Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when anticipating how a Comparative Political Studies (CPS) manuscript will be evaluated — desk screening, anonymous peer review, decision categories, and how reviewers judge comparative work. Calibrates expectations; it does not write the submission or the rebuttal.
Use when deciding whether a research question fits Comparative Political Studies (CPS) and how to frame its comparative contribution. Tests comparative leverage and travel; it does not design the study or write the paper.
Use when reasoning about how CVPR review actually works at 16,000-submission scale, covering the OpenReview pipeline and timeline, reviewer-duty enforcement and desk rejects, the reviewer LLM ban, AC and discussion dynamics, oral/highlight/poster decision tiers, and calibrating expectations to a ~25% acceptance rate.
Use when designing or auditing the empirical evidence for an EACL paper, covering tuned and LLM baselines, multilingual breadth matched to the claim, significance and variance floors, human-evaluation agreement, data-contamination controls, ablations, and error taxonomies, so that every stated result is measured rather than asserted.
Use when designing or auditing the evidence in an ECAI paper — choosing proof versus experiment by claim shape across ECAI's breadth (theory/KR, planning/search, ML, multi-agent, applied), fair baselines, seeds and spread, honest ablations, and provenance, all supporting a claim inside a 7-page body.
Use when modeling how ECCV review actually works — the OpenReview pipeline from March registration to June decisions, the 2026 reviewer-duty enforcement that desk-rejects authors of late or LLM-written reviews, rebuttal-to-AC-discussion dynamics, and what the ECVA-run, Springer-published structure means for outcomes.
Use when positioning an Environmental Science & Technology (ES&T) manuscript against prior work across environmental chemistry, engineering, toxicology, and policy. ES&T is multidisciplinary, so the paper must engage the right literatures and state the knowledge gap it closes. It frames the gap and citations; it does not fabricate references.
Use when designing or auditing the evaluation of a EuroSys paper — choosing workloads that earn the word realistic, tuning baselines beyond their defaults, decomposing end-to-end wins into per-mechanism gains, measuring overheads and worst cases, and sizing experiments to the claims the paper actually makes.
Use when deciding whether a storage project belongs at USENIX FAST or should be routed to OSDI, ATC, NSDI, EuroSys, HotStorage, MSST, SYSTOR, or a storage journal (ACM TOS), and when distinguishing FAST from general-systems siblings by storage-contribution shape, real-device evidence, and the two-deadline calendar.
Use when strengthening ESEC/FSE reproducibility and open-science evidence, covering the Data Availability statement, anonymized-but-runnable artifacts, provenance pinning for mining and LLM studies, claim-to-evidence mapping, honest degrees of reproducibility, and consistency between what the paper says and what the artifact contains.