deep-research

Automate systematic academic literature reviews across search, analysis, and report compilation.

Updated Jun 12, 2026
One-click install
npx skills add https://github.com/flowel/AiSkills --skill deep-research-flowel
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/flowel/AiSkills/tree/main/skills/codex/deep-research
Command: npx skills add https://github.com/flowel/AiSkills --skill deep-research-flowel

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires paper_finder, search_semantic_scholar, pdf2image, arxiv, semantic_scholar, openreview, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill systematically conducts academic literature reviews, saving time and ensuring thoroughness in research processes.

Core Features & Use Cases

  • Systematic Review: Follows a strict 6-phase workflow for literature reviews.
  • Structured Notes: Generates structured notes for each paper, with detailed analysis.
  • Synthesized Report: Outputs a comprehensive report organized by phase.
  • Use Case: When conducting a literature review for a research project, this Skill helps organize papers, extract insights, and compile a final report.

Quick Start

Use the deep-research skill to initiate a literature review on the topic "machine learning for natural language processing".

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I automate a systematic literature review for academic research?

Automate a systematic literature review by using a 6-phase workflow that searches APIs, downloads papers, deep reads text, analyzes code, and compiles a synthesized report.

Can I search arXiv and Semantic Scholar papers for a comprehensive academic review?

Yes, search arXiv and Semantic Scholar papers directly by utilizing integrated APIs to retrieve, download, and extract detailed insights for academic research synthesis.

What is the best way to generate a structured report from multiple academic papers?

Generate a structured report by deep reading each paper, extracting structured notes with detailed analysis, and synthesizing the extracted insights into a final comprehensive document.

Does the systematic review process require pre-downloaded PDFs to analyze papers?

No, the systematic review process does not require pre-downloaded PDFs because it utilizes various APIs and Python libraries for automatically searching and downloading papers for analysis.

How does deep reading and code analysis work during a literature review?

Deep reading and code analysis work by processing downloaded papers and assets to extract structured notes, validate findings, and synthesize comprehensive insights for the final report.

What happens if paper_finder or search_semantic_scholar APIs fail during a review?

If APIs fail during a review, robust error handling and validation mechanisms across all phases ensure the systematic literature review process continues without interrupting the final report compilation.