Claude Skills by brycewang-stanford

Use when strengthening TACAS (ETAPS) reproducibility, covering the clean evaluation-VM packaging that the artifact process assumes, pinned dependencies and offline execution, a claim-to-script mapping so every benchmark number regenerates, honest degrees of reproducibility, consistency between the paper and the artifact, and the category difference between a mandatory tool-paper artifact and a voluntary research-paper artifact.

Use when reasoning about how a TACAS (ETAPS) submission is evaluated, covering the per-category blind model (double-blind research vs single-blind tool/case-study), the single annual PC round with a rebuttal, the parallel mandatory artifact evaluation that feeds tool-paper acceptance, accept/reject decisions, and how TACAS's process differs from CAV's and from a journal's.

Use when auditing a TACAS (ETAPS) submission for EasyChair readiness, covering the choice among the four paper categories (research, case-study, regular tool, tool-demonstration), the correct LNCS page limit and llncs.cls format, the per-category blind mode (double-blind research vs single-blind tool/case-study), the mandatory tool-paper artifact deadline, and desk-reject triage before the firm ETAPS deadline.

Use when deciding what belongs in a TACAS (ETAPS) paper body versus its appendix, supplementary website, and artifact, covering the 16-page (or 6-page) llncs.cls budget that excludes references and appendix, the rule that decision-critical content stays in the reviewed pages, category-appropriate anonymity of supplementary material, and how to split a verification paper between body, appendix, and a mandatory-or-voluntary artifact.

Use when deciding whether a formal-methods / verification project belongs at TACAS (ETAPS) or a sibling like CAV, VMCAI, FMCAD, SPIN, or a journal, AND — distinctively — which of TACAS's four categories (research, case-study, regular tool, tool-demonstration) it fits, plus whether the work is a SV-COMP competition contribution rather than a paper.

Use when planning a TACAS (ETAPS) project timeline from category choice and venue fit through the EasyChair paper deadline, the mandatory tool-paper artifact deadline, the rebuttal window, notification, the voluntary post-acceptance artifact round, LNCS camera-ready, and presentation, with backward-planning offsets that account for TACAS's single annual round and its parallel paper+artifact review.

Use when revising a TACAS (ETAPS) paper for a clear construction-or-analysis contribution on the first page, a stated soundness/completeness claim, honest benchmark evidence, category-appropriate structure (research vs tool vs case-study vs tool-demo), disciplined use of the 16-page (or 6-page) LNCS budget, and correct handling of double-blind wording for research papers.

Use when the empirical identification strategy is the bottleneck for a The Economic Journal (EJ) manuscript — quasi-experimental designs (DID, IV, RDD, event study) or structural estimation. Stress-tests the design and its economic interpretation before drafting tables; it does not write the model from scratch (see ecj-theory-model).

Use when writing or repairing the introduction and related-work framing for a The Economic Journal (EJ) manuscript — situating the contribution for a broad economics readership with author-date citations. Frames positioning and the intro arc; it does not run the empirics or build the model.

Use when a The Economic Journal (EJ) decision letter (R&R or reject-with-encouragement) has arrived and you need to draft the response-to-referees letter and revision plan. Structures the response and the diff; it does not redo the analysis (route back to ecj-identification / ecj-theory-model / ecj-robustness first).

Use when running a pre-submission pre-mortem on a The Economic Journal (EJ) manuscript to anticipate the broad-interest, identification, and mechanism objections a demanding general-interest referee will raise. Builds the threat list and pre-empts it; it does not write the R&R response (see ecj-rebuttal).

Use when assembling the data and code replication package for a The Economic Journal (EJ) manuscript to the RES / EJ Data Editor standard (DCAS-endorsed, Zenodo deposit, reproducibility check before final acceptance). Builds the package and README; it does not run the analysis itself.

Use when the main result of a The Economic Journal (EJ) manuscript rests on a single specification and you need to pre-empt the alternative-explanation and fragility objections a demanding referee will raise. Builds the robustness battery and the falsification logic; it does not establish the primary identification (see ecj-identification).

Use when running the final pre-submission preflight for a The Economic Journal (EJ) manuscript via Editorial Express — single PDF format, author-date references, single-blind review, JEL codes and keywords, full-length vs. short-paper choice, submission-fee awareness, funding disclosure, and the RES/EJ data-and-code policy. Final mechanical gate; it does not improve the economic argument.

Use when finalizing the main exhibits (tables and figures) of a The Economic Journal (EJ) manuscript so each one carries economic content, reads to a general audience, and is self-contained. Sets exhibit design and notes standards; it does not decide which results to report (see ecj-robustness).

