Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This collection provides a structured framework for quantitative social scientists and applied economists to manage the full lifecycle of empirical research. It streamlines the transition from raw data acquisition through causal inference and econometrics to the production of publication-ready manuscripts.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Expected outputs or reference results, if available
Check the repository for this skill’s setup.
Use the replicate skill to inspect the project at [PROJECT_DIRECTORY]. Start with a concise preflight covering seeds, software versions, paths, pipeline integrity, data documentation, environment documentation, and whether expected outputs can be matched. Report the most important issues and proposed next checks without modifying files.
Use the lit-review skill for [TOPIC_OR_RESEARCH_QUESTION]. Produce a concise initial literature map organized into theoretical contributions, empirical findings, methodological innovations, and open debates. Include a small set of relevant citations, distinguish working papers from published papers, note empirical identification strategies, and explicitly flag any citation that cannot be verified. Check [SUPPORTING_PAPERS_DIRECTORY] and existing .bib files if provided.
Use the stata-power-analysis skill to draft a concise power-analysis brief for [STUDY_DESIGN]. Clarify the estimand and target effect size, list the assumptions required for the calculation, and explain what additional inputs are needed to estimate power, minimum detectable effect, or sample size. Distinguish prospective power analysis from ex post rationalization.
Claude
Codex
Cursor
OpenClaw
Antigravity