Research, academic papers, education, and exam prep (4.4K skills)
Find your way around Diverga with a guide to its 24 research agents across nine categories. View commands, example requests, direct invocation syntax, and checkpoints where people review research decisions, with recommendations based on research context.
Design studies that combine quantitative data, such as surveys, with qualitative evidence, such as interviews. It recommends a suitable design and outlines study phases, participant selection, timing, and ways to combine findings into an integrated interpretation.
Clarify the philosophical assumptions behind a research project and check whether they fit the proposed methods. Get a reasoned research stance, draft proposal wording, and guidance for explaining how the researcher's background and values shape the study.
Download and read academic PDFs in small batches, splitting them into four-page files. Build structured notes covering research questions, methods, data, findings, and replication feasibility, with progress saved after each batch.
Generate 15–20 research directions from a question, topic, or data opportunity, then narrow them to 5–7 candidates. Receive ranked ideas with feasibility assessments, key risks, confidence scores, and reasons for rejecting the others.
Review academic manuscripts for argument quality, causal evidence, statistical methods, citations, and presentation. Receive a structured report with strengths, major concerns, suggested improvements, and likely referee objections tied to specific parts of the paper.
Configure the social-science-research plugin through guided questions about your field, institution, journals, and datasets. Save research preferences, researcher details, and R figure colors in project files for use in your research context.
Check citations in LaTeX and Quarto manuscripts against a bibliography file. Find missing references, unused entries, and likely citation key typos, then flag incomplete fields, author formatting problems, and character encoding issues.
Review a research paper alongside its Stata, R, or Python code to check reproducibility, code quality, and agreement with the main findings. Receive a Markdown report with supporting evidence, uncertainties, strengths, and prioritized next steps.
Set up a research project with separate folders for code, source data, cleaned datasets, results, and documents. Create a research rules file from a template, a project README, and an initial progress log.
Turn an initial research idea into a project specification through a structured interview. Develop testable questions, hypotheses, methods for identifying causal effects, and data requirements, then rank options by feasibility and contribution and save the plan.
Check a paper's numerical claims against saved analysis outputs before submission. Receive a report identifying verified figures, unsupported claims, missing files, unreferenced outputs, and citation keys absent from the bibliography, without changing the manuscript.
Check an economics paper before submission with two parallel reviewers. Assess its contribution, whether the design supports causal conclusions, and unsupported claims, then receive a short report with fixes ranked by severity.
Find datasets for a research question and compare whether they support the planned study. Receive ranked candidates with feasibility grades, coverage, access requirements, methodological limitations, and recommended next steps for obtaining the most suitable data.
Turn research ideas into a coordinated program with clear questions, data needs, methods, team roles, and publication plans. Connect academic papers with policy and public-facing outputs while considering feasibility, data availability, and long-term institutional activities.
Build and check research replication packages so a project's results can be reproduced. Routes checks to a dedicated agent that examines seeds, versions, file paths, workflow integrity, data documentation, execution environments, and matching outputs.
Carry a research task from brainstorming and planning through code implementation, review, and documentation. Multiple agents handle independent implementation tasks in parallel, then report the resulting files, changes, and findings.
Examine figures, tables, and empirical results before interpreting them. The skill reviews every visible feature, explores possible explanations, checks sample sizes and patterns across estimates, and records unresolved questions in a structured report.
Turn regression results, summary statistics, and simulation output into tables and figures for academic papers. Apply consistent number formatting, labels, and accessible visual styles, then produce files ready to include in LaTeX documents.
Review a grant proposal before submission through six specialized perspectives. Receive a consolidated report covering funder fit, research methods, feasibility, budget, consistency, and writing, with prioritized revisions and questions a review panel might ask.
Review econometric code, proofs, data workflows, and outputs with multiple specialist agents. Assess identification—the assumptions that let data establish an effect—alongside estimation, numerical stability, and reproducibility, then consolidate findings into prioritized tasks.
Prepare academic papers for journal submission by checking manuscripts and figures, adapting journal formatting, drafting cover letters and responses to reviewers, and tracking revisions through resubmission with a structured response table.
Assess a social science paper outline in a .qmd file for missing research questions, contributions, hypotheses, data, and analysis plans. Receive criterion ratings and concrete suggestions in a separate report, with causal assumptions assessed when relevant.
Turn social science papers into structured Markdown reading notes covering contributions, key findings, methods, data, and limitations. Summaries include quantitative results, references to relevant tables or pages, keywords, and a BibTeX citation for later reference.