deep-research

Conduct multi-source web research and synthesize structured reports with cited sources.

Updated May 17, 2026
One-click install
npx skills add https://github.com/Amna-exe/EventFlow_App --skill deep-research-amna-exe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/Amna-exe/EventFlow_App/tree/main/Final-MAD-project-main-4zipzipzipzipzip-1-ite1zipzip/.local/secondary_skills/deep-research
Command: npx skills add https://github.com/Amna-exe/EventFlow_App --skill deep-research-amna-exe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Answering complex questions that require gathering, cross-checking, and synthesizing information from many web sources is slow and error-prone when done manually, and single-search answers often lack depth, citations, and source credibility assessment. ## Core Features & Use Cases - Parallel Multi-Agent Research: Decomposes a topic into focus areas and launches parallel research subagents that each run multiple web searches, including local-language queries for region-specific topics. - Source Triangulation & Credibility Scoring: Rates sources into tiers (government/academic, major publications, blogs) and requires 3+ sources for every major claim, with conflict resolution rules. - Structured Report Generation: Produces prose-first research reports with executive summaries, inline citations, limitations, recommendations, and a numbered source list. - Use Case: Ask for a deep dive on the state of the electric vehicle market in 2026, and receive a cited report covering market share, battery technology, policy, infrastructure, and consumer economics drawn from 15-25+ sources. ## Quick Start Research the current state of the electric vehicle market and write a structured report with cited sources.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I run a deep research report on a topic?

State your research question and desired depth, such as a standard or deep dive. The skill decomposes the topic into focus areas, launches parallel research subagents, cross-references sources, and delivers a structured report with inline citations.

What is the difference between quick, standard, and deep research tiers?

Quick uses 3 subagents and 8+ sources for focused questions in 2-5 minutes. Standard uses 5 subagents and 15+ sources for most requests. Deep adds gap-fill subagents and self-critique with 25+ sources for critical decisions.

When should I use web search instead of deep research?

Use a direct web search for simple factual lookups answerable in one or two queries. Deep research is for complex multi-angle questions needing triangulation, credibility scoring, and a cited report.

How are sources evaluated for credibility in research reports?

Sources are rated in three tiers: government, multilateral, and academic sources are Tier 1; major publications and industry reports are Tier 2; blogs and promotional content are Tier 3. Major claims require at least three supporting sources.

What are the limitations of automated web research?

It cannot access paywalled journals, subscription databases, or social media content, and cannot conduct primary research like surveys or interviews. Findings are a snapshot in time and some pages may fail to fetch.