Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when targeting SIAM Review (SIAM Rev.) or deciding whether an applied- or computational-mathematics manuscript fits this expository, broad-readership SIAM venue. Encodes the journal's fit, framing, expository-and-rigor bar, house style, official-submission re-check, and desk-reject heuristics.
Use when targeting SIGDIAL Conference on Discourse and Dialogue (SIGDIAL) or deciding whether a computer-science manuscript fits this venue. Encodes conference fit, framing, evidence bar, submission-cycle checks, rebuttal posture, and desk-reject risks for dialogue systems.
Use when designing or auditing the evaluation of a SIGGRAPH / TOG paper, covering head-to-head comparisons against the strongest prior method, ablations, performance/timing reporting with hardware, image/geometry quality metrics, perceptual and user studies, and matching the evidence to the graphics claim shape.
Use when writing or auditing the related-work positioning of a SIGGRAPH / TOG paper, covering the computer-graphics literature lanes (rendering, geometry, animation, simulation, imaging, fabrication, learning-for-graphics), capability-delta positioning against the strongest prior method, and correct attribution across SIGGRAPH, SIGGRAPH Asia, TOG, EG/CGF, and sibling venues.
Use to model the SIGGRAPH / SIGGRAPH Asia Technical Papers review pipeline and calibrate expectations, covering the single 6-point score scale, the primary/secondary/tertiary reviewer structure, the 1000-word rebuttal, the Technical Papers Committee meeting, conditional acceptance with second-stage verification, and the dual-track Journal-vs-Conference decision.
Use when designing or auditing the empirical program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff discipline, paired significance testing with multiple-comparison correction, baseline tuning symmetry, ablations that isolate mechanisms, efficiency reporting, and LLM-era evaluation pitfalls.
Use when positioning a paper against the information-retrieval literature for SIGIR — tracing lineage through SIGIR/TOIS/TREC canon, contrasting mechanisms with the nearest recent SIGIR papers, avoiding venue misattribution (DPR is EMNLP, ANCE is ICLR, NCF is WWW), and handling arXiv-era concurrent work in a fast-moving field.
Use when strengthening the reproducibility of a SIGIR paper or preparing a SIGIR Reproducibility track submission — pinning the retrieval pipeline, seeds and variance for neural rankers, documenting collection versions and index settings, and structuring a reproduction study of published IR results with honest divergence analysis.
Use when reasoning about how SIGIR evaluates submissions — the per-track OpenReview machinery, double-blind full/short review versus single-anonymous Resources review, the PC-member nomination duty, what IR reviewers score (evaluation validity above novelty claims), the ACM Peer Review Policy layer, and how decisions land.
Use when deciding whether a project belongs at SIGIR and in which of its tracks — testing whether retrieval is the contribution or the plumbing, forking across full/short/resources/reproducibility/perspectives/industry, and routing misfits to ECIR, CIKM, WSDM, CHIIR, ICTIR, RecSys, TheWebConf, or NLP/ML venues.