Use when a The Economic Journal (EJ) manuscript needs an explicit economic model or mechanism — either a theory paper's model, or the framework that gives a reduced-form empirical result its economic meaning. Builds and disciplines the economic argument; it does not run estimation (see ecj-identification).

Use when scoping or framing a research question for a The Economic Journal (EJ) manuscript and you need to test whether it is "EJ-shaped" — a substantial contribution of broad interest to economists at large, full-length or short-paper. Diagnoses fit and frames the contribution; it does not design the empirics.

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

Use when polishing the prose of a The Economic Journal (EJ) manuscript into its clear, generalist-legible, economics-first register. Tightens voice, structure, and citation/format house style; it does not fix the economic argument itself (see ecj-theory-model / ecj-identification).

Use when packaging datasets, models, or code for the Web Conference (WWW) Artifacts Available badge or for reviewer scrutiny, covering archival-repository choice, the light-verification bar, web-data licensing and takedown realities, anonymized artifacts during review, and what the badge does and does not certify.

Use when drafting the Web Conference (WWW) rebuttal inside its one-week window, triaging reviews from the venue's mixed systems/mining/social-science reviewer pool, answering misread-track objections, protecting anonymity, and deciding what can honestly be promised for the camera-ready versus what needs new evidence.

Use when preparing a Web Conference (WWW) camera-ready after acceptance, covering the uniform 12-page/8-content proceedings budget, de-anonymization and restored acknowledgements, ACM e-rights and TAPS production, ACM Open cost exposure, author registration, and the artifact-badging submission that rides along with the final files.

Use when designing or auditing the empirical section of a Web Conference (WWW) paper — matching evidence to the claim's scale, choosing datasets with provenance and freshness, blocking temporal and popularity leakage, running honest baselines from the sibling circuit, and deciding when live-platform or user-study evidence is required.

Use when positioning a Web Conference (WWW) submission against prior literature — tracing lineage through three decades of WWW proceedings, contrasting with the WSDM/CIKM/SIGIR/KDD sibling circuit, handling the venue's preprint-non-citation rule, and budgeting references against the shared 12-page PDF tail.

Use when hardening the reproducibility of a Web Conference (WWW) paper whose evidence rests on crawls, platform APIs, live systems, or user logs — covering dataset decay, temporal snapshots, seed and environment reporting, the reproducibility appendix inside the 12-page PDF, and honest claims when the Web itself cannot be replayed.

Use when reasoning about how the Web Conference (WWW) evaluates papers — track-scoped double-blind review, the rebuttal-to-notification pipeline, how the ten research tracks shape reviewer expectations, main versus companion proceedings outcomes, and what authors can and cannot influence at each stage.

Use when auditing a Web Conference (WWW) research-tracks submission before the abstract or full-paper deadline, covering track choice among the ten research tracks, the single-PDF 8+references+appendix page arithmetic within 12 pages, EasyChair profile completeness, the author-list freeze, the 7-submission cap, and double-blind checks.

Use when deciding what belongs in the Web Conference (WWW) appendix versus the 8 main pages versus an external artifact, under the single-PDF 12-page ceiling where references and appendix share the tail, reviewers need not read past page 8, and no separate supplementary upload exists in the research tracks.

Use when deciding whether a project belongs at the Web Conference (WWW) at all, which of the ten research tracks should review it, whether the short-paper or Web4Good lane fits better, and when the work should instead route to WSDM, SIGIR, CIKM, KDD, ICWSM, WebSci, or an ML flagship.

Use when planning a team's calendar around the Web Conference (WWW) annual cycle — the autumn abstract/paper deadlines, the holiday-week rebuttal, January decisions, the short-paper and Web4Good fallback windows inside the same edition, venue-volatility contingencies, and rerouting after rejection.

Use when drafting or revising a Web Conference (WWW) paper's prose — building the web-native framing that answers "why is this a WWW paper" on page one, writing for a mixed computing/social-science/economics readership, compressing into 8 self-contained pages, and handling scale numbers and platform names with precision.

Use when packaging code, data, samplers, solvers, and logs for a UAI submission's 50 MB supplementary ZIP or a public post-acceptance release, making probabilistic-inference claims independently runnable while keeping every file double-blind, given that UAI reviewers may open the archive but are not obliged to read it.

Use when drafting UAI author responses during the OpenReview rebuttal window, turning reviewer objections about technical correctness, novelty, evidential backing, or clarity into anonymous, evidence-anchored replies that survive the reviewer-and-area-chair discussion phase that follows immediately after authors go quiet.

