Deep Research is a domain-agnostic research team for rigorous academic work. It turns a vague topic into a scored research question, designs the method, searches the literature, verifies sources, synthesises the findings and compiles an APA 7.0 report.
Eight modes cover the common situations: full research, a quick brief, paper review, literature review, fact-check, a three-way paper scan, Socratic guided dialogue, and systematic review with optional meta-analysis. Editor, devil’s advocate and ethics agents review the result before it is final.
What You Get
- A precise research question with scope boundaries and a methodology blueprint
- An annotated APA 7.0 bibliography with a documented, reproducible search strategy
- A synthesis that resolves contradictions and names gaps, plus a risk-of-bias assessment for systematic reviews
- A complete research report reviewed by an editor, a devil’s advocate and an ethics agent
Common Use Cases
- Researching a topic from question to finished APA report
- Running a systematic review or meta-analysis with PRISMA reporting
- Fact-checking specific claims against graded sources
- Thinking through a vague research direction with Socratic questions
What Makes It Unique
The team has specialist roles that most single-prompt research skills lack: a source verification agent that grades evidence and flags predatory journals, a devil’s advocate that challenges assumptions, an ethics reviewer, and bias and meta-analysis agents for systematic reviews. A routing step asks for clarification when your materials span several phases, and retrieved web text is treated as data and never as instructions. It pairs with sibling skills for writing, reviewing and a full pipeline.
Under The Hood
The skill loads a long SKILL.md that routes your request to one of eight modes and dispatches agent files from its agents folder, each limited to one phase and its own output folder. The bibliography agent searches literature sources and web pages for the search strategy, and can query the Semantic Scholar API to resolve and de-duplicate sources, skipping that step when the service is unavailable. Agents write the briefs, bibliographies and reports to your project as files. Pasted and fetched text is treated as data, and directives inside it are reported and not followed.