Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when deciding whether a question is a method-defined fit for an Experimental Economics (ExpEcon) manuscript and which treatment contrast to build it around. Frames the fit decision; it does not invent results or citations.
Use when designing or auditing ACM FAccT empirical work — quantitative fairness audits with disaggregated metrics and fair baselines, qualitative and participatory studies with coding and reflexivity, mixed-methods designs, sound handling of protected attributes and proxies, consent and IRB for human-subjects and community-facing work, and matching evidence to the shape of a fairness/accountability/transparency claim.
Use when reasoning about how an ACM FAccT submission is evaluated — mutually-anonymous review by a mixed CS+law+social-science pool matched via author-selected focus areas, Area Chairs, the short factual-correction rebuttal, the new Accept/Revise/Reject decision with a revise-and-resubmit round, and how FAccT's interdisciplinary process differs from a pure-ML conference's single-shot rebuttal.
Use when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an AI-ethics venue (AIES), by testing whether fairness, accountability, or transparency is a first-class contribution and whether the interdisciplinary framing is native rather than bolted on.
Use when strengthening USENIX FAST reproducibility and open-science evidence, covering device and firmware provenance, device-state disclosure, trace availability and replay, claim-to-evidence mapping, honest degrees of reproducibility on hardware that ages and varies, and consistency between what the paper says and what the artifact contains.
Use when reasoning about how a USENIX FAST submission is evaluated, covering double-blind program-committee review with outside referees, the author-response (rebuttal) period, the Accept / Accept-with-shepherding / One-shot-Revision / Reject decision set, how a one-shot revision differs from a journal R&R and from OSDI/ATC handling, and where author leverage exists.
Use when executing and reporting the statistical analysis for a Field Crops Research (FCR) manuscript — mixed models for multi-environment, block-design, and split-plot designs, genotype-by-environment (G×E) and stability analysis, estimated marginal means with SED/LSD, and crop-model evaluation. FCR requires data analysed with appropriate statistics that match the design and address the objectives. Guides analysis norms; it does not fabricate results.
Use to understand how Field Crops Research (FCR) evaluates a manuscript — initial editor screening against the journal's scope boundary, the single-anonymized review model with typically two or more reviewers, and the common reasons for desk rejection (controlled-environment-only, single-site single-season, descriptive/local, out-of-scope species). Sets expectations and shapes the paper to survive review; it does not contact editors.
Use when deciding whether an agronomy or crop-science project fits Field Crops Research (FCR) and which article type to target. FCR's defining test is field-based agronomic significance with multi-season/-environment relevance — it rejects controlled-environment-only, single-site single-season, horticultural/woody-perennial, and corroborative/descriptive/local-only work. Helps frame the question; it does not collect data.
Use when targeting 《金融监管研究》(Financial Regulation Research — 原中国银监会 2012 年创办、不收任何费用的金融监管专业学术月刊) or deciding whether a Chinese finance manuscript fits this regulation-focused venue. Encodes the journal's regulatory fit, framing, abstract/keyword/GB-citation house style, fee-free policy, online-system submission re-check, and desk-reject heuristics.