deep-research

Orchestrates a 13-agent pipeline for academic research, literature review, and APA report generation.

Updated Sep 9, 2026
One-click install
npx skills add https://github.com/xlinh2301/EditCTC --skill deep-research-xlinh2301
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/xlinh2301/EditCTC/tree/main/.agents/skills/deep-research
Command: npx skills add https://github.com/xlinh2301/EditCTC --skill deep-research-xlinh2301

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Conducting rigorous academic research requires coordinating question formulation, systematic literature search, source verification, synthesis, and report writing — 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 6 phases (scoping, investigation, analysis, composition, review, revision) with devil's advocate checkpoints and ethics review. - 8 Operational Modes: Choose from full research, quick brief, paper review, literature review, fact-check, three-way WHY/HOW/WHAT paper scan, Socratic guided dialogue, and PRISMA 2020 systematic review with optional meta-analysis. - Source Verification & Integrity: Verifies citations against Semantic Scholar, OpenAlex, Crossref, and arXiv, detects hallucinated references, screens predatory journals, and grades evidence quality. - Use Case: Ask it to research the impact of AI on higher education quality assurance, and it produces a verified annotated bibliography, cross-source synthesis, and a full APA 7.0 report that passed editorial and ethics review. ## Quick Start Ask the agent to research a specific topic, for example: 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 run a systematic literature review with PRISMA compliance?▼

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

How does the skill detect hallucinated or fake citations?▼

The source verification agent cross-checks every citation against Semantic Scholar, OpenAlex, Crossref, and arXiv using DOI lookups and title matching. Unmatched identifiers, retracted papers, and predatory journals are flagged, and contamination signals mark post-2024 preprints for extra scrutiny.

What is the difference between full mode, quick mode, and lit-review mode?▼

Full mode runs all core agents and produces a 3,000-8,000 word APA report. Quick mode uses four agents for a 500-1,500 word brief. Lit-review mode stops at bibliography, verification, and synthesis, producing an annotated bibliography plus synthesis of 1,500-4,000 words.

Can I use it when I only have a vague research idea?▼

Yes, use socratic mode. A mentor agent guides you through a 5-layer questioning dialogue (clarification, assumptions, evidence, perspectives, implications) to refine a vague interest into a concrete research question without generating answers for you.

Does the deep research skill support Chinese-language sources?▼

Yes, it includes a Chinese literature verification protocol covering ISTIC and CNKI registered DOIs plus PubMed coordinate lookups for Chinese medical journals. Trigger keywords and Socratic mode also support Traditional Chinese and Korean.

When should I not use this skill?▼

Do not use it for writing a paper from existing research (use academic-paper), structured review of a single paper (use academic-paper-reviewer), or a full research-to-paper pipeline (use academic-pipeline). It is designed for the research and evidence-gathering stage.