deep-research

Orchestrate parallel multi-agent research workflows and generate structured reports.

Updated Dec 11, 2025
One-click install
npx skills add https://github.com/Fancu1/dotfile --skill deep-research-fancu1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/Fancu1/dotfile/tree/main/skills/deep-research
Command: npx skills add https://github.com/Fancu1/dotfile --skill deep-research-fancu1

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates complex, multi-stage research tasks by breaking them down into parallelizable sub-goals, executing them across multiple agents, and then systematically aggregating, refining, and delivering a polished, comprehensive report.

Core Features & Use Cases

  • Parallel Agent Orchestration: Decomposes a broad research objective into smaller, concurrently executable sub-tasks.
  • Automated Data Gathering: Leverages installed skills or MCP tools for web crawling, data collection, and information retrieval.
  • Structured Report Generation: Aggregates findings from sub-processes into a coherent, chaptered report with key conclusions and recommendations.
  • Use Case: Conducting a thorough competitive analysis for a new product, involving market trends, competitor strategies, and customer sentiment, culminating in a detailed strategy report.

Quick Start

Use the deep-research skill to conduct a comprehensive analysis of the latest advancements in renewable energy technologies.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I automate competitive analysis and generate a structured research report?

Automated competitive analysis report generation is achieved by decomposing a broad research objective into parallel sub-goals. Multiple agents execute these sub-tasks concurrently to gather data, which is then systematically aggregated into a chaptered report with key conclusions.

How does multi-agent orchestration work for parallel web research?

Multi-agent orchestration for web research works by breaking down a target into smaller, concurrently executable sub-tasks within a sandboxed environment. Each agent leverages installed skills or MCP tools for data retrieval, and sub-results are aggregated via scripts into a polished report.

Do I need specific web crawling tools installed to use automated data aggregation?

Automated data aggregation prioritizes web access through your installed skills or MCP tools. You need to provide these data retrieval mechanisms beforehand so the parallel agents can successfully gather and aggregate the required information for the final report.

What is the best way to conduct a deep dive into market trends and competitor strategies?

The best way to conduct a deep dive into market trends and competitor strategies is using parallel agent orchestration. This approach systematically executes concurrent sub-goals for data collection and aggregates the findings into a comprehensive, evidence-based strategy report.

Can I use this systematic research approach for evidence-based writing on renewable energy?

Systematic research for evidence-based writing on topics like renewable energy is fully supported. The workflow decomposes the subject into parallel sub-goals, gathers data via web tools, and delivers a polished, chaptered report with actionable conclusions.

What are the limitations of using sandboxed environments for multi-agent data gathering?

Sandboxed environments for multi-agent data gathering limit direct access to local system resources and restricted networks. Data retrieval is strictly mediated through installed skills or MCP tools, meaning any external source requiring authentication outside these tools cannot be accessed.