Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when deciding how code, computations, or data attach to a SODA (ACM-SIAM Symposium on Discrete Algorithms) paper — SODA itself runs no artifact track, so this skill covers computer-assisted proof evidence, implementation companions, and when to route the artifact to co-located ALENEX's formal artifact evaluation instead.
Use when deciding whether and how experiments belong in a SODA (ACM-SIAM Symposium on Discrete Algorithms) paper — SODA's scope includes experimental validation but theorems carry the decision, so this skill designs supporting numerics honestly and routes implementation-led work to co-located ALENEX or to SEA.
Use when positioning a SODA (ACM-SIAM Symposium on Discrete Algorithms) paper in the algorithms literature — tracing bound lineages across SODA/STOC/FOCS/ESA/ICALP and journals, handling arXiv-first priority culture, citing conference versus journal versions correctly, and self-citation under lightweight double-blind rules.
Use when reasoning about how a SODA (ACM-SIAM Symposium on Discrete Algorithms) submission is evaluated — the per-edition program committee under joint ACM-SIAM sponsorship, HotCRP triage of a record-size submission pool, lightweight double-blind refereeing of full versions, the September rebuttal, and October decisions.
Use when deciding whether a result is SODA-shaped (ACM-SIAM Symposium on Discrete Algorithms) — concrete algorithmic problems, data structures, and discrete mathematics with quantitative progress — versus routing to STOC/FOCS, ESA, ICALP, ITCS, SOSA, ALENEX, SoCG, or a journal, judged from SODA's algorithms-first identity.
Use when hardening the reproducibility of a SOSP paper's results before submission — pinning the OS-level environment, recording hardware and topology, making every figure regenerable from logged runs, separating measurement noise from effect size, and preparing the ground for post-acceptance artifact evaluation.
Use when executing and reporting the analysis for a Social Psychology Quarterly (SPQ) manuscript so it survives expert, masked review — honest uncertainty, robustness, sound measurement, and reporting appropriate to experiments, surveys/secondary data, or interpretive analysis in sociological social psychology. Guides analysis norms; it does not fabricate results.
Use when building or fixing the literature review for 《中国社会科学》 (Social Sciences in China) — entering the theoretical lineage (classic authors and schools) rather than piling up recent empirical citations, and positioning the paper as a move within an ongoing scholarly conversation. Use when references are a variable-list instead of a theory dialogue.
当需要为《中国科学：信息科学》(Scientia Sinica Informationis, SSI) 稿件设计与呈现实验、使证据与主张相称时调用。覆盖主张-证据匹配、真实数据与代表性基准、公平对比与统一评测协议、仿真/半实物/硅后实测/理论证明的区分、统计报告与显著性、消融实验隔离贡献、跨子学科（计算机/控制/通信/微电子）的证据范式，以及理论类论文的证明呈现。作为国家级大信息学科综合旗舰，本刊强调科学价值与严谨证据，实验设计需经得起外审推敲。
当需要理解《中国科学：信息科学》(Scientia Sinica Informationis, SSI) 的审稿流程、校准评审预期、判断作者在各环节的可行动空间时调用。覆盖编辑部初审→编委送外审→外审专家评议→复审→主编/编委会终审的链路、三审三校制度（报道级，以官网为准）、审稿原则（公平公正公开客观）、退修（大修/小修）与录用/退稿决定、90 天未获意见可改投的条款、审稿周期与轮次，以及与英文姊妹刊 Science China Information Sciences 评审的异同。适用于投稿后到录用前的全过程校准。