deep-research

Conduct multi-source web research and synthesize findings into cited structured reports.

Updated May 25, 2026
One-click install
npx skills add https://github.com/dheejay282002/final_project --skill deep-research-dheejay282002
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/dheejay282002/final_project/tree/main/.local/secondary_skills/deep-research
Command: npx skills add https://github.com/dheejay282002/final_project --skill deep-research-dheejay282002

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Answering complex questions that require more than a quick search is slow and error-prone: sources conflict, claims go unverified, and reports lack citations. This Skill automates comprehensive multi-source research with source credibility scoring, triangulation, and structured report generation. ## Core Features & Use Cases - Parallel Subagent Research: Decomposes a topic into focus areas and launches parallel research subagents, each running multiple web searches and fetching full articles. - Source Triangulation & Scoring: Rates sources into credibility tiers (government/academic, major publications, blogs) and requires 3+ sources per major claim. - Tiered Depth Levels: Quick (8+ sources), Standard (15+), and Deep (25+) modes with gap analysis and self-critique phases for critical decisions. - Use Case: Ask for a deep dive on the state of the electric vehicle market in 2026, and receive a structured report with an executive summary, key findings, inline citations, limitations, and a numbered source list. ## Quick Start Research the competitive landscape of the electric vehicle market in 2026 and produce a cited report.

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 complex topic?▼

State your research question and desired depth, such as asking for a deep dive on a market or technology. The skill decomposes the topic into focus areas, launches parallel research subagents, triangulates sources, and delivers a cited structured report.

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 research requests. Deep adds gap-fill subagents and a self-critique phase with 25+ sources for critical decisions.

When should I use web search directly instead of deep research?▼

Use a direct web search for simple factual lookups answerable in one or two queries. Deep research is for multi-angle questions needing cross-referenced evidence, such as market analysis, technology comparisons, or claim verification.

How does the research verify claims and handle conflicting sources?▼

Every major claim requires support from at least three sources, with credibility tiers ranking government and academic sources above publications and blogs. When sources conflict, higher-tier and more recent data wins, and unresolved discrepancies are reported explicitly.

What are the limitations of automated web research?▼

It cannot access paywalled journals, subscription databases, or social media content, and it cannot conduct primary research like surveys or interviews. Web fetches may fail on JavaScript-heavy or paywalled pages, so findings are a snapshot in time.