deep-research

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

Updated May 19, 2026
One-click install
npx skills add https://github.com/richardnguyen0715/agent-sharing --skill deep-research-richardnguyen0715
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/richardnguyen0715/agent-sharing/tree/main/.github/skills/deep-research
Command: npx skills add https://github.com/richardnguyen0715/agent-sharing --skill deep-research-richardnguyen0715

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Conducting rigorous academic research requires coordinating literature search, source verification, synthesis, bias checking, and report writing — a process that is slow, error-prone, and vulnerable to confirmation bias and fabricated citations when done ad hoc. ## Core Features & Use Cases - 13-Agent Research Pipeline: Coordinates specialized agents across 6 phases (scoping, investigation, analysis, composition, review, revision) with mandatory Devil's Advocate checkpoints and ethics review. - 7 Operational Modes: full, quick, review, lit-review, fact-check, socratic (guided research dialogue), and systematic-review (PRISMA 2020 with RoB 2/ROBINS-I and meta-analysis). - Source Integrity Controls: Cross-index triangulation via Semantic Scholar, OpenAlex, and Crossref to detect hallucinated or contaminated citations, plus predatory journal screening. - Use Case: Ask it to research the impact of AI on higher education quality assurance, and it produces a verified annotated bibliography, synthesis with gap analysis, and a full APA 7.0 report reviewed by editorial, ethics, and devil's advocate agents. ## Quick Start Ask the assistant to research a topic such as the impact of AI on higher education quality assurance and select a mode like full, quick, or socratic.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I run a systematic literature review with PRISMA compliance?▼

Invoke the systematic-review mode, which follows a 5-phase PRISMA 2020 protocol: protocol registration, systematic search, screening, data extraction with risk of bias assessment (RoB 2 and ROBINS-I), and synthesis with optional meta-analysis and GRADE rating.

What is the difference between full, quick, and socratic research modes?▼

Full mode runs all core agents producing a 3,000-8,000 word APA report. Quick mode produces a 500-1,500 word brief. Socratic mode guides you through a 5-layer questioning dialogue to refine a vague idea into a concrete research question without giving direct answers.

How does the pipeline detect fabricated or hallucinated citations?▼

The bibliography agent triangulates every source across Semantic Scholar, OpenAlex, and Crossref, flagging unmatched entries and post-2024 preprints as contamination signals. Unverifiable references are treated as failures, never as uncertain.

Can deep-research hand off results to academic paper writing?▼

Yes. It hands off the Research Question Brief, Methodology Blueprint, Annotated Bibliography, and Synthesis Report to the academic-paper skill, whose intake agent skips redundant steps like topic scoping and literature search.

What happens when the Devil's Advocate finds a critical issue?▼

Critical-severity findings block pipeline progression until resolved. Revision loops are capped at two iterations, and any remaining unresolved issues are documented in an acknowledged limitations section of the final report.

Does the research pipeline support languages other than English?▼

Yes. Trigger keywords and Socratic mode support Traditional Chinese alongside English, and the output language follows the user's language while keeping academic terminology in English.