What problem does it solve? Turning a vague research idea into a rigorous empirical design is hard: researchers must position against existing literature, specify hypotheses, variables, data, identification strategy, and robustness checks without overlooking endogeneity risks or data gaps. ## Core Features & Use Cases - Structured Design Generation: Produces an archived design document covering 14 sections, from research question and theory mechanism to expected table structure and next actions. - Context-Aware Grounding: Reads the wiki context, empirical pages, project READMEs, and research-intent notes so the design reflects what the literature already did versus what the project should do. - Honest Feasibility Assessment: Lists missing data fields instead of pretending the design is executable when local data are insufficient. - Use Case: A PhD student studying the effect of remote work on firm productivity invokes the skill after ingesting relevant papers, and receives a dated design document with hypotheses, variable definitions, an identification strategy addressing endogeneity, and a list of data gaps to fill. ## Quick Start Ask the assistant to run the empirical-design skill with your research question, for example: generate an empirical research design for studying how remote work affects firm productivity.
