deep-research

Generates cited research reports from multi-source web searches using firecrawl and exa MCP tools.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/listentomi/Orcajack --skill deep-research-listentomi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/listentomi/Orcajack/tree/main/skills/science/deep-research
Command: npx skills add https://github.com/listentomi/Orcajack --skill deep-research-listentomi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Answering complex questions thoroughly requires searching many sources, reading them in depth, and synthesizing findings with citations, which is slow and error-prone when done manually. ## Core Features & Use Cases - Multi-Source Search: Runs structured sub-question searches across firecrawl and exa MCP tools, targeting 15-30 unique sources per topic. - Deep Source Reading: Fetches full content of key URLs with firecrawl_scrape or crawling_exa instead of relying on snippets. - Cited Report Generation: Produces a structured report with executive summary, themed sections, inline citations, key takeaways, source list, and methodology notes. - Parallel Research: Splits broad topics across subagents that research sub-questions concurrently before synthesis. - Use Case: Ask for a deep dive into the competitive landscape for AI code editors and receive a sourced report with cross-referenced claims and recency-prioritized evidence. ## Quick Start Research the current state of nuclear fusion energy and give me a cited report with key takeaways.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I do deep web research with cited sources using an AI agent?▼

Break the topic into 3-5 sub-questions, search each with firecrawl_search or web_search_exa, deep-read 3-5 key sources, then synthesize a report with inline citations, a source list, and a methodology section.

What MCP tools are needed for multi-source web research?▼

At least one of firecrawl or exa MCP servers is required. Firecrawl provides firecrawl_search, firecrawl_scrape, and firecrawl_crawl; exa provides web_search_exa, web_search_advanced_exa, and crawling_exa. Using both gives the best coverage.

Firecrawl vs exa for web search and scraping?▼

Firecrawl focuses on search plus full-page scraping and crawling of URLs, while exa offers semantic web search with filters like publication date and token-limited content extraction. They are complementary and can be used together.

Can I parallelize research across multiple subagents?▼

Yes. For broad topics, launch parallel research agents where each handles a subset of sub-questions, searches and reads sources independently, and returns findings for the main session to synthesize into the final report.

How are unsourced or unverified claims handled in research reports?▼

Every claim requires a source, single-source claims are flagged as unverified, and missing information is reported as insufficient data rather than guessed. Estimates and opinions are explicitly labeled as inference.