Use when converting an accepted UAI paper into its PMLR proceedings version, covering de-anonymization, final formatting against the UAI template, metadata for the PMLR volume, restoring public code and data links, poster and spotlight preparation for the conference, and sequencing work back from the camera-ready deadline.

Use when designing or auditing UAI experiments where inference quality is the endpoint, covering calibration and coverage measurement, posterior diagnostics, structure-recovery metrics for causal and graphical models, seeded repeated runs, baselines from both sampling and optimization families, and mapping each claim to its evidence.

Use when positioning a UAI submission within the probabilistic reasoning, graphical-model, causality, and Bayesian ML literature, covering PMLR archival status of recent UAI volumes, double-blind self-citation discipline, concurrent arXiv and workshop versions, and the cross-community citation coverage UAI reviewers check first.

Use when hardening reproducibility evidence for a UAI paper, including seeds, sampler convergence diagnostics, ELBO and calibration traces, dataset and hyperparameter disclosure, compute reporting, and honest code-availability statements, since UAI strongly encourages released code and data and reviews whether claims are convincingly backed.

Use when reasoning about UAI peer review on OpenReview, including bidding, double-blind evaluation against the correctness, novelty, backing, and clarity criteria, the author-response window, the reviewer-and-area-chair discussion that follows it, decision timing, spotlight versus poster outcomes, and PMLR publication of accepted papers.

Use when auditing a UAI submission for OpenReview readiness, covering the February paper deadline, the 8-page main part with unlimited appendices in one PDF, the 15 MB file cap, the optional 50 MB supplementary ZIP, double-blind rules, the reviewer-volunteer agreement, dual-submission checks, and desk-reject triage before upload.

Use when splitting a UAI paper between the 8-page main part, the unlimited in-PDF appendix for proofs and protocols, and the optional 50 MB supplementary ZIP, deciding what reviewers must see in the body versus what may sit in material they are not required to read, all under double-blind and single-file constraints.

Use when deciding whether a project belongs at UAI, where uncertainty representation, probabilistic reasoning, graphical models, causal inference, or decision making under uncertainty must be the contribution itself, and when to route instead to AISTATS, NeurIPS, ICML, COLT, CLeaR, or a statistics journal before drafting begins.

Use when planning a UAI cycle end to end, from venue-fit confirmation through the winter submission deadline, the spring review and author-response phases, the June decision, the July PMLR camera-ready, and the August conference, as one backward-planned calendar with named owners for anonymity, evidence, and packaging tasks.

Use when revising a UAI manuscript for probabilistic-inference readers, enforcing precise notation for distributions, graphs, and interventions, explicit assumption and identifiability statements, an 8-page main part that carries the whole argument while proofs sit in the appendix, and claims calibrated to what the theory and experiments show.

Use when packaging the artifacts behind a UIST paper — code, toolkits, hardware design files, and datasets — first as anonymous review-time evidence that the system is real, then as a public release engineered for reuse, in a venue with no formal badge committee doing the checking for you.

Use when writing the UIST rebuttal — budgeting the 5,000-character self-contained response, prioritizing factual corrections and novelty defenses over taste disputes, promising only camera-ready changes you can deliver, and writing for the PC discussion that follows rather than for the reviewers alone.

Use when converting a conditional UIST acceptance into a published paper — delivering the rebuttal-promised changes by the July deadline, working the ACM TAPS pipeline with alt text for every figure and table, de-anonymizing correctly, finalizing the video figure, and preparing the Detroit talk and demo.

Use when designing or auditing the evaluation of a UIST paper — choosing among technical benchmarks, controlled comparisons, usability walkthroughs, expert sessions, and demonstration applications, matching evaluation shape to the systems claim, and avoiding the ritual study that proves nothing the paper asserts.

Use when positioning a UIST submission against prior art — organizing by capability delta rather than paper lists, covering the technique lineage, toolkit ancestry, and commercial systems reviewers know, citing your own work in the third person, and verifying venue attribution through the ACM DL and dblp.

Use when making a UIST paper's results replicable — reporting implementation parameters and measurement protocols so a lab could rebuild the system, specifying hardware down to parts and calibration, logging technical evaluations deterministically, and writing honest availability statements for interface systems.

Use when interpreting the UIST review pipeline — anonymous PC-plus-external review of papers and videos, the rebuttal's role, PC-meeting decisions, conditional acceptance mechanics, reading systems-reviewer psychology, and choosing the demo/poster fallback or resubmission path after a rejection.