics.
  • Citation and Summarization: Offers clear formats for inline citations, source tables, and structured research summaries.
  • Use Case: Researching the latest advancements in quantum computing for a technical report, ensuring all claims are backed by credible, up-to-date sources.

Quick Start

Use the research skill to find and summarize the latest developments in AI-powered drug discovery, citing all sources.

Frequently Asked Questions about research

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

FAQPage Schema
How do I conduct web research without getting AI hallucinations?

To prevent AI hallucination during web research, this process enforces strict rules against inventing information, URLs, or statistics, and requires verifying facts across multiple independent sources before synthesizing any cited summaries.

What is the best way to evaluate source credibility for a technical report?

The best way to evaluate source credibility is applying the SCAR test, which assesses the Source, Currency, Accuracy, and Relevance of information, alongside checking specific bias indicators to ensure reliable evidence-based retrieval.

How do I verify facts across multiple independent sources?

You can verify facts by employing the two-source rule and conducting version sensitivity checks, ensuring that claims are cross-referenced across multiple independent sources before being synthesized into your final structured summary.

Can I use advanced search strategies like exact phrase matching and site-scoping for research?

Yes, you can use advanced search strategies including exact phrase matching, exclusion, site-scoping, filetype searches, and multi-query approaches to systematically define questions and retrieve targeted information for technical and analytical domains.

How do I synthesize research findings into structured cited summaries?

You synthesize research findings by combining cross-verified facts into structured cited summaries, utilizing clear formats for inline citations and source tables to ensure all claims are backed by credible, up-to-date sources.

What are the limitations of using automated search for fact verification?

A key limitation is that automated search cannot bypass the need for human judgment in applying the SCAR test and bias indicators, as the process strictly requires evaluating source credibility and cross-verifying facts to avoid generating inaccurate outputs.