Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when running and reporting the estimation for a Journal of Policy Analysis and Management (JPAM) manuscript — program-evaluation estimates plus the cost-benefit and distributional analysis JPAM expects, with robustness, heterogeneity, and honest uncertainty. Guides analysis norms; it does not replace the identification design.
Use when positioning a Journal of Policy Analysis and Management (JPAM) manuscript against prior work — the policy-evaluation evidence base, the relevant economics / political-science / public-management literatures, and the policy/program record. Frames the gap and contribution; it does not design the study or write the full review.
Use when defending the causal identification of a Journal of Policy Analysis and Management (JPAM) manuscript — RCTs, difference-in-differences / event study, regression discontinuity / kink, instrumental variables, and synthetic control for policy and program evaluation. Strengthens the design and its assumptions; it does not write estimation code.
Use when anticipating how a Journal of Policy Analysis and Management (JPAM) manuscript will be evaluated — desk screening, double-blind peer review, the article types and which are not peer-reviewed, decision categories, and what JPAM referees reward and punish. Sets expectations; it does not write the paper or the rebuttal.
Use when judging whether a research idea fits the Journal of Policy Analysis and Management (JPAM) — a credibly evaluable policy or program question with a decision-relevant takeaway that reaches across economics, political science, and public management. Tests fit and sharpens the question; it does not design the study or run analysis.
Use when executing and reporting the analysis for a Journal of Public Administration Research and Theory (JPART) manuscript so it survives expert, double-blind review and the journal's mandatory data-and-code release. Covers honest uncertainty, robustness, and the PA-specific traps (common-method bias, selection). Guides analysis norms; it does not fabricate results.
Use when deciding whether a public-administration project fits the Journal of Public Administration Research and Theory (JPART) rather than a sibling venue (PAR, JPAM, Governance). JPART rewards a contribution to public-management theory tested with rigor, not a stand-alone policy finding. Helps frame the question; it does not collect data.
Use when the empirical identification strategy is the bottleneck for a Journal of Political Economy (JPE) manuscript — quasi-experimental designs (DID, IV, RDD, event study) or structural estimation. Stress-tests the design and its economic interpretation before drafting tables; it does not write the model from scratch (see jpe-theory-model).
Use when the main result of a Journal of Political Economy (JPE) manuscript rests on a single specification and you need to pre-empt the alternative-explanation and fragility objections a Chicago referee will raise. Builds the robustness battery and the falsification logic; it does not establish the primary identification (see jpe-identification).
Use when estimating and stress-testing results for a Journal of Public Policy & Marketing (JPP&M) manuscript — treatment effects from experiments, DiD/RDD/synthetic-control policy evaluations, subgroup analyses for vulnerable populations, and policy-interpretable reporting. Runs the analysis; it does not choose the design (jppm-methods).