Claude Skills by brycewang-stanford

Use to understand how Mind evaluates a submission — triple-anonymous peer review, quality as the sole criterion, the role of expert referees, and what it means for a journal that receives over 800 submissions a year. Sets expectations and shapes the paper to survive review; it does not contact editors.

Use when responding to a Mind decision — a revise-and-resubmit, a reject-with-encouragement, or referee reports to address before resubmitting. The response must answer expert philosophical objections without weakening the thesis, while keeping the manuscript prepared for triple-anonymous review. Structures the revision and the response letter; it does not fabricate new arguments.

Use when organizing a Mind article so the argument unfolds in the clearest possible order within the ~8,000-word limit. The job is architecture, not prose polish — a roadmap, the right order of premises, signposting, and a conclusion that claims exactly what was earned. Structures the paper; it does not write the sentences (see mind-writing-style).

Use when running the final pre-submission preflight for Mind via ScholarOne — preparation for triple-anonymous review, the ~8,000-word limit, the 50–200-word abstract, line numbering, the one-article-per-12-months rule, file format, and the MIND house style. Final checks; it does not draft content.

Use when building the central argument of a Mind article — stating a sharp thesis and constructing a valid, sound argument for it. This is the core of an analytic-philosophy paper: explicit premises, a valid inference to the conclusion, and defensible premises. Structures the argument; it does not generate the philosophical content for you.

Use when deciding whether a philosophy project fits Mind and which content type (article, discussion, book review, critical notice) to target. Mind takes quality as the sole criterion and excludes no area, style, or school, so the test is the significance and defensibility of the thesis, not novelty of topic alone. Helps frame the question; it does not do the philosophy for you.

Use as the entry point for any Mind (philosophy journal) article. Routes to the right Mind sub-skill based on where you are in the lifecycle and whether the piece is an article, discussion note, book review, or critical notice. Mind is analytic philosophy — argument, not data — so the router's first job is to confirm there is a sharp thesis and a sound argument. It dispatches; it does not draft content.

Use when drafting or polishing the prose of a Mind article so the argument is maximally clear to a broad philosophical readership within the ~8,000-word limit. Mind asks that even technical material be accompanied by informal exposition. Tightens sentences and clarity; it does not generate the argument (see mind-thesis-and-argument).

Use to write the NEJM structured abstract — four headed sections (Background, Methods, Results, Conclusions), ≤250 words, with the trial registration number and funding source, leading the Results with the primary outcome reported as an effect size with a 95% CI. Late-stage polish skill.

Use to convert references to NEJM's Vancouver / ICMJE numbered style — numbered in order of appearance, limited author lists then et al., NLM journal abbreviations, and a capped reference count. Late-stage style pass.

Use to confirm clinical ethics and research-integrity requirements for an NEJM submission — IRB/ethics-committee approval and informed consent per the Declaration of Helsinki, ICMJE conflict-of-interest disclosures and authorship criteria, the role-of-the-funding-source statement, and the ICMJE data-sharing statement.

Use to build NEJM clinical display items correctly — Table 1 baseline characteristics by group (with standardized differences, not P values), Kaplan-Meier curves with numbers-at-risk, forest plots for subgroups and meta-analyses, and the CONSORT participant flow diagram.

Use first, before any writing, to stress-test whether a clinical study clears NEJM's bar — practice-changing clinical impact, methodological rigor, and generalizability. Decides NEJM vs Lancet/JAMA vs a specialty journal.

Use after NEJM reviews arrive — often including a dedicated statistical reviewer and an editor letter — to triage the decision, answer statistical comments rigorously, and draft a point-by-point response that quotes each comment, the response, and the revised manuscript text. Do not run before the main text is actually revised.

Use to select and enforce the correct EQUATOR reporting guideline for a clinical study — CONSORT for RCTs (with the participant flow diagram), STROBE for observational, PRISMA for systematic reviews — and to build the required checklist and diagram before submission.

Use to enforce NEJM's clinical statistical reporting — confidence intervals over bare P values, the pre-specified intention-to-treat primary analysis, multiplicity control for secondary endpoints, pre-specified subgroups with interaction tests, missing-data handling, and absolute risk with NNT alongside relative measures.

