deep-research

Conduct multi-source web research and synthesize findings into cited reports with source credibility scoring.

Updated Apr 20, 2026
One-click install
npx skills add https://github.com/AmirEmad11/instabot --skill deep-research-amiremad11
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/AmirEmad11/instabot/tree/main/.local/secondary_skills/deep-research
Command: npx skills add https://github.com/AmirEmad11/instabot --skill deep-research-amiremad11

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Answering complex questions that require more than a quick search—market analysis, technology evaluations, due diligence, fact-checking—demands gathering dozens of sources, cross-checking conflicting claims, and synthesizing everything into a trustworthy report. Doing this manually is slow and error-prone. ## Core Features & Use Cases - Parallel Multi-Agent Research: Decomposes a topic into focus areas and launches simultaneous research subagents, each running multiple web searches and fetching full articles. - Source Triangulation & Credibility Scoring: Rates sources into tiers (government/academic, major publications, blogs) and requires 3+ sources for every major claim, with explicit conflict resolution rules. - Structured Cited Reports: Produces prose-first 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 comprehensive report covering market share, battery technology, policy, infrastructure, and consumer economics—every claim backed by cited, tier-rated sources. ## Quick Start Research the competitive landscape of the electric vehicle market in 2026 and write a cited report with source credibility ratings.

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, cross-references sources, and delivers a cited report.

What research depth tiers are available and when should I use each?

Three tiers exist: Quick (3 subagents, 8+ sources, 2-5 minutes) for focused questions, Standard (5 subagents, 15+ sources) for most requests, and Deep (25+ sources with gap-fill and self-critique) for critical decisions or comprehensive reviews.

How does source credibility scoring work in research reports?

Sources are rated in three tiers: Tier 1 for government, multilateral, and academic sources; Tier 2 for major publications and industry reports; Tier 3 for blogs and promotional content. Major claims require 3+ sources, with higher tiers preferred when data conflicts.

When should I use a simple 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 multi-angle questions needing many sources, such as market analysis, technology comparisons, or claim verification.

What are the limitations of web-based deep research?

It cannot access paywalled journals, subscription databases, or social media content, and cannot conduct primary research like surveys or interviews. Some pages fail to fetch due to JavaScript or paywalls, mitigated by retries and alternative URLs.

Can deep research handle country-specific or non-English topics?

Yes. Research subagents run at least one or two searches in the local language for country or region-specific topics, since government data, local media, and industry reports are often only published in the local language.