deep-research

Decompose research objectives into structured sub-questions and executable tasks.

7|1|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/LvcidPsyche/polymarket-arbitrage-bot --skill deep-research-lvcidpsyche
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/LvcidPsyche/polymarket-arbitrage-bot/tree/main/skills/deep-research
Command: npx skills add https://github.com/LvcidPsyche/polymarket-arbitrage-bot --skill deep-research-lvcidpsyche

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep Research Agent helps teams tackle complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files.

Core Features & Use Cases

  • Multi-Step Research Planning: The agent doesn't just search; it plans. It decomposes your high-level objective into a structured set of sub-questions and executable tasks to ensure no detail is overlooked.
  • Task Decomposition & Orchestration: Specialized subagents are orchestrated to handle isolated research threads or domains, allowing for parallel exploration and deeper domain-specific analysis.
  • Large-Context Document Analysis: Leveraging advanced long-context reasoning, the agent can analyze extensive volumes of documentation, files, and search results to find the "needle in the haystack."
  • Cross-Thread Memory Persistence: Key findings, decisions, and context are persisted across conversations. This allows for iterative research that builds upon previous discoveries without losing momentum.
  • Synthesized Reporting: The final output is a coherent, well-supported analysis or recommendation that integrates findings from multiple sources into a clear and actionable report.

Quick Start

Invoke the deepsearch command with your research objective to begin planning, decomposition, and synthesis.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I decompose complex research objectives into structured sub-questions?

To decompose complex research objectives into structured sub-questions, use an agent that plans multi-step workflows, delegates isolated threads to subagents, and aggregates findings for synthesis. This ensures no detail is overlooked during investigation.

What is the best way to maintain context across long research sessions?

The best way to maintain context across long research sessions is using cross-thread memory persistence. This mechanism saves key findings, decisions, and context across conversations, enabling iterative research that builds upon previous discoveries without losing momentum.

Can I use subagents to orchestrate parallel exploration for academic research?

Yes, you can use subagents to orchestrate parallel exploration for academic research. Specialized subagents handle isolated research threads or domains, allowing coordinated exploration and deeper domain-specific analysis across your long-context reasoning tasks.

How do I synthesize findings from multiple sources into a coherent report?

To synthesize findings from multiple sources into a coherent report, apply an orchestration workflow that aggregates context from subagents and leverages long-context reasoning. This integrates diverse discoveries into a clear, actionable analysis.

Does deep research planning work with large volumes of documentation?

Yes, deep research planning works with large volumes of documentation by leveraging advanced long-context reasoning. It analyzes extensive files and search results to find the needle in the haystack during complex investigative workflows.