deep-research

Perform structured multi-round web research across diverse sources.

14|1|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/stay-leave/mini_agent --skill deep-research-stay-leave
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/stay-leave/mini_agent/tree/main/skills/deep-research
Command: npx skills add https://github.com/stay-leave/mini_agent --skill deep-research-stay-leave

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a systematic framework for online information gathering, guiding multi-round, multi-angle web research so that answers come from diverse, verified sources rather than single, shallow searches.

Core Features & Use Cases

  • Structured research workflow that coordinates multi-query sessions across different angles and sources.
  • Guidance for research-before-creation tasks, ensuring up-to-date and multi-perspective context for reports, presentations, UI, and content.
  • Best-practice prompts and decision criteria to decide when to stop searching and how to synthesize results.

Quick Start

Trigger the deep-research workflow to start multi-round web_search across multiple queries.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I conduct multi-source web research to verify online information?

Multi-source web research verifies online information by executing structured, multi-round search strategies across diverse perspectives. It employs iterative refinement and strict search discipline to ensure gathered results are accurate, balanced, and properly cited.

What is the best way to gather context before creating reports or presentations?

Context gathering for reports uses a structured research workflow that coordinates multi-query search sessions across different angles. This ensures up-to-date, multi-perspective context is synthesized from diverse, verified online sources before content generation.

When do I need a multi-round search strategy for information gathering?

A multi-round search strategy is needed when single, shallow searches fail to provide accurate answers. It enables dimensional exploration and iterative refinement to gather balanced perspectives and verify information from diverse web sources.

Can I use dimensional exploration to ensure source diversity in my research?

Dimensional exploration ensures source diversity by guiding multi-angle web research across different queries. This structured approach coordinates multiple search sessions, guaranteeing that results are synthesized from varied, verified online sources.

How does the research workflow decide when to stop searching and synthesize results?

The research workflow decides when to stop searching by applying best-practice prompts and decision criteria. It evaluates whether diverse, verified information has been gathered across multiple rounds before synthesizing the final results.