Use to confirm study-design rigor and the mandatory prospective trial registration, protocol, and statistical analysis plan before writing up a clinical study for NEJM. Surfaces registration problems early — they cannot be fixed retroactively.

Use as the final preflight before submitting to NEJM — a complete clinical checklist across significance, registration, reporting guidelines, abstract, statistics, display items, ethics, references, and required files. Bundles a checklist and a clinical cover-letter template.

Use when deciding which nejm-* sub-skill to invoke next, or when sequencing a clinical manuscript from significance test through response to reviewers for The New England Journal of Medicine. Routes — it does not replace — the specialized skills.

Use to structure and tighten an NEJM Original Article into terse IMRAD — short main text (~2700 words), limited references, claim-first results, and a sober discussion with explicit limitations and calibrated clinical implications. Enforces NEJM's plain, concise house style.

Use to contextualize theory for 《南开管理评论》 (Nankai Business Review) — showing how the China context changes construct meanings, mechanisms, or boundary conditions, rather than using China merely as a sampling site. Use when the China context appears only in the sample description, or when the paper asserts "Chinese characteristics" without specifying how the context alters the theory.

Use to write the discussion section for 《南开管理评论》 (Nankai Business Review) so it loops back to the introduction's gap and advances a management theory — extension, boundary condition, or integration — rather than restating results. Use when the discussion only summarizes findings, or when the theoretical-contribution paragraph repeats the hypotheses without saying what changed in the theory.

Use for experimental studies submitted to 《南开管理评论》 (Nankai Business Review) — design (between/within, scenario/vignette, lab/field), manipulation checks, randomization and confound control, effect sizes and power, and mediation/moderation via experimental-causal-chain or measurement-of-mediation designs. Use when a hypothesis is tested by manipulating an independent variable rather than measuring it.

Use to judge whether a manuscript fits 《南开管理评论》 (Nankai Business Review) before investing in revision, and to re-route off-fit papers — math models to 管理科学学报, macro policy-evaluation to 管理世界 / 中国工业经济, capital-market governance to 会计研究 / 金融研究. Use when the topic, method, or framing might be a mismatch for a theory-building management journal.

Use to develop hypotheses for 《南开管理评论》 (Nankai Business Review) so each is backed by an explicit theoretical mechanism, not intuition. Use when hypotheses read as "we expect a positive relationship", when mediation/moderation logic is asserted without a mechanism, or when the hypothesis set is not derived from the theory invoked in the introduction.

Use for measurement rigor in 《南开管理评论》 (Nankai Business Review) survey studies — reliability (Cronbach's α, composite reliability), validity (convergent via AVE, discriminant via Fornell-Larcker / HTMT), and common-method-bias diagnosis (Harman single-factor, marker variable, common latent factor). Use whenever a paper uses self-report scales, especially if measures were borrowed or single-source.

Use for qualitative theory-building submitted to 《南开管理评论》 (Nankai Business Review) — multi-case comparison (replication logic, case selection), grounded-theory coding (open / axial / selective), theoretical saturation, and trustworthiness (data triangulation, member checking, audit trail). Use when the contribution is built inductively from cases or interviews rather than from survey/experiment data.

Use to draft the revise-and-resubmit (R&R) response letter for 《南开管理评论》 (Nankai Business Review) — addressing reviewer concerns on theoretical contribution, mechanism logic, measurement (reliability/validity/CMV), analysis (mediation/moderation/HLM or experiment/qualitative rigor), and contextualization. Use only after the manuscript itself has been revised, not before.

Use for the pre-submission preflight to 《南开管理评论》 (Nankai Business Review) — checking abstract/keyword limits, manuscript length, bilingual title/abstract, reference style (GB/T 7714 plus the journal's 来稿规范说明), the online submission system at nbr.nankai.edu.cn, anonymity, and document hygiene. Use right before submitting; verify every rule against the journal's current 来稿规范说明.

Use for survey-based structural equation modeling in 《南开管理评论》 (Nankai Business Review) — CFA/SEM fit indices, mediation and moderation, moderated mediation with bootstrap indirect effects and the index of moderated mediation, and multilevel models (HLM) for nested data. Use when testing construct-relationship hypotheses (mediation / moderation / moderated mediation) on questionnaire data.

