deep-research

Conducts academic research via a 13-agent pipeline from question formulation to APA 7.0 report.

Updated Jun 4, 2026
One-click install
npx skills add https://github.com/Hdx123321/Test --skill deep-research-hdx123321
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/Hdx123321/Test/tree/main/.claude/skills/deep-research
Command: npx skills add https://github.com/Hdx123321/Test --skill deep-research-hdx123321

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, matplotlib, seaborn, spacy, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a comprehensive solution for rigorous academic research, handling a wide range of tasks from question formulation to literature review, analysis, report compilation, and ethical review.

Core Features & Use Cases

  • Research Question Formulation: Transforms vague topics into precise, FINER-scored research questions with scope boundaries.
  • Systematic Literature Search: Identifies relevant sources, applies inclusion/exclusion criteria, and creates annotated bibliographies in APA 7.0 format.
  • Synthesis & Analysis: Integrates evidence, resolves contradictions, and performs thematic synthesis.
  • Report Compilation: Drafts APA 7.0 reports, including title, abstract, methodology, findings, discussion, and references.
  • Ethical Review: Assesses AI-assisted research ethics, attribution integrity, dual-use screening, and fair representation.
  • Use Case: Ideal for researchers needing a full academic pipeline, from formulating a research question to compiling a complete APA 7.0 report.

Quick Start

Research the impact of AI on higher education quality assurance.

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 and APA 7.0 report compilation?

Automate systematic literature reviews by using a 13-agent pipeline to handle research question formulation, source verification, cross-source synthesis, and final APA 7.0 report compilation. It resolves contradictions and assesses risk of bias.

Can I perform a meta-analysis and risk of bias assessment using Python?

Perform meta-analysis and risk of bias assessment using Python by leveraging dependencies like pandas and numpy. The pipeline integrates these libraries to resolve contradictions and synthesize cross-source evidence for systematic reviews.

Does this deep research pipeline handle AI-assisted research ethics and dual-use screening?

The deep research pipeline handles AI-assisted research ethics by conducting dedicated ethics reviews, attribution integrity checks, dual-use screening, and fair representation assessments within its comprehensive 13-agent workflow.

What is the best way to formulate FINER-scored research questions for academic research?

Formulate FINER-scored research questions by applying Socratic mentoring within the pipeline to transform vague topics into precise queries with clear scope boundaries. This ensures systematic review questions meet rigorous academic standards.

Do I need spacy and matplotlib installed to run systematic review scripts?

You need spacy and matplotlib installed along with pandas, numpy, and seaborn to run the systematic review scripts. These Python libraries support various tasks including natural language processing and data visualization within the research pipeline.

Why does the systematic review pipeline include a devil's advocate challenge?

The systematic review pipeline includes a devil's advocate challenge to critically test the robustness of your cross-source synthesis and editorial review. This ensures the compiled APA 7.0 report withstands rigorous academic scrutiny and resolves evidence contradictions.