Auto-Empirical-Research-Skills
Auto-Empirical Research Skills (AERS) is a curated academic-industrial AI toolkit for empirical research, developed by Stanford REAP and CoPaper.AI. It provides a verified library of over 1,072 vendored agent skills and a mapped ecosystem of 23,000+ skills across 119 repositories covering eight social science disciplines. The system automates the full research pipeline from data cleaning and identification to estimation, robustness checks, table generation, and submission-ready drafting. Unlike standard marketing lists, AERS focuses on verified behavior matched against known answers, ensuring reproducibility and accuracy. It includes a numeric benchmark, eval harness, security audit, and continuous integration to maintain quality. Designed for researchers, the toolkit supports rapid completion of empirical papers while allowing user-contributed skills. The project emphasizes trust through multi-layer validation and organizes capabilities by research workflow stages to streamline complex analytical tasks.