deep-research

Coordinate multi-source research and generate verified reports.

3|Updated Feb 24, 2026

Search Tags:#automation #code analysis #research #web search #multi-agent #information synthesis

One-click install

npx skills add https://github.com/phyr97/deep-research --skill deep-research-phyr97

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/phyr97/deep-research/tree/main/skills/deep-research
Command: npx skills add https://github.com/phyr97/deep-research --skill deep-research-phyr97

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines complex research tasks by orchestrating multiple specialized sub-agents to gather, verify, and synthesize information efficiently.

Core Features & Use Cases

Multi-Mode Research: Conducts web, codebase, knowledge, or combined investigations tailored to the user's query.
Automated Planning and Dispatch: Plans detailed sub-questions with specified depths and angles, then dynamically spawns appropriate scrapers.
Result Synthesis: Aggregates findings from multiple sources, verifies claims, and creates comprehensive reports.
Use Case: A developer needs an in-depth analysis of a new library’s security features, involving web research, code review, and expert knowledge verification, all coordinated seamlessly.

Quick Start

Ask the AI to analyze a specific technical topic, for example: "Evaluate the security implications of using OAuth 2.0 in mobile apps," and the Skill will orchestrate the research process automatically.

Frequently Asked Questions about deep-research

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

FAQPage Schema

How do I automate multi-source research across web and codebases?▼

Multi-source research is automated by coordinating specialized sub-agents to collect, verify, and synthesize findings from web pages, codebases, and expert knowledge into a structured report.

What is the best way to synthesize information from multiple web searches?▼

Information synthesis from multiple web searches is handled by aggregating findings from dynamically spawned scrapers, verifying claims across sources, and generating comprehensive reports.

Can I generate a comprehensive report evaluating library security features?▼

You can generate comprehensive reports by asking the AI to evaluate a specific technical topic, which orchestrates web research, code review, and expert knowledge verification.

Does multi-agent research support planning sub-questions for complex technical analysis?▼

Multi-agent research supports complex technical analysis by planning detailed sub-questions with specified depths and angles before dynamically spawning appropriate target-specific scrapers.