deep-research

Generate structured research prompts with frameworks, sub-questions, and sources.

77|8|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/laborany/laborany --skill deep-research-laborany
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/laborany/laborany/tree/main/skills/deep-research
Command: npx skills add https://github.com/laborany/laborany --skill deep-research-laborany

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image.

What problem does it solve?

深度研究工具将用户提出的研究主题转化为可执行的多源网络研究计划,输出可追溯且带有可点击引用的结构化 Markdown/HTML 报告并保存。

Core Features & Use Cases

  • 自动化研究规划:基于需求快速生成研究框架、核心子问题与信息源指引。
  • 动态领域分析:根据领域识别权威源并定制化检索策略,覆盖中英文平台。
  • 可追溯报告产出:输出带 YAML frontmatter 的多格式报告,包含元数据与完整引用。
  • 快速迭代:在阶段确认后进行多轮更新,确保输出与用户需求对齐。

Quick Start

直接提交你的研究主题,系统将返回一份完整的研究提示词草案供你确认。

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I generate a structured research report with citations from multiple sources?

To generate a structured research report with citations, submit your research topic to receive an executable multi-source research plan. The system produces traceable Markdown or HTML reports complete with YAML frontmatter and clickable citations.

How does automated research planning select frameworks like SWOT or PEST for domain analysis?

Automated research planning dynamically selects appropriate frameworks like SWOT, PEST, or timeline based on your identified domain. It tailors the retrieval strategy by recognizing authoritative sources across Chinese and English platforms.

Can I use citation management to output reports with YAML frontmatter in Markdown format?

Yes, you can use this citation management capability to output Markdown reports featuring YAML frontmatter. The generated reports include complete metadata, integrated research frameworks, and full traceable citations.

Do I need pdfplumber or pypdf to extract text for multi-source search workflows?

You do not need to manually run pypdf or pdfplumber to start the multi-source search workflow. These dependencies support internal PDF processing, allowing you to directly submit research topics for prompt generation.

What is the best way to iterate on prompt engineering for deep research topics?

The best way to iterate on prompt engineering for deep research is to review the initial prompt draft, request adjustments, and confirm the stage. The system performs multi-round updates to ensure the output aligns with your specific domain requirements.