Use to articulate the theoretical gap and contribution for 《南开管理评论》 (Nankai Business Review) — turning a set of construct relationships into a statement of what existing management theory cannot explain and what this paper adds (concept / proposition / framework / boundary condition). Use when the contribution still reads as "we test whether X affects Y".

Use when deciding which nbr-* sub-skill to invoke next, or when sequencing manuscript work from fit judgment through rebuttal for 《南开管理评论》 (Nankai Business Review). Routes — does not replace — the specialized skills, and re-routes math-model or macro-policy papers to sibling journal stacks.

Use when packaging NeurIPS code, data, models, demos, benchmarks, or other research artifacts for anonymous review, reproducibility, public release, or MLRC-style artifact scrutiny.

Use when drafting or triaging NeurIPS OpenReview author responses, rebuttals, and discussion-period replies under the current year's response mechanics and double-blind constraints.

Use when preparing accepted NeurIPS papers for camera-ready upload, de-anonymization, final checklist, code/data release, OpenReview metadata, and post-acceptance obligations.

Use when stress-testing NeurIPS experimental evidence, including baselines, ablations, data splits, compute, negative results, real-world use, and claim-to-evidence calibration.

Use when positioning a NeurIPS submission against current-cycle ML literature, contemporaneous work, preprints, neighboring conferences, and the exact technical delta from prior methods.

Use when strengthening NeurIPS reproducibility evidence, checklist answers, code/data instructions, random-seed controls, compute disclosure, or deciding whether MLRC/TMLR is a better route.

Use when explaining or diagnosing the NeurIPS main-track review process, including OpenReview, reviewer and AC roles, contribution-type review, ethics flags, reciprocal reviewing, discussion, and LLM-review policy.

Use when auditing a NeurIPS main-track submission for current-cycle CFP, OpenReview, formatting, anonymity, track, contribution-type, checklist, code/data, dual-submission, and LLM/agent policy compliance.

Use when deciding what NeurIPS material belongs in the main PDF, references, text appendices, mandatory checklist, separate code/data ZIP, or external public artifact.

Use when deciding whether a paper belongs at NeurIPS, choosing main-track versus another NeurIPS track, selecting contribution type, or rerouting to a better AI/ML venue.

Use when planning a NeurIPS manuscript workflow from topic selection through submission, review, author response, decision, camera-ready, artifact release, and possible rerouting.

Use when rewriting a machine-learning paper for NeurIPS-style contribution framing, concise claims, contribution-type alignment, limitations, societal impact, and checklist-compatible prose.

Use when articulating the contribution of an Operations Research (OR) manuscript — especially the mandatory cover-letter contribution statement (since 1 June 2023, fewer than 500 words) and the discussion's significance claims. Frames why the work matters to OR; it does not position against specific prior papers (ors-literature-positioning) or run experiments (ors-data-analysis).

Use when running and reporting the computational study for an Operations Research (OR) manuscript — benchmark instances, baselines, reproducible experiments, statistical care for stochastic output, and the ORJournal code-and-data reproducibility workflow. Executes and reports the numerical evidence; it does not prove the results (ors-methods) or lay out the exhibits (ors-tables-figures).

Use when placing an Operations Research (OR) manuscript against the OR/MS literature — separating your model, results, and algorithmic guarantees from the closest prior work so the novelty is unambiguous. Positions the contribution; it does not formulate the model (ors-theory-development) or write the contribution statement (ors-contribution-framing).

Use when designing the proof technique, algorithm, or simulation protocol for an Operations Research (OR) manuscript — choosing the right machinery (duality, dynamic programming, probabilistic coupling, convergence analysis, simulation output analysis) to actually establish the claimed results. Establishes the results; it does not state the model (ors-theory-development) or run the experiments (ors-data-analysis).

Use when responding to an Operations Research (OR) decision letter — writing the point-by-point response, closing proof gaps, adding baselines/instances, and passing the ORJournal code/data reproducibility review across a revision cycle. Drafts the revision and response; it does not parse the decision in the first place (ors-review-process) or run the final preflight (ors-submission).

Use when navigating the Operations Research (OR) editorial process — the departmental area-editor routing, the soft double-anonymous model with asymmetric transparency, decision types, and how to read a decision letter from the handling Area Editor. Explains how review works and how to read a decision; it does not draft the response (ors-rebuttal) or run the preflight (ors-submission).