Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when an International Economic Review (IER) result may be sensitive to specification, sample, functional form, calibration, or inference choices. Organizes robustness by threat to the load-bearing assumption; it does not run the regressions.
Use when the model is the contribution for an International Economic Review (IER) manuscript and its assumptions, results, or comparative statics are not yet tight. Stress-tests load-bearing assumptions, generality, and the proof to IER's theory/structural bar; it does not write the proofs.
Use when deciding whether a question is broad and rigorous enough for an International Economic Review (IER) manuscript, and which branch (theory / structural-macro / econometric method / applied micro) frames it. Tests fit and scope; it does not invent evidence or citations.
Use when running and reporting the computational experiments — and assembling the reproducible code/data deposit — for an INFORMS Journal on Computing (IJOC) manuscript. Turns a designed protocol (see ijoc-methods) into defensible, reproducible results; it does not redesign the experiment.
Use when staking the computational/methodological contribution of an INFORMS Journal on Computing (IJOC) manuscript against OR/MS and CS prior art. Positions the advance relative to the right baselines and the right frontier; it does not invent citations.
Use when the method choice, baselines, and computational-experiment design need alignment for an INFORMS Journal on Computing (IJOC) manuscript — before the experiments are run at scale. Designs a fair, reproducible experimental protocol; it does not write the algorithm proofs (see ijoc-theory-development).
Use when the algorithm or model formulation, its correctness, and its theoretical guarantees are the bottleneck for an INFORMS Journal on Computing (IJOC) manuscript. Pins down formulation, complexity, and what the method provably does before experiments are finalized; it does not run the experiments.
Use when deciding whether a project is computing-first enough for an INFORMS Journal on Computing (IJOC) submission and which of its 10 technical areas fits. Scopes the contribution to the OR↔computing interface; it does not invent results or citations.
Use when designing or auditing ACM IMC measurements, covering representative vantage points, honest ground truth, longitudinal design for a moving Internet, safe and ethical active measurement, coverage-bias quantification, provenance pinning, and matching the measurement to the shape of each claim about the real Internet.
Use when strengthening ACM IMC reproducibility and availability evidence, covering the artifact-availability declaration, measurement provenance (vantage points, dates, tool versions), dataset release with schema, honest reproducibility for a moving Internet, the Replicability Track, and consistency between what the paper claims and what the released data contains.