Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when deciding whether a result is COLT-shaped (Conference on Learning Theory) — a theorem-first learning-theory contribution — versus better routed to ALT, STOC/FOCS, NeurIPS/ICML/AISTATS, JMLR, or a statistics journal, and whether the right vehicle is a full paper or a COLT open-problem piece.
Use when executing and reporting the analysis for a Communication Research (CR) manuscript so it survives expert, double-anonymized review — ANOVA/regression/SEM, mediation/moderation with honest uncertainty, reliability, and APA statistical reporting. Guides analysis norms; it does not fabricate results.
Use when defending the research design of a Communication Research (CR) manuscript — experiments (lab/online), panel surveys, and content analysis with intercoder reliability. CR is quantitative and demanding about identification, measurement, and confound control. Strengthens the design; it does not write code.
Use to understand how Communication Research (CR) evaluates a manuscript — double-anonymized review, editorial screening for quantitative/theory fit, external review, and the requirement that two independent positive reviews back a Revise or Accept decision. Sets expectations and shapes the paper to survive review; it does not contact editors.
Use when deciding whether a communication project fits Communication Research (CR) and is shaped as quantitative, theory-testing social science. CR rewards a clear communication-science question with a testable mechanism, not platform novelty or description. Helps frame the question; it does not collect data.
Use when executing and reporting the analysis for a Conservation Biology manuscript so it survives expert, double-blind review — appropriate ecological/statistical models, honest uncertainty, robustness, and reproducibility. Covers detection, hierarchical models, spatial structure, and effect sizes that matter for conservation. Guides analysis norms; it does not fabricate results.
Use when positioning a Conservation Biology manuscript against the literature so it reads as a novel, transferable contribution to conservation science. Conservation Biology readers span ecology, social science, and practice, so the paper must engage the relevant conservation literatures and state the gap precisely. Stakes the contribution; it does not write the literature review.
Use to understand how Conservation Biology evaluates a manuscript — double-blind peer review (adopted 2014), editorial screening for scope/novelty/conservation relevance, the editorial-board structure, decision categories, and the Registered Reports route. Sets expectations and shapes the paper to survive review; it does not contact editors.
Use when designing or auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments, honest and tuned baselines, measurement statistics and uncertainty, trace and config provenance, and contamination-aware ablations for ML-for-networking work.
Use when deciding whether a networking project belongs at ACM CoNEXT or should be routed to SIGCOMM, NSDI, IMC, SIGMETRICS, MobiCom, or HotNets, and when using CoNEXT's two-cycles-per-year calendar and PACMNET journal-style fit to choose the venue and the cycle by contribution shape and evidence maturity.