research

Perform exhaustive multi-domain research with cited, structured findings.

5|Updated Nov 18, 2025
One-click install
npx skills add https://github.com/krishagel/geoffrey --skill research-krishagel
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/krishagel/geoffrey/tree/main/skills/research
Command: npx skills add https://github.com/krishagel/geoffrey --skill research-krishagel

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Discovery-driven, exhaustive research using parallel LLM agents for comprehensive, current information gathering.

Core Features & Use Cases

  • Discovery-driven, context-aware results loaded from user context
  • Clarifying questions first to pin goals, constraints, and success criteria
  • Multimedia sources and real-time citations for claims
  • Structured output with executive summary, detailed findings, and references
  • Phase-based workflow: query understanding, parallel discovery, synthesis, and reporting

Quick Start

Ask a question such as "Tell me about the current state of AI ethics in 2025" and expect a structured, cited report.

Frequently Asked Questions about research

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

FAQPage Schema
How do I conduct exhaustive research with current, cited sources?

Exhaustive research uses parallel multi-source discovery and synthesis to gather comprehensive, well-sourced findings across travel, shopping, work/education, AI coding, and consulting domains. This Skill orchestrates query decomposition, deep scraping, multimedia discovery, and evidence-driven recommendations, ensuring every claim is cited in structured output ready for analysis or RAG pipelines.

Can I get research results with real-time citations and multimedia sources?

Yes. This Skill performs domain-aware research by fetching dynamic data via browser control, discovering multimedia sources, and synthesizing findings with citations attached to each claim. Results include executive summaries, detailed findings, and structured references across diverse sources.

How does parallel LLM agent research differ from standard information gathering?

Parallel LLM agents decompose queries and search multiple sources simultaneously rather than sequentially, delivering faster, exhaustive coverage. This approach applies domain context from user preferences, orchestrates cross-LLM workflows, and produces evidence-driven recommendations with multimedia discovery built in.

What domains and use cases does this research workflow cover?

Research covers travel, shopping, work/education, AI coding, and consulting domains. The Skill loads domain context from preferences, applies clarifying questions to pin goals and success criteria, and delivers structured output with executive summary, detailed findings, and multimedia references suited to each domain.

Does this Skill work for real-time research on current topics?

Yes. The Skill fetches dynamic data via browser control and applies parallel discovery across multiple sources to deliver current findings. Every claim is cited with real-time sources, making it suited for topics requiring up-to-date information and multimedia evidence.