Claude Skills by brycewang-stanford

Use when assembling the data and code replication package for a Journal of the European Economic Association (JEEA) manuscript so it clears the JEEA Data Editor's pre-acceptance verification under the DCAS standard. Builds the package and README; it does not run the analysis.

Use when the headline result of a Journal of the European Economic Association (JEEA) manuscript needs to be shown stable to specification, sample, inference, and (for theory) assumption perturbations. Organizes robustness around the actual threats a general-interest referee will raise; it does not design the main result.

Use when running the final pre-submission preflight for the Journal of the European Economic Association (JEEA) via the EEA submission system — EEA membership gate, submission fee, single-blind format, online appendix, the no-asterisks house style, and the data-policy declarations. Final checks; it does not draft content.

Use when building or revising tables and figures for a Journal of the European Economic Association (JEEA) manuscript so exhibits read clean for a general-interest audience and respect JEEA house norms. Shapes exhibits; it does not change the underlying estimates.

Use when a Journal of the European Economic Association (JEEA) manuscript contains a theoretical or structural model whose assumptions, generality, or results need sharpening to the journal's general-interest bar. Disciplines the model and makes its results legible; it does not run empirics or polish prose.

Use when deciding whether a question fits the Journal of the European Economic Association (JEEA) rather than a field journal or a sibling general-interest outlet for a JEEA manuscript. Tests general-interest fit and sharpens the question; it does not design the empirics or model.

Use when deciding which jeea-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for a Journal of the European Economic Association (JEEA) submission. Routes — it does not replace — the specialized skills.

Use when revising the prose, abstract, and introduction of a Journal of the European Economic Association (JEEA) manuscript so the idea lands for a general-interest readership. Shapes how the argument reads; it does not change the result, identification, or exhibits.

在处理《通信学报》(Journal on Communications, JOC) 稿件的代码与数据可用性问题时调用。讲清本刊作为中文通信期刊目前没有独立于正文评审的"制品/工件徽章"(artifact badge) 制度这一现状，指导在没有正式制品评审的前提下，如何通过开放代码/数据/复现包、规范数据可用性声明、匿名评审仓库、仿真参数与信道实现公开等方式，主动提升通信实验的可信度与可复现性，帮助作者把可用性材料组织到既符合本刊三审制评审关注点、又不误称本刊有官方徽章制度的程度，适用于物理层、网络、安全与信号处理方向的中文长文。

当为《通信学报》(Journal on Communications, JOC) 收到的外审与编委会意见撰写逐条答复与修回说明时调用；用于把 Journal on Communications 三审制下的审稿意见转化为可核验的修回材料。指导把大修/小修意见拆成可追踪条目、逐条给出"意见—回应—修改位置"的闭环答复，撰写礼貌而有据的修回说明信、在稿件中做差异标注（修改处标色/标注页行号），处理相互矛盾或超范围的意见、对不认同意见的有据申辩，兼顾本刊三审制多轮修回与月刊排期，帮助把一份通信/网络/信息安全/信号处理方向中文长文的修回材料做到审稿人一眼可核、编委会易于通过的程度。

当《通信学报》(Journal on Communications, JOC) 稿件通过三审制录用后、进入定稿与出版阶段时调用；用于把 Journal on Communications 录用稿稳妥推进到正式见刊。指导完成录用后的清样/校样核对、按官方模板终排、缴纳版面费（约 600 元/面，以通知为准）、签署版权/授权、核对作者信息与基金项目、确认中英文摘要与图表在终排中的正确性、处理 DOI 与见刊排期等收尾工作，兼顾本刊月刊出版节奏（每月 25 日出版）与档期排队，帮助把一份通信/网络/信息安全/信号处理方向的中文长文从"录用"稳妥推进到"正式见刊"，避免在定稿环节因校对疏漏或缴费延迟影响出版。

在为《通信学报》(Journal on Communications, JOC) 稿件设计与呈现实验、仿真或实测证据时调用。覆盖通信学科特有的链路级/系统级仿真、标准信道模型（AWGN/Rayleigh/多径/多普勒）、SNR-BER 与容量/吞吐/时延曲线、蒙特卡洛置信区间、公平基线选取与消融实验、网络协议仿真（NS-3/OMNeT++）与信息安全实验（威胁模型下的安全性证明与开销量化），指导用研究问题 RQ 驱动实验、保证统计严谨与可复现，帮助把证据做到能经受本刊外审对实验充分性、公平性与统计显著性的质疑，适用于物理层、网络、安全、信号处理各方向的通信中文长文。

在为《通信学报》(Journal on Communications, JOC) 稿件撰写相关工作与文献综述、确立创新性时调用。指导以 delta（相对最强基线的增量）为主线组织通信领域文献，覆盖信道编码/无线传输/网络协议/信息安全/信号处理等子方向的分类归纳，区分本刊与《电子学报》《计算机学报》等兄弟刊读者的关注点，规范 GB/T 7714 引用与中英文文献并重，避免罗列式综述与漏引近三年关键工作，帮助把相关工作写成能支撑本文创新性论证、经得起本刊外审对新颖性质疑的一节，适用于研究长文与规范综述两种体例。

当为《通信学报》(Journal on Communications, JOC) 稿件建立可复现性与实验可重复保障时调用；用于让 Journal on Communications 外审能按说明在声明环境下复现通信仿真主结果。指导固定通信仿真的信道实现、随机种子、蒙特卡洛次数、参数表与数据集划分，规范复现包（环境依赖、config、脚本、校验和）的组织，防范数据泄漏与"精挑参数"，处理受限数据/私有信道测量的可获取性说明，并把复现信息恰当写入正文实验设置与数据可用性声明，帮助把一篇通信/网络/信息安全/信号处理方向的中文长文做到外审能按说明在声明环境下复现主结果，提升本刊三审制下对实证可信度的评价。

在需要理解《通信学报》(Journal on Communications, JOC) 的审稿流程、预测各环节结果与识别作者可用杠杆时调用。对本刊初审（编辑审查规范/对口性/知网查重）→ 外审（约 2~3 名专家评审通信学科贡献）→ 终审（由编委会负责给出最终结果）三审制建模，说明约 1~3 个月的审稿周期、修回（大修/小修）与退稿的常见判定，指导作者在每个环节采取的应对策略（对口性论证、实证补强、修回闭环、按月刊排期跟进），帮助把稿件顺利推进本刊三审制，适用于通信/网络/信息安全/信号处理方向的中文长文投稿。

在向《通信学报》(Journal on Communications, JOC) 正式提交稿件前做投稿就绪审计时调用。覆盖官网 infocomm-journal.com/txxb 与 CBPT 在线投稿系统 cbpt.infocomm-journal.com、行文次序（中文题名≤20字/中英文结构式摘要/关键词≥4/中图分类号 TN/文献标识码/文章编号）、约 12000 字符篇幅、GB/T 7714 参考文献、知网查重重复率 20% 红线、不收稿件处理费但审稿费 300 元/篇与版面费 600 元/面、栏目归属与一稿多投禁令，并在提交前做退稿风险分诊。适用于把一份通信/网络/信息安全/信号处理方向的中文原创长文打磨到符合本刊三审制门槛的场景。

当为《通信学报》(Journal on Communications, JOC) 稿件划分正文与附录/补充材料/多媒体附件时调用；用于在 Journal on Communications 约 12000 字符篇幅约束下控制正文信息密度。指导用"决定性"标准判断哪些内容（关键推导、主实验、核心算法）必须进正文，哪些（冗长证明、超参搜索、额外场景、大表、演示视频、数据集说明）宜放附录或补充材料，兼顾本刊约 12000 字符的篇幅约束与外审复核创新性/正确性的需要，规范补充材料的编号、引用与可获取性说明，帮助把一篇通信/网络/信息安全/信号处理方向的中文长文的篇幅与信息密度控制到既完整又不臃肿、经得起本刊格式与篇幅审查的程度。

当为《通信学报》(Journal on Communications, JOC) 立项或判断一份稿件是否对口本刊时调用；用于把选题定位到 Journal on Communications 的通信学科版图并与兄弟刊区分。帮助判断选题是否落在本刊通信学科版图（通信理论与技术、无线/移动通信、网络与交换、信息安全与密码、信号处理），把它与《电子学报》《计算机学报》《软件学报》《自动化学报》《中国科学:信息科学》等兄弟刊的分工区分开，并据贡献强度选定学术论文/技术报告/综述/短文的稿件类型，评估创新性、工程价值与实证充分度是否够本刊三审制门槛，避免投错刊或写成偏离本刊口味的稿件。

当需要为一次《通信学报》(Journal on Communications, JOC) 投稿规划从选题到见刊的完整时间线、并把 12 个技能按顺序编排调度时调用。给出选题定位、写作、实证准备、投稿审计、初审→外审→终审三审制应对、修回、录用定稿各阶段的里程碑、预计周期与检查点，帮助作者把握约 1~3 个月的审稿节奏与月刊出版排期，识别每个环节的作者杠杆与常见卡点，并指明在每一步应调用本包中的哪一个具体技能，适用于统筹一篇通信/网络/信息安全/信号处理方向中文长文的整体投稿工程。

当撰写或润色《通信学报》(Journal on Communications, JOC) 中文科技长文的体例与规范时调用；用于让稿件符合 Journal on Communications 的排版与编辑规范、经得起初审格式审查。覆盖官方行文次序、中文题名≤20字、中英文结构式摘要（目的/方法/结果/结论，中文≤200字）、中英文关键词≥4、中图分类号 TN、文献标识码与文章编号、量与单位法定用法、数学符号与公式排版、图表规范、参考文献 GB/T 7714 著录（含中文文献著录与中英文对照），以及作者简介与基金项目标注，帮助把一篇通信/网络/信息安全/信号处理方向的稿件写到符合本刊排版与编辑规范、经得起初审格式审查的程度。

Use when packaging code, datasets, configs, and deployment evidence for a KDD paper, where the repository cited in the submission is the only artifact reviewers can reach because rebuttals ban links. Covers anonymized repo construction, scale-claim harnesses, ADS evidence without production data, and post-acceptance release.

Use when drafting KDD rebuttals on OpenReview, where authors answer each review under a no-hyperlink rule, cannot upload revisions, and write for the area chair who recommends Accept, Reject, or Resubmit. Covers evidence-anchoring without links, per-reviewer triage, and turning a likely Resubmit into next-cycle material at ACM SIGKDD.

Use when preparing an accepted KDD paper for ACM proceedings, covering the 12-page proceedings budget with 9 content pages, the extra content page over the submission, the 3-page cap on references plus appendix, ACM e-rights and TAPS source processing, ACM Open APC status, de-anonymization, and Digital Library metadata for SIGKDD.

Use when designing or auditing the empirical section of a KDD paper, where evidence combines quality deltas with scalability and efficiency measurements, temporal-leakage-safe splits, mechanism-isolating ablations, tuning-symmetric baselines, and, for the ADS track, post-launch measurement design that survives the desk check.

Use when positioning a KDD submission against the data-mining lineage (prior KDD volumes, ICDM, SDM, WSDM, CIKM, WWW) and the ML flagships, handling venue misattribution traps, cross-cycle resubmission overlap, concurrent arXiv work, and the mechanism-contrast style of novelty argument that ACM SIGKDD reviewers expect.

Use when hardening the reproducibility story of a KDD paper, where reproducibility is an explicit decision factor for area chairs. Covers claim-to-evidence tiers for mining pipelines, seeds and splits on large graphs and streams, baseline-tuning disclosure, compute reporting, and honest limits for ADS deployment results.

Use when reasoning about how KDD papers get judged in its dual-cycle OpenReview process: per-review rebuttal, area-chair recommendations weighed on merit through reproducibility and ethics, PC-chair decisions, the Resubmit outcome feeding the next cycle, the mixed academic-industry reviewer pool, and generative-AI review rules.

Use when auditing a KDD submission for readiness in either cycle, covering Research vs ADS track declaration, OpenReview profile completeness for all authors, the ACM sigconf 8-content-page budget, double-blind checks, in-paper artifact references, resubmission declarations, and desk-reject triggers specific to ACM SIGKDD.

Use when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the camera-ready rule capping references plus appendix at 3 of 12 pages. Covers appendix triage, reviewer-discretion reality, and the one-page cross-cycle resubmission change summary.

Use when deciding whether a project belongs at KDD and in which track — Research vs Applied Data Science vs Datasets and Benchmarks vs AI for Sciences — or whether it routes to ICDM, SDM, WSDM, CIKM, WWW, VLDB, or an ML flagship. Covers the deployment-evidence fork, data-regime framing, and SIGKDD fit signals before writing.

Use when planning a KDD project calendar across the venue's two submission cycles per year, including cycle choice, abstract-then-paper deadline pairs a week apart, rebuttal capacity planning, the Resubmit-to-next-cycle loop, ADS evidence lead times, and ACM e-rights/TAPS camera-ready scheduling for SIGKDD.

Use when revising a KDD paper into the venue's register, where the first page names a data regime, a mechanism, and scale evidence, efficiency adjectives trace to design decisions, and two-column sigconf pages punish sprawl. Covers Research vs ADS voice, dataset-size discipline, assertive contribution bullets, and 8-page compression.

Use when planning or auditing the analysis of a Language (LSA) manuscript so the evidence credibly supports the theoretical claim. Covers quantitative modeling (mixed-effects in R), phonetic measurement, corpus statistics, and the analytic trail from glossed data or judgments to the generalization. Improves the analysis chain; it does not fabricate results.

Use when preparing the data, annotation, and reproducibility materials for a Language (LSA) manuscript — shared datasets and code, glossed corpora, sound files, and the ethics of working with language consultants and communities. Language values transparent, documented data; over-stating a mandated deposit is as wrong as hiding materials. Documents and shares; it does not run the analysis.

Use when positioning a Language (LSA) manuscript within the literature so it reads as in dialogue with current linguistics across frameworks. Language reviewers are drawn from across subfields; the positioning must engage the strongest rival accounts fairly, not build a subfield-only wall. Maps the conversation; it does not write the literature review.

Use when responding to a Language (LSA) decision — a revise-and-resubmit response letter, or an author Rejoinder in the Perspectives target-article-and-commentaries format. Turns reviewer objections into a point-by-point revision plan that engages rival frameworks and firms up evidence. Structures the response; it does not fabricate new results.

Use when defending the empirical design of a Language (LSA) manuscript on the terms of its subfield — elicitation and fieldwork, corpus construction, phonetic measurement, experiment, or the diachronic/typological sample. Language judges each kind of evidence by its own standards, and the design must support the theoretical claim. Defends the design; it does not run the analysis.

Use when anticipating how a Language (LSA) manuscript will be judged — the double-anonymous review, the general-audience and cross-framework bar, the desk-return filters (descriptive data dump, single-framework parochialism, undocumented data), and the decision categories. Sets expectations and stress-tests before submission; it does not write the paper.

Use when running the final pre-submission preflight for Language (LSA) via the Cambridge University Press ScholarOne portal — double-anonymous anonymization, the section and word-limit rules (General Research Article ≤18,000 words; Review Article ≤5,000), the abstract, Leipzig glossing, IPA, the Language Style Sheet, figure alt text, and open-access status. Final checks; it does not draft content.

Use when preparing the exhibits of a Language (LSA) manuscript — numbered examples, Leipzig-convention interlinear glosses, IPA transcription, tableaux/trees, and quantitative tables and figures. Language has specific conventions for linguistic examples that reviewers and typesetters enforce. Prepares exhibits; it does not generate data.

Use when turning a linguistic pattern into a theoretically grounded claim for a Language (LSA) manuscript — an analysis with explicit assumptions, observable predictions, and engagement across competing frameworks rather than inside one formalism. Structures the argument; it does not gloss data or run the statistics.

Use when deciding whether a linguistics project fits Language (Linguistic Society of America) and how to frame it. Language is a generalist flagship spanning every subfield; the test is a theoretically grounded contribution legible to the whole discipline, not a description of one language or a result inside one framework. Helps frame the question; it does not collect or gloss data.

Use when starting or navigating any manuscript aimed at Language (Linguistic Society of America) and unsure which skill applies — it reads your stage and piece type (General Research Article, Research Report, Review Article, Discussion Note, or an online-only section: Perspectives, Phonological Analysis, Language and Public Policy, Teaching Linguistics) and routes you to the matching sub-skill. It dispatches; it does not draft analysis.

Use when polishing the prose and house style of a Language (LSA) manuscript so it reads for a general linguistics audience and conforms to the Language Style Sheet / Unified Style Sheet for Linguistics. Language prizes analysis legible across frameworks and subfields; jargon and single-formalism prose lose readers. Polishes and conforms; it does not build the argument.

Use when preparing a MICRO artifact for post-acceptance evaluation — packaging simulators, configs, traces, and scripts so evaluators can regenerate the paper's figures, targeting the ACM Available/Functional/Reproducible badges, handling licensed workloads and long simulations, and earning the optional artifact appendix.

Use when reviews arrive for a MICRO submission and the rebuttal/revision window opens — triaging reviewer objections by what can change a decision, answering methodology attacks with runs and configs rather than promises, keeping anonymity intact, and staying inside MICRO's professional-conduct rules for rebuttals.

Use when a MICRO paper is accepted and the camera-ready is due — the nine-week July-to-September window in the 2026 cycle, de-anonymization and acknowledgments restoration, keeping the all-author reference rule, integrating rebuttal promises, the optional post-AE artifact appendix, and IEEE/ACM publication logistics.

Use when designing or auditing the evaluation of a MICRO paper — choosing the right instrument on the ladder from analytical model to cycle-level simulator to RTL to silicon, tuning baselines the PC will respect, selecting workload suites, running ablations and sensitivity sweeps, and reporting geomeans with full overhead accounting.

Use when building a MICRO paper's related-work coverage and positioning — sweeping the four-venue architecture literature plus journals and industry disclosures, differentiating by mechanism structure and cost rather than by numbers, obeying MICRO's all-author citation format, and verifying venue attribution via dblp before citing.

Use when hardening a MICRO paper's results for re-derivation — pinning simulator commits and configs, recording workload trace provenance and SimPoint recipes, versioning power/area models, capturing RTL toolchain state, and writing the run manifests that later survive MICRO's post-acceptance artifact evaluation.