academic-deep-research

Orchestrates a 13-agent pipeline for rigorous academic research and APA 7.0 report generation.

Updated Sep 8, 2026
One-click install
npx skills add https://github.com/salomepoulain/makery-stations --skill academic-deep-research-salomepoulain
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: academic-deep-research
Source: https://github.com/salomepoulain/makery-stations/tree/main/stations/claude/workbench/pantry/skills/academic-deep-research
Command: npx skills add https://github.com/salomepoulain/makery-stations --skill academic-deep-research-salomepoulain

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Conducting rigorous academic research requires formulating answerable research questions, systematically searching literature, verifying sources, synthesizing evidence, and producing properly formatted reports — a process that is slow, error-prone, and hard to keep methodologically consistent when done manually. ## Core Features & Use Cases - 13-Agent Research Pipeline: Coordinates specialized agents across six phases (scoping, investigation, analysis, composition, review, revision) with mandatory devil's advocate checkpoints and ethics review. - Eight Operational Modes: Choose from full research, quick brief, paper review, literature review, fact-check, three-way WHY/HOW/WHAT paper scan, Socratic guided research dialogue, and PRISMA 2020 systematic review with optional meta-analysis. - Quality Safeguards: Source verification with evidence-hierarchy grading, predatory journal detection, risk-of-bias assessment (RoB 2, ROBINS-I), and APA 7.0 report compilation with editorial review. - Use Case: A graduate student unsure of a research direction starts in Socratic mode to converge on a FINER-scored research question, then escalates to a full systematic review with meta-analysis and a PRISMA-compliant report. ## Quick Start Ask the assistant to research a topic such as the impact of AI on higher education quality assurance, or request guided research help when your research question is still vague.

Frequently Asked Questions about academic-deep-research

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

FAQPage Schema
How do I run a systematic review with meta-analysis using AI agents?

Invoke the systematic-review mode, which follows a PRISMA 2020-compliant five-phase protocol: protocol registration, systematic search, screening, data extraction with risk-of-bias assessment (RoB 2 and ROBINS-I), and synthesis with GRADE. It produces a full PRISMA report plus forest plot data.

What research modes does this skill support?

Eight modes are available: full research, quick brief, paper review, literature review, fact-check, three-way WHY/HOW/WHAT paper scan, Socratic guided dialogue, and systematic review with optional meta-analysis. A selection flowchart in the skill routes your situation to the right mode.

How does Socratic mode help when I have no clear research question?

Socratic mode activates a mentor agent that guides you through five dialogue layers — clarification, assumption probing, evidence, perspectives, and implications — without giving direct answers. It is the default recommendation when your research direction is vague.

Does the skill verify sources and detect predatory journals?

Yes. A dedicated source verification agent grades sources on an evidence hierarchy, screens for predatory journals, flags conflicts of interest, and assesses currency. Fact-check mode runs this verification standalone on specific claims.

When should I use academic-paper instead of this research skill?

Use academic-paper when you are writing a paper rather than researching, and academic-paper-reviewer for structured review of an existing manuscript. This skill handles the research phase and hands off its artifacts (RQ brief, bibliography, synthesis) to academic-paper for drafting.

What happens when the research pipeline finds a critical flaw?

The devil's advocate agent runs three mandatory checkpoints and blocks progression on critical-severity issues such as fatal logical flaws. Revision loops are capped at two iterations, with remaining issues documented as acknowledged